{ "format_version": "0.1.0a", "format_revision": 11, "generated_at": "2026-10-05T06:41:09.650609Z", "processing_seconds": 0.6801, "source": { "filename": "insurance-customers.csv", "format": "csv", "size_bytes": 827600, "sha256": "19a6bbb20f91125c6d212c74bfe7d9b8710f114e36042a3179dfec6f18b62389", "encoding": "utf-8-sig", "delimiter": "," }, "config": { "string_analysis": { "very_short_max_length": 5, "short_max_length": 20, "medium_max_length": 50, "long_max_length": 255, "length_distribution_max_length": 50, "examples_per_length": 10 }, "value_examples": { "full_distribution_max_distinct": 50, "short_text_max_length": 20, "short_text_percentile": 0.95, "short_text_result_size": 20, "long_text_result_size": 20, "long_text_truncate_at": 30, "truncation_suffix": "...", "inline_display_size": 3 }, "scan": { "csv": { "encoding": "utf-8-sig", "delimiter": "," }, "json": { "collections": null, "discovery_max_depth": 3, "flatten": { "enabled": true, "separator": ".", "max_depth": null }, "arrays": { "mode": "preserve" } }, "excel": { "dataset_path": null, "header_row": null }, "errors": { "policy": "strict", "max_locations": 10 }, "values": { "null_markers": [ "N/A", "NULL" ], "null_markers_case_sensitive": true, "missing": [ "absent", "null", "empty", "blank", "marker" ] }, "normalization": { "nfc": true, "trim": true, "collapse_whitespace": true, "casefold": true, "strip_accents": true }, "limits": { "max_fields": 10000, "max_depth": 64, "max_record_observations": 100000, "max_line_bytes": 16777216, "max_distinct_per_field": 100000, "max_tracked_values": 2000000, "max_stored_value_length": 1000, "max_listed_frequencies": 100, "max_samples": 100, "max_variant_groups": 100, "max_variants_per_group": 20, "max_evidence_examples": 10, "max_tracked_records": 2000000, "max_listed_records": 10 }, "records": { "preview": 20, "duplicates": true }, "types": { "minimum_confidence": 0.95 }, "detection": { "minimum_share": 0.95, "warmup_values": 10000, "probe_interval": 100, "rare_share": 0.001 }, "detectors": { "number": { "enabled": true, "conventions": [ "dot", "comma" ], "ambiguous_convention": null }, "date": { "enabled": true, "orders": [ "YMD", "MDY", "DMY" ], "separators": [ "-", "/", "." ], "ambiguous_order": null, "month_languages": [ "en", "fr" ] }, "boolean": { "enabled": true, "pairs": [ [ "true", "false" ], [ "yes", "no" ], [ "y", "n" ], [ "oui", "non" ], [ "vrai", "faux" ] ] }, "enumeration": { "enabled": true, "minimum_values": 500, "maximum_distinct": 49, "case_sensitive": true }, "email": { "enabled": true, "max_tracked_domains": 10000, "max_listed_domains": 20 }, "url": { "enabled": true, "schemes": [ "http", "https", "ftp" ], "www": true, "max_tracked_hosts": 10000, "max_listed_hosts": 20 }, "phone": { "enabled": true, "regions": [ "nanp", "fr" ] }, "postal_code": { "enabled": true, "regions": [ "ca", "us" ] }, "currency": { "enabled": true, "conventions": [ "dot", "comma" ], "ambiguous_convention": null }, "percentage": { "enabled": true, "conventions": [ "dot", "comma" ], "ambiguous_convention": null }, "quantity": { "enabled": true, "conventions": [ "dot", "comma" ], "ambiguous_convention": null, "max_tracked_units": 10000, "max_listed_units": 20 }, "uuid": { "enabled": true }, "ip_address": { "enabled": true, "versions": [ "ipv4", "ipv6" ] } }, "patterns": [], "exposure": { "sensitive_values": "mask" }, "random_seed": 42 } }, "datasets": [ { "id": "rows", "kind": "table", "summary": { "row_count": 3000, "column_count": 34, "cell_count": 102000, "missing_count": 12532, "missing_percent": 12.29, "trim_count": 0, "collapse_internal_whitespace_count": 129, "duplicate_row_count": 8, "duplicate_row_status": "complete", "empty_row_count": 0, "empty_column_count": 0, "constant_column_count": 0, "with_issues_column_count": 15, "numeric_column_count": 4, "date_column_count": 6, "string_column_count": 24, "inferred_type_counts": { "text": 24, "date": 6, "integer": 2, "number": 2 }, "inferred_type_percents": { "text": 70.59, "date": 17.65, "integer": 5.88, "number": 5.88 }, "semantic_type_counts": { "enumeration": 14, "none": 11, "date": 6, "postal_code": 1, "email": 1, "phone": 1 }, "semantic_type_percents": { "enumeration": 41.18, "none": 32.35, "date": 17.65, "postal_code": 2.94, "email": 2.94, "phone": 2.94 } }, "date_summary": { "present_count": 14912, "valid_count": 13259, "ambiguous_count": 1630, "ambiguous_percent": 10.93, "invalid_date_count": 23, "not_date_count": 0, "maximum_column_ambiguous_count": 356, "columns": [ { "column_id": "column_6", "name": "date_naissance", "position": 6, "ambiguous_count": 356, "relative_ambiguous_percent": 100.0 }, { "column_id": "column_23", "name": "date_debut", "position": 23, "ambiguous_count": 335, "relative_ambiguous_percent": 94.1 }, { "column_id": "column_24", "name": "date_fin", "position": 24, "ambiguous_count": 274, "relative_ambiguous_percent": 76.97 }, { "column_id": "column_30", "name": "date_creation", "position": 30, "ambiguous_count": 299, "relative_ambiguous_percent": 83.99 }, { "column_id": "column_31", "name": "date_modification", "position": 31, "ambiguous_count": 313, "relative_ambiguous_percent": 87.92 }, { "column_id": "column_32", "name": "date_reclamation", "position": 32, "ambiguous_count": 53, "relative_ambiguous_percent": 14.89 } ] }, "columns": [ { "id": "column_1", "name": "filiale", "path": "filiale", "position": 1, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 3, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 3, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 3, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 3, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 3, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 3, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 3, "examples": [ "principal", "quebec", "ontario" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 3, "values": [ { "value": "principal", "count": 2185, "truncated": false }, { "value": "quebec", "count": 568, "truncated": false }, { "value": "ontario", "count": 247, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 3000, "minimum_length": 6, "maximum_length": 9, "mean_length": 8.27, "median_length": 9.0, "distinct_length_count": 3, "fixed_length": null, "length_distribution": [ { "length": 6, "count": 568, "percent": 18.93, "relative_percent": 26.0, "examples": [ { "value": "quebec", "count": 568 } ] }, { "length": 7, "count": 247, "percent": 8.23, "relative_percent": 11.3, "examples": [ { "value": "ontario", "count": 247 } ] }, { "length": 9, "count": 2185, "percent": 72.83, "relative_percent": 100.0, "examples": [ { "value": "principal", "count": 2185 } ] } ], "representative_examples": [ "principal", "quebec", "ontario" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "principal", "ontario", "quebec" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 3 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "principal", "type": "string", "record": 1 }, "last": { "value": "quebec", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 3000, "mixed_case": 0, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 6, "max_length": 9, "mean_length": 8.267333333333333, "median_length": 9, "length_histogram": [ { "length": 6, "count": 568 }, { "length": 7, "count": 247 }, { "length": 9, "count": 2185 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_2", "name": "id_client", "path": "id_client", "position": 2, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2992, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2992, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2992, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2992, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 3000, "changed_percent": 100.0, "distinct_count": 2992, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2992, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2992, "examples": [ "CLI-00002347", "CLI-00055908", "CLI-00090070" ], "value_profile": { "selection": "diverse_sample", "sampled_distinct_count": 100, "values": [ { "value": "CLI-00002347", "count": 2, "truncated": false }, { "value": "CLI-00055908", "count": 2, "truncated": false }, { "value": "CLI-00090070", "count": 2, "truncated": false }, { "value": "CLI-00006847", "count": 1, "truncated": false }, { "value": "CLI-00039141", "count": 1, "truncated": false }, { "value": "CLI-00060958", "count": 1, "truncated": false }, { "value": "CLI-00064436", "count": 1, "truncated": false }, { "value": "CLI-00073463", "count": 1, "truncated": false }, { "value": "CLI-00128253", "count": 1, "truncated": false }, { "value": "CLI-00144919", "count": 1, "truncated": false }, { "value": "CLI-00159408", "count": 1, "truncated": false }, { "value": "CLI-00181670", "count": 1, "truncated": false }, { "value": "CLI-00193541", "count": 1, "truncated": false }, { "value": "ONT0002696", "count": 1, "truncated": false }, { "value": "ONT0007921", "count": 1, "truncated": false }, { "value": "ONT0011490", "count": 1, "truncated": false }, { "value": "ONT0018008", "count": 1, "truncated": false }, { "value": "QC-0002-9919", "count": 1, "truncated": false }, { "value": "QC-0003-4507", "count": 1, "truncated": false }, { "value": "QC-0004-1864", "count": 1, "truncated": false } ] }, "semantic_type": null, "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 3000, "minimum_length": 9, "maximum_length": 13, "mean_length": 11.83, "median_length": 12.0, "distinct_length_count": 5, "fixed_length": null, "length_distribution": [ { "length": 9, "count": 1, "percent": 0.03, "relative_percent": 0.04, "examples": [] }, { "length": 10, "count": 246, "percent": 8.2, "relative_percent": 9.05, "examples": [ { "value": "ONT0011035", "count": 2 }, { "value": "ONT0000982", "count": 1 }, { "value": "ONT0002696", "count": 1 }, { "value": "ONT0004892", "count": 1 }, { "value": "ONT0004923", "count": 1 }, { "value": "ONT0007842", "count": 1 }, { "value": "ONT0007921", "count": 1 }, { "value": "ONT0011463", "count": 1 }, { "value": "ONT0011490", "count": 1 }, { "value": "ONT0015049", "count": 1 } ] }, { "length": 11, "count": 19, "percent": 0.63, "relative_percent": 0.7, "examples": [ { "value": "CLI-0000043", "count": 1 }, { "value": "CLI-0000072", "count": 1 } ] }, { "length": 12, "count": 2717, "percent": 90.57, "relative_percent": 100.0, "examples": [ { "value": "CLI-00002347", "count": 2 }, { "value": "CLI-00055908", "count": 2 }, { "value": "CLI-00090070", "count": 2 }, { "value": "CLI-00103032", "count": 2 }, { "value": "CLI-00141576", "count": 2 }, { "value": "CLI-00190952", "count": 2 }, { "value": "CLI-00194194", "count": 2 }, { "value": "CLI-00000012", "count": 1 }, { "value": "CLI-00000020", "count": 1 }, { "value": "CLI-00000037", "count": 1 } ] }, { "length": 13, "count": 17, "percent": 0.57, "relative_percent": 0.63, "examples": [ { "value": "CLI--00001642", "count": 1 }, { "value": "CLI--00019558", "count": 1 }, { "value": "CLI--00028886", "count": 1 }, { "value": "CLI--00058765", "count": 1 }, { "value": "CLI--00107966", "count": 1 }, { "value": "CLI--00111170", "count": 1 }, { "value": "CLI--00113511", "count": 1 }, { "value": "CLI--00123143", "count": 1 }, { "value": "CLI--00136985", "count": 1 }, { "value": "CLI--00139003", "count": 1 } ] } ], "representative_examples": [ "CLI-00002347", "ONT0011035", "CLI-0000043" ] }, "numeric": null, "detectors": [], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "CLI-00000281", "type": "string", "record": 1 }, "last": { "value": "QC-0004-9871", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 3000, "lowercase": 0, "mixed_case": 0, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 9, "max_length": 13, "mean_length": 11.834333333333333, "median_length": 12, "length_histogram": [ { "length": 9, "count": 1 }, { "length": 10, "count": 246 }, { "length": 11, "count": 19 }, { "length": 12, "count": 2717 }, { "length": 13, "count": 17 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_3", "name": "civilite", "path": "civilite", "position": 3, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 3000, "changed_percent": 100.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2, "examples": [ "M.", "Mme" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 2, "values": [ { "value": "M.", "count": 1517, "truncated": false }, { "value": "Mme", "count": 1483, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "very_short", "present_count": 3000, "minimum_length": 2, "maximum_length": 3, "mean_length": 2.49, "median_length": 2.0, "distinct_length_count": 2, "fixed_length": null, "length_distribution": [ { "length": 2, "count": 1517, "percent": 50.57, "relative_percent": 100.0, "examples": [ { "value": "M.", "count": 1517 } ] }, { "length": 3, "count": 1483, "percent": 49.43, "relative_percent": 97.76, "examples": [ { "value": "Mme", "count": 1483 } ] } ], "representative_examples": [ "M.", "Mme" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "Mme", "M." ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 2 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "Mme", "type": "string", "record": 1 }, "last": { "value": "Mme", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 1517, "lowercase": 0, "mixed_case": 1483, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 2, "max_length": 3, "mean_length": 2.4943333333333335, "median_length": 2, "length_histogram": [ { "length": 2, "count": 1517 }, { "length": 3, "count": 1483 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_4", "name": "prenom", "path": "prenom", "position": 4, "inferred_type": "text", "type_counts": { "text": 2993 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 7, "missing_percent": 0.23, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 6, "collapse_internal_whitespace_percent": 0.2, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 227, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 227, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 227, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 6, "changed_percent": 0.2, "distinct_count": 227, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 2983, "changed_percent": 99.43, "distinct_count": 218, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 536, "changed_percent": 17.87, "distinct_count": 213, "distinct_status": "complete" } ], "variant_group_count": 13, "variant_group_status": "complete", "variant_groups": [ { "key": "daniel", "count": 48, "distinct_count": 2, "variants": [ { "value": "Daniel", "count": 47 }, { "value": "daniel", "count": 1 } ], "truncated": false }, { "key": "melanie", "count": 36, "distinct_count": 2, "variants": [ { "value": "Mélanie", "count": 35 }, { "value": "melanie", "count": 1 } ], "truncated": false }, { "key": "sylvie", "count": 36, "distinct_count": 2, "variants": [ { "value": "Sylvie", "count": 35 }, { "value": "sylvie", "count": 1 } ], "truncated": false }, { "key": "diane", "count": 25, "distinct_count": 2, "variants": [ { "value": "Diane", "count": 24 }, { "value": "diane", "count": 1 } ], "truncated": false }, { "key": "francois", "count": 25, "distinct_count": 3, "variants": [ { "value": "François", "count": 23 }, { "value": "Francois", "count": 1 }, { "value": "francois", "count": 1 } ], "truncated": false }, { "key": "veronique", "count": 24, "distinct_count": 2, "variants": [ { "value": "Véronique", "count": 23 }, { "value": "Veronique", "count": 1 } ], "truncated": false }, { "key": "leo", "count": 23, "distinct_count": 2, "variants": [ { "value": "Léo", "count": 17 }, { "value": "Leo", "count": 6 } ], "truncated": false }, { "key": "pierre", "count": 23, "distinct_count": 2, "variants": [ { "value": "Pierre", "count": 22 }, { "value": "pierre", "count": 1 } ], "truncated": false }, { "key": "lucas", "count": 20, "distinct_count": 2, "variants": [ { "value": "Lucas", "count": 19 }, { "value": "lucas", "count": 1 } ], "truncated": false }, { "key": "florence", "count": 19, "distinct_count": 2, "variants": [ { "value": "Florence", "count": 18 }, { "value": "florence", "count": 1 } ], "truncated": false }, { "key": "louis-philippe", "count": 17, "distinct_count": 2, "variants": [ { "value": "Louis-Philippe", "count": 16 }, { "value": "louis-philippe", "count": 1 } ], "truncated": false }, { "key": "sofia", "count": 15, "distinct_count": 2, "variants": [ { "value": "Sofia", "count": 14 }, { "value": "sofia", "count": 1 } ], "truncated": false }, { "key": "zoe", "count": 13, "distinct_count": 2, "variants": [ { "value": "Zoé", "count": 12 }, { "value": "Zoe", "count": 1 } ], "truncated": false } ], "variant_groups_truncated": false }, "distinct_count": 227, "examples": [ "Daniel", "Robert", "Sophie" ], "value_profile": { "selection": "diverse_sample", "sampled_distinct_count": 100, "values": [ { "value": "Daniel", "count": 47, "truncated": false }, { "value": "Robert", "count": 38, "truncated": false }, { "value": "Sophie", "count": 38, "truncated": false }, { "value": "Louise", "count": 26, "truncated": false }, { "value": "Martin", "count": 25, "truncated": false }, { "value": "Stéphane", "count": 22, "truncated": false }, { "value": "Audrey", "count": 21, "truncated": false }, { "value": "Thomas", "count": 19, "truncated": false }, { "value": "Pierre-Luc", "count": 17, "truncated": false }, { "value": "Ezra", "count": 16, "truncated": false }, { "value": "Elizabeth", "count": 15, "truncated": false }, { "value": "Olivia", "count": 15, "truncated": false }, { "value": "Jack", "count": 14, "truncated": false }, { "value": "Evelyn", "count": 13, "truncated": false }, { "value": "Gianna", "count": 13, "truncated": false }, { "value": "Hugo", "count": 12, "truncated": false }, { "value": "Jean-Philippe", "count": 12, "truncated": false }, { "value": "Zoé", "count": 12, "truncated": false }, { "value": "Floorence", "count": 1, "truncated": false }, { "value": "Noa h", "count": 1, "truncated": false } ] }, "semantic_type": null, "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 2993, "minimum_length": 3, "maximum_length": 14, "mean_length": 6.29, "median_length": 6.0, "distinct_length_count": 12, "fixed_length": null, "length_distribution": [ { "length": 3, "count": 113, "percent": 3.78, "relative_percent": 15.35, "examples": [ { "value": "Luc", "count": 25 }, { "value": "Ava", "count": 22 }, { "value": "Léo", "count": 17 }, { "value": "Léa", "count": 15 }, { "value": "Mia", "count": 14 }, { "value": "Zoé", "count": 12 }, { "value": "Zoe", "count": 1 } ] }, { "length": 4, "count": 376, "percent": 12.56, "relative_percent": 51.09, "examples": [ { "value": "Marc", "count": 34 }, { "value": "Jean", "count": 32 }, { "value": "Éric", "count": 30 }, { "value": "Liam", "count": 29 }, { "value": "Anne", "count": 24 }, { "value": "Nova", "count": 18 }, { "value": "Emma", "count": 16 }, { "value": "Ezra", "count": 16 }, { "value": "Levi", "count": 16 }, { "value": "Luna", "count": 15 } ] }, { "length": 5, "count": 629, "percent": 21.02, "relative_percent": 85.46, "examples": [ { "value": "Julie", "count": 34 }, { "value": "André", "count": 33 }, { "value": "Serge", "count": 31 }, { "value": "Alain", "count": 30 }, { "value": "Denis", "count": 27 }, { "value": "Marie", "count": 26 }, { "value": "Diane", "count": 24 }, { "value": "Josée", "count": 24 }, { "value": "Lucie", "count": 24 }, { "value": "Mateo", "count": 22 } ] }, { "length": 6, "count": 736, "percent": 24.59, "relative_percent": 100.0, "examples": [ { "value": "Daniel", "count": 47 }, { "value": "Robert", "count": 38 }, { "value": "Sophie", "count": 38 }, { "value": "Claude", "count": 37 }, { "value": "Sylvie", "count": 35 }, { "value": "Michel", "count": 32 }, { "value": "Louise", "count": 26 }, { "value": "Martin", "count": 25 }, { "value": "Gilles", "count": 24 }, { "value": "Samuel", "count": 24 } ] }, { "length": 7, "count": 421, "percent": 14.07, "relative_percent": 57.2, "examples": [ { "value": "Mélanie", "count": 35 }, { "value": "William", "count": 29 }, { "value": "Jacques", "count": 24 }, { "value": "Mathieu", "count": 24 }, { "value": "Nicolas", "count": 24 }, { "value": "Valérie", "count": 24 }, { "value": "Gabriel", "count": 22 }, { "value": "Suzanne", "count": 22 }, { "value": "Patrick", "count": 21 }, { "value": "Chantal", "count": 20 } ] }, { "length": 8, "count": 304, "percent": 10.16, "relative_percent": 41.3, "examples": [ { "value": "Isabelle", "count": 35 }, { "value": "Caroline", "count": 31 }, { "value": "Nathalie", "count": 27 }, { "value": "François", "count": 23 }, { "value": "Stéphane", "count": 22 }, { "value": "Philippe", "count": 21 }, { "value": "Béatrice", "count": 19 }, { "value": "Florence", "count": 18 }, { "value": "Theodore", "count": 16 }, { "value": "Benjamin", "count": 15 } ] }, { "length": 9, "count": 285, "percent": 9.52, "relative_percent": 38.72, "examples": [ { "value": "Charlotte", "count": 33 }, { "value": "Stéphanie", "count": 33 }, { "value": "Catherine", "count": 28 }, { "value": "Véronique", "count": 23 }, { "value": "Alexandre", "count": 22 }, { "value": "Sébastien", "count": 21 }, { "value": "Christine", "count": 20 }, { "value": "Marie-Ève", "count": 20 }, { "value": "Gabrielle", "count": 19 }, { "value": "Geneviève", "count": 19 } ] }, { "length": 10, "count": 59, "percent": 1.97, "relative_percent": 8.02, "examples": [ { "value": "Pierre-Luc", "count": 17 }, { "value": "Marc-André", "count": 11 }, { "value": "MMarie-Ève", "count": 1 } ] }, { "length": 11, "count": 13, "percent": 0.43, "relative_percent": 1.77, "examples": [] }, { "length": 12, "count": 14, "percent": 0.47, "relative_percent": 1.9, "examples": [ { "value": "Marie-Claude", "count": 14 } ] }, { "length": 13, "count": 26, "percent": 0.87, "relative_percent": 3.53, "examples": [ { "value": "Jean-François", "count": 14 }, { "value": "Jean-Philippe", "count": 12 } ] }, { "length": 14, "count": 17, "percent": 0.57, "relative_percent": 2.31, "examples": [ { "value": "Louis-Philippe", "count": 16 } ] } ], "representative_examples": [ "Daniel", "Julie", "Mélanie" ] }, "numeric": null, "detectors": [], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 2993, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 7, "blank": 0, "marker": 0, "content": 2993 }, "missing": { "count": 7, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 7, "blank": 0, "marker": 0 } }, "first": { "value": "Lucie", "type": "string", "record": 1 }, "last": { "value": "Sophie", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 536, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 6, "uppercase": 0, "lowercase": 10, "mixed_case": 2983, "no_letters": 0 }, "string_lengths": { "count": 2993, "min_length": 3, "max_length": 14, "mean_length": 6.289675910457735, "median_length": 6, "length_histogram": [ { "length": 3, "count": 113 }, { "length": 4, "count": 376 }, { "length": 5, "count": 629 }, { "length": 6, "count": 736 }, { "length": 7, "count": 421 }, { "length": 8, "count": 304 }, { "length": 9, "count": 285 }, { "length": 10, "count": 59 }, { "length": 11, "count": 13 }, { "length": 12, "count": 14 }, { "length": 13, "count": 26 }, { "length": 14, "count": 17 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_5", "name": "nom", "path": "nom", "position": 5, "inferred_type": "text", "type_counts": { "text": 2996 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 4, "missing_percent": 0.13, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 5, "collapse_internal_whitespace_percent": 0.17, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 214, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 214, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 214, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 5, "changed_percent": 0.17, "distinct_count": 214, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 2980, "changed_percent": 99.33, "distinct_count": 203, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 260, "changed_percent": 8.67, "distinct_count": 202, "distinct_status": "complete" } ], "variant_group_count": 12, "variant_group_status": "complete", "variant_groups": [ { "key": "fortin", "count": 68, "distinct_count": 2, "variants": [ { "value": "Fortin", "count": 67 }, { "value": "fortin", "count": 1 } ], "truncated": false }, { "key": "gagnon", "count": 60, "distinct_count": 2, "variants": [ { "value": "Gagnon", "count": 59 }, { "value": "gagnon", "count": 1 } ], "truncated": false }, { "key": "wilson", "count": 43, "distinct_count": 2, "variants": [ { "value": "Wilson", "count": 42 }, { "value": "wilson", "count": 1 } ], "truncated": false }, { "key": "poirier", "count": 32, "distinct_count": 2, "variants": [ { "value": "Poirier", "count": 31 }, { "value": "poirier", "count": 1 } ], "truncated": false }, { "key": "dube", "count": 30, "distinct_count": 2, "variants": [ { "value": "Dubé", "count": 29 }, { "value": "dube", "count": 1 } ], "truncated": false }, { "key": "cloutier", "count": 28, "distinct_count": 2, "variants": [ { "value": "Cloutier", "count": 27 }, { "value": "cloutier", "count": 1 } ], "truncated": false }, { "key": "martel", "count": 28, "distinct_count": 2, "variants": [ { "value": "Martel", "count": 27 }, { "value": "martel", "count": 1 } ], "truncated": false }, { "key": "baker", "count": 23, "distinct_count": 2, "variants": [ { "value": "Baker", "count": 22 }, { "value": "baker", "count": 1 } ], "truncated": false }, { "key": "michaud", "count": 21, "distinct_count": 2, "variants": [ { "value": "Michaud", "count": 20 }, { "value": "michaud", "count": 1 } ], "truncated": false }, { "key": "evans", "count": 12, "distinct_count": 2, "variants": [ { "value": "Evans", "count": 11 }, { "value": "evans", "count": 1 } ], "truncated": false }, { "key": "collins", "count": 11, "distinct_count": 2, "variants": [ { "value": "Collins", "count": 10 }, { "value": "collins", "count": 1 } ], "truncated": false }, { "key": "ho", "count": 5, "distinct_count": 2, "variants": [ { "value": "Ho", "count": 4 }, { "value": "ho", "count": 1 } ], "truncated": false } ], "variant_groups_truncated": false }, "distinct_count": 214, "examples": [ "Roy", "Tremblay", "Fortin" ], "value_profile": { "selection": "diverse_sample", "sampled_distinct_count": 100, "values": [ { "value": "Roy", "count": 73, "truncated": false }, { "value": "Tremblay", "count": 72, "truncated": false }, { "value": "Fortin", "count": 67, "truncated": false }, { "value": "Poirier", "count": 31, "truncated": false }, { "value": "Scott", "count": 27, "truncated": false }, { "value": "Nadeau", "count": 16, "truncated": false }, { "value": "Adams", "count": 14, "truncated": false }, { "value": "Roberts", "count": 9, "truncated": false }, { "value": "Wu", "count": 6, "truncated": false }, { "value": "Zhang", "count": 5, "truncated": false }, { "value": "O'Connor", "count": 3, "truncated": false }, { "value": "Clarkk", "count": 1, "truncated": false }, { "value": "De Luca", "count": 1, "truncated": false }, { "value": "Halll", "count": 1, "truncated": false }, { "value": "Tremblayy", "count": 1, "truncated": false }, { "value": "WWright", "count": 1, "truncated": false }, { "value": "aSvard", "count": 1, "truncated": false }, { "value": "eLfebvre", "count": 1, "truncated": false }, { "value": "karquis", "count": 1, "truncated": false }, { "value": "wilson", "count": 1, "truncated": false } ] }, "semantic_type": null, "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 2996, "minimum_length": 2, "maximum_length": 10, "mean_length": 6.22, "median_length": 6.0, "distinct_length_count": 9, "fixed_length": null, "length_distribution": [ { "length": 2, "count": 46, "percent": 1.54, "relative_percent": 6.08, "examples": [ { "value": "Li", "count": 22 }, { "value": "Le", "count": 13 }, { "value": "Wu", "count": 6 }, { "value": "ho", "count": 1 } ] }, { "length": 3, "count": 151, "percent": 5.04, "relative_percent": 19.97, "examples": [ { "value": "Roy", "count": 73 }, { "value": "Lee", "count": 29 }, { "value": "Kim", "count": 17 }, { "value": "Ali", "count": 14 }, { "value": "Cox", "count": 11 } ] }, { "length": 4, "count": 247, "percent": 8.24, "relative_percent": 32.67, "examples": [ { "value": "Côté", "count": 64 }, { "value": "Dubé", "count": 29 }, { "value": "Chen", "count": 28 }, { "value": "Wong", "count": 21 }, { "value": "King", "count": 18 }, { "value": "Hall", "count": 17 }, { "value": "Khan", "count": 10 }, { "value": "Pham", "count": 10 }, { "value": "Cook", "count": 6 }, { "value": "Park", "count": 6 } ] }, { "length": 5, "count": 529, "percent": 17.66, "relative_percent": 69.97, "examples": [ { "value": "Morin", "count": 59 }, { "value": "Smith", "count": 52 }, { "value": "Gagné", "count": 51 }, { "value": "Lewis", "count": 36 }, { "value": "Brown", "count": 34 }, { "value": "Caron", "count": 33 }, { "value": "White", "count": 33 }, { "value": "Scott", "count": 27 }, { "value": "Patel", "count": 24 }, { "value": "Clark", "count": 23 } ] }, { "length": 6, "count": 756, "percent": 25.23, "relative_percent": 100.0, "examples": [ { "value": "Fortin", "count": 67 }, { "value": "Lavoie", "count": 62 }, { "value": "Gagnon", "count": 59 }, { "value": "Taylor", "count": 47 }, { "value": "Girard", "count": 42 }, { "value": "Wilson", "count": 42 }, { "value": "Simard", "count": 36 }, { "value": "Martel", "count": 27 }, { "value": "Nguyen", "count": 27 }, { "value": "Poulin", "count": 26 } ] }, { "length": 7, "count": 385, "percent": 12.85, "relative_percent": 50.93, "examples": [ { "value": "Ouellet", "count": 50 }, { "value": "Leblanc", "count": 46 }, { "value": "Boucher", "count": 43 }, { "value": "Johnson", "count": 42 }, { "value": "Poirier", "count": 31 }, { "value": "Leclerc", "count": 29 }, { "value": "Grenier", "count": 24 }, { "value": "Michaud", "count": 20 }, { "value": "Marquis", "count": 15 }, { "value": "Cormier", "count": 12 } ] }, { "length": 8, "count": 735, "percent": 24.53, "relative_percent": 97.22, "examples": [ { "value": "Tremblay", "count": 72 }, { "value": "Bouchard", "count": 66 }, { "value": "Gauthier", "count": 60 }, { "value": "Bergeron", "count": 48 }, { "value": "Bélanger", "count": 44 }, { "value": "Lévesque", "count": 43 }, { "value": "Paquette", "count": 36 }, { "value": "Thompson", "count": 36 }, { "value": "Campbell", "count": 33 }, { "value": "Beaulieu", "count": 31 } ] }, { "length": 9, "count": 125, "percent": 4.17, "relative_percent": 16.53, "examples": [ { "value": "Pelletier", "count": 54 }, { "value": "St-Pierre", "count": 23 }, { "value": "Rodriguez", "count": 14 }, { "value": "Fernandes", "count": 10 }, { "value": "Chowdhury", "count": 9 }, { "value": "Hernandez", "count": 8 }, { "value": "C ampbell", "count": 1 }, { "value": "CCloutier", "count": 1 }, { "value": "Rdoriguez", "count": 1 }, { "value": "Tremblayy", "count": 1 } ] }, { "length": 10, "count": 22, "percent": 0.73, "relative_percent": 2.91, "examples": [ { "value": "Desjardins", "count": 15 }, { "value": "Richardson", "count": 5 }, { "value": "P elletier", "count": 1 }, { "value": "RRodriguez", "count": 1 } ] } ], "representative_examples": [ "Fortin", "Tremblay", "Morin" ] }, "numeric": null, "detectors": [], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 2996, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 4, "blank": 0, "marker": 0, "content": 2996 }, "missing": { "count": 4, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 4, "blank": 0, "marker": 0 } }, "first": { "value": "Roy", "type": "string", "record": 1 }, "last": { "value": "Morin", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 260, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 5, "uppercase": 0, "lowercase": 16, "mixed_case": 2980, "no_letters": 0 }, "string_lengths": { "count": 2996, "min_length": 2, "max_length": 10, "mean_length": 6.219626168224299, "median_length": 6, "length_histogram": [ { "length": 2, "count": 46 }, { "length": 3, "count": 151 }, { "length": 4, "count": 247 }, { "length": 5, "count": 529 }, { "length": 6, "count": 756 }, { "length": 7, "count": 385 }, { "length": 8, "count": 735 }, { "length": 9, "count": 125 }, { "length": 10, "count": 22 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_6", "name": "date_naissance", "path": "date_naissance", "position": 6, "inferred_type": "date", "type_counts": { "date": 2991, "text": 3 }, "type_confidence": 0.999, "type_error_count": 3, "type_error_percent": 0.1, "missing_count": 6, "missing_percent": 0.2, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2889, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2889, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2889, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2889, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2889, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2889, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2889, "examples": [ "1939-11-09", "2000-12-20", "2026-13-40" ], "value_profile": { "selection": "random_sample", "sampled_distinct_count": 100, "values": [ { "value": "1939-11-09", "count": 3, "truncated": false }, { "value": "2000-12-20", "count": 3, "truncated": false }, { "value": "2026-13-40", "count": 3, "truncated": false }, { "value": "09-25-1942", "count": 1, "truncated": false }, { "value": "12-06-1985", "count": 1, "truncated": false }, { "value": "15-04-1988", "count": 1, "truncated": false }, { "value": "18-07-1986", "count": 1, "truncated": false }, { "value": "1937-09-30", "count": 1, "truncated": false }, { "value": "1940-04-26", "count": 1, "truncated": false }, { "value": "1949-08-25", "count": 1, "truncated": false }, { "value": "1951-09-23", "count": 1, "truncated": false }, { "value": "1968/12/04", "count": 1, "truncated": false }, { "value": "1979-06-17", "count": 1, "truncated": false }, { "value": "1981-04-22", "count": 1, "truncated": false }, { "value": "1986-02-01", "count": 1, "truncated": false }, { "value": "1987-05-18", "count": 1, "truncated": false }, { "value": "1987-12-10", "count": 1, "truncated": false }, { "value": "1998-02-18", "count": 1, "truncated": false }, { "value": "20-10-1979", "count": 1, "truncated": false }, { "value": "2007-07-24", "count": 1, "truncated": false } ] }, "semantic_type": "date", "exposure": null, "date_profile": { "status": "mixed", "present_count": 2994, "valid_count": 2635, "valid_percent": 88.01, "ambiguous_count": 356, "ambiguous_percent": 11.89, "invalid_date_count": 3, "invalid_date_percent": 0.1, "not_date_count": 0, "not_date_percent": 0.0, "resolved_ambiguous_order": null, "ambiguous_order_source": null, "ambiguity_evidence": { "DMY": 325, "MDY": 138 }, "formats": [ { "format": "YYYY-MM-DD", "order": "YMD", "separator": "-", "count": 2166, "percent": 72.34, "iso": true }, { "format": "DD-MM-YYYY", "order": "DMY", "separator": "-", "count": 323, "percent": 10.79, "iso": false }, { "format": "MM-DD-YYYY", "order": "MDY", "separator": "-", "count": 137, "percent": 4.58, "iso": false }, { "format": "YYYY/MM/DD", "order": "YMD", "separator": "/", "count": 6, "percent": 0.2, "iso": false }, { "format": "DD/MM/YYYY", "order": "DMY", "separator": "/", "count": 2, "percent": 0.07, "iso": false }, { "format": "MM/DD/YYYY", "order": "MDY", "separator": "/", "count": 1, "percent": 0.03, "iso": false } ], "format_count": 6, "breakdown": [ { "label": "YYYY-MM-DD", "category": "valid", "count": 2166, "percent": 72.34 }, { "label": "Ambiguous: DD-MM-YYYY or MM-DD-YYYY", "category": "ambiguous", "count": 356, "percent": 11.89 }, { "label": "DD-MM-YYYY", "category": "valid", "count": 323, "percent": 10.79 }, { "label": "MM-DD-YYYY", "category": "valid", "count": 137, "percent": 4.58 }, { "label": "YYYY/MM/DD", "category": "valid", "count": 6, "percent": 0.2 }, { "label": "DD/MM/YYYY", "category": "valid", "count": 2, "percent": 0.07 }, { "label": "MM/DD/YYYY", "category": "valid", "count": 1, "percent": 0.03 }, { "label": "Invalid date", "category": "invalid", "count": 3, "percent": 0.1 }, { "label": "Not a date", "category": "not_date", "count": 0, "percent": 0.0 } ] }, "string_profile": null, "numeric": null, "detectors": [ { "id": "date", "status": "complete", "primary": false, "eligible_count": 2994, "matched_count": 2635, "matched_percent": 88.01, "ambiguous_count": 356, "invalid_count": 3, "formats": [ { "format": "YYYY-MM-DD", "count": 2166, "percent": 72.34 }, { "format": "DD-MM-YYYY", "count": 323, "percent": 10.79 }, { "format": "MM-DD-YYYY", "count": 137, "percent": 4.58 }, { "format": "YYYY/MM/DD", "count": 6, "percent": 0.2 }, { "format": "DD/MM/YYYY", "count": 2, "percent": 0.07 }, { "format": "MM/DD/YYYY", "count": 1, "percent": 0.03 } ], "coverage": { "eligible": 2994, "tested": 2994, "matched": 2635, "ambiguous": 356, "invalid": 3, "not_matched": 0, "not_tested": 0, "share_tested": 0.8801, "share_eligible": 0.8801 }, "evidence": { "matched": [ "1961-03-31", "1983-01-14", "1941-09-10", "1936-12-13", "1943-04-16", "1979-07-29", "1996-03-27", "1958-01-22", "1987-11-05", "1981-09-04" ], "ambiguous": [ "11-02-1944", "01-01-2006", "06-02-1974", "11-10-1985", "05-06-1969", "07-10-1983", "03-09-1985", "07-04-1985", "02-11-2005", "12-08-1988" ], "invalid": [ "2026-13-40" ], "not_matched": [] }, "details": { "ambiguity": { "count": 356, "candidates": [ { "formats": [ "DD-MM-YYYY", "MM-DD-YYYY" ], "count": 356 } ], "evidence": { "DMY": 325, "MDY": 138 }, "resolution": null } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 2994, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 6, "blank": 0, "marker": 0, "content": 2994 }, "missing": { "count": 6, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 6, "blank": 0, "marker": 0 } }, "first": { "value": "1961-03-31", "type": "string", "record": 1 }, "last": { "value": "01-10-1949", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 0, "mixed_case": 0, "no_letters": 2994 }, "string_lengths": { "count": 2994, "min_length": 10, "max_length": 10, "mean_length": 10, "median_length": 10, "length_histogram": [ { "length": 10, "count": 2994 } ] }, "numeric": null, "booleans": null, "temporal": { "count": 2635, "ambiguous": 356, "kinds": [ { "kind": "date", "count": 2635, "min": "1936-09-22", "max": "2008-09-16", "years": [ { "year": 1936, "count": 8 }, { "year": 1937, "count": 28 }, { "year": 1938, "count": 33 }, { "year": 1939, "count": 38 }, { "year": 1940, "count": 36 }, { "year": 1941, "count": 33 }, { "year": 1942, "count": 35 }, { "year": 1943, "count": 27 }, { "year": 1944, "count": 48 }, { "year": 1945, "count": 41 }, { "year": 1946, "count": 43 }, { "year": 1947, "count": 38 }, { "year": 1948, "count": 37 }, { "year": 1949, "count": 38 }, { "year": 1950, "count": 38 }, { "year": 1951, "count": 42 }, { "year": 1952, "count": 41 }, { "year": 1953, "count": 38 }, { "year": 1954, "count": 41 }, { "year": 1955, "count": 41 }, { "year": 1956, "count": 37 }, { "year": 1957, "count": 35 }, { "year": 1958, "count": 34 }, { "year": 1959, "count": 31 }, { "year": 1960, "count": 31 }, { "year": 1961, "count": 46 }, { "year": 1962, "count": 41 }, { "year": 1963, "count": 37 }, { "year": 1964, "count": 42 }, { "year": 1965, "count": 50 }, { "year": 1966, "count": 45 }, { "year": 1967, "count": 44 }, { "year": 1968, "count": 41 }, { "year": 1969, "count": 39 }, { "year": 1970, "count": 34 }, { "year": 1971, "count": 34 }, { "year": 1972, "count": 28 }, { "year": 1973, "count": 45 }, { "year": 1974, "count": 31 }, { "year": 1975, "count": 43 }, { "year": 1976, "count": 35 }, { "year": 1977, "count": 22 }, { "year": 1978, "count": 39 }, { "year": 1979, "count": 43 }, { "year": 1980, "count": 34 }, { "year": 1981, "count": 38 }, { "year": 1982, "count": 44 }, { "year": 1983, "count": 34 }, { "year": 1984, "count": 35 }, { "year": 1985, "count": 35 }, { "year": 1986, "count": 40 }, { "year": 1987, "count": 48 }, { "year": 1988, "count": 29 }, { "year": 1989, "count": 31 }, { "year": 1990, "count": 23 }, { "year": 1991, "count": 29 }, { "year": 1992, "count": 27 }, { "year": 1993, "count": 33 }, { "year": 1994, "count": 28 }, { "year": 1995, "count": 46 }, { "year": 1996, "count": 50 }, { "year": 1997, "count": 29 }, { "year": 1998, "count": 30 }, { "year": 1999, "count": 34 }, { "year": 2000, "count": 28 }, { "year": 2001, "count": 36 }, { "year": 2002, "count": 46 }, { "year": 2003, "count": 38 }, { "year": 2004, "count": 27 }, { "year": 2005, "count": 36 }, { "year": 2006, "count": 40 }, { "year": 2007, "count": 32 }, { "year": 2008, "count": 24 } ] } ] } } }, { "id": "column_7", "name": "sexe", "path": "sexe", "position": 7, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 3000, "changed_percent": 100.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2, "examples": [ "M", "F" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 2, "values": [ { "value": "M", "count": 1517, "truncated": false }, { "value": "F", "count": 1483, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "very_short", "present_count": 3000, "minimum_length": 1, "maximum_length": 1, "mean_length": 1.0, "median_length": 1.0, "distinct_length_count": 1, "fixed_length": 1, "length_distribution": [ { "length": 1, "count": 3000, "percent": 100.0, "relative_percent": 100.0, "examples": [ { "value": "M", "count": 1517 }, { "value": "F", "count": 1483 } ] } ], "representative_examples": [ "M" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "F", "M" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 2 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "F", "type": "string", "record": 1 }, "last": { "value": "F", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 3000, "lowercase": 0, "mixed_case": 0, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 1, "max_length": 1, "mean_length": 1, "median_length": 1, "length_histogram": [ { "length": 1, "count": 3000 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_8", "name": "langue_preferee", "path": "langue_preferee", "position": 8, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2, "examples": [ "fr", "en" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 2, "values": [ { "value": "fr", "count": 2101, "truncated": false }, { "value": "en", "count": 899, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "very_short", "present_count": 3000, "minimum_length": 2, "maximum_length": 2, "mean_length": 2.0, "median_length": 2.0, "distinct_length_count": 1, "fixed_length": 2, "length_distribution": [ { "length": 2, "count": 3000, "percent": 100.0, "relative_percent": 100.0, "examples": [ { "value": "fr", "count": 2101 }, { "value": "en", "count": 899 } ] } ], "representative_examples": [ "fr" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "fr", "en" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 2 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "fr", "type": "string", "record": 1 }, "last": { "value": "fr", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 3000, "mixed_case": 0, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 2, "max_length": 2, "mean_length": 2, "median_length": 2, "length_histogram": [ { "length": 2, "count": 3000 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_9", "name": "numero_voie", "path": "numero_voie", "position": 9, "inferred_type": "integer", "type_counts": { "integer": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2576, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2576, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2576, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2576, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2576, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2576, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2576, "examples": [ "4185", "8398", "9730" ], "value_profile": { "selection": "random_sample", "sampled_distinct_count": 100, "values": [ { "value": "4185", "count": 4, "truncated": false }, { "value": "8398", "count": 4, "truncated": false }, { "value": "9730", "count": 4, "truncated": false }, { "value": "3069", "count": 2, "truncated": false }, { "value": "3866", "count": 2, "truncated": false }, { "value": "7447", "count": 2, "truncated": false }, { "value": "9852", "count": 2, "truncated": false }, { "value": "3905", "count": 1, "truncated": false }, { "value": "3932", "count": 1, "truncated": false }, { "value": "5062", "count": 1, "truncated": false }, { "value": "5310", "count": 1, "truncated": false }, { "value": "58", "count": 1, "truncated": false }, { "value": "609", "count": 1, "truncated": false }, { "value": "654", "count": 1, "truncated": false }, { "value": "6959", "count": 1, "truncated": false }, { "value": "7140", "count": 1, "truncated": false }, { "value": "8067", "count": 1, "truncated": false }, { "value": "916", "count": 1, "truncated": false }, { "value": "9295", "count": 1, "truncated": false }, { "value": "9959", "count": 1, "truncated": false } ] }, "semantic_type": null, "exposure": null, "date_profile": null, "string_profile": null, "numeric": { "minimum": 11.0, "maximum": 9999.0, "range": 9988.0, "mean": 4947.492, "median": 4858.0 }, "detectors": [ { "id": "number", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [ { "format": "0", "count": 3000, "percent": 100.0 } ], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "4682", "518", "2943", "6132", "9307", "2174", "909", "6362", "7641", "528" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "ambiguity": { "count": 0, "candidates": [], "evidence": { "comma": 0, "dot": 0 }, "resolution": null } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "4682", "type": "string", "record": 1 }, "last": { "value": "5013", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 0, "mixed_case": 0, "no_letters": 3000 }, "string_lengths": { "count": 3000, "min_length": 2, "max_length": 4, "mean_length": 3.891, "median_length": 4, "length_histogram": [ { "length": 2, "count": 25 }, { "length": 3, "count": 277 }, { "length": 4, "count": 2698 } ] }, "numeric": { "count": 3000, "native_count": 0, "text_count": 3000, "min": 11, "max": 9999, "sum": 14842476, "mean": 4947.492, "population_variance": 8354300.537936, "population_std": 2890.380690832265, "positive": 3000, "negative": 0, "zero": 0, "integral_decimals": 0, "median": { "status": "complete", "value": 4858 } }, "booleans": null, "temporal": null } }, { "id": "column_10", "name": "type_voie", "path": "type_voie", "position": 10, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 31, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 31, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 31, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 31, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 899, "changed_percent": 29.97, "distinct_count": 28, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 185, "changed_percent": 6.17, "distinct_count": 28, "distinct_status": "complete" } ], "variant_group_count": 3, "variant_group_status": "complete", "variant_groups": [ { "key": "avenue", "count": 445, "distinct_count": 2, "variants": [ { "value": "avenue", "count": 324 }, { "value": "Avenue", "count": 121 } ], "truncated": false }, { "key": "boulevard", "count": 409, "distinct_count": 2, "variants": [ { "value": "boulevard", "count": 311 }, { "value": "Boulevard", "count": 98 } ], "truncated": false }, { "key": "place", "count": 116, "distinct_count": 2, "variants": [ { "value": "place", "count": 84 }, { "value": "Place", "count": 32 } ], "truncated": false } ], "variant_groups_truncated": false }, "distinct_count": 31, "examples": [ "rue", "avenue", "boulevard" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 31, "values": [ { "value": "rue", "count": 461, "truncated": false }, { "value": "avenue", "count": 324, "truncated": false }, { "value": "boulevard", "count": 311, "truncated": false }, { "value": "Street", "count": 202, "truncated": false }, { "value": "chemin", "count": 189, "truncated": false }, { "value": "route", "count": 152, "truncated": false }, { "value": "rang", "count": 124, "truncated": false }, { "value": "Avenue", "count": 121, "truncated": false }, { "value": "Road", "count": 99, "truncated": false }, { "value": "Boulevard", "count": 98, "truncated": false }, { "value": "place", "count": 84, "truncated": false }, { "value": "montée", "count": 82, "truncated": false }, { "value": "Drive", "count": 75, "truncated": false }, { "value": "terrasse", "count": 71, "truncated": false }, { "value": "croissant", "count": 70, "truncated": false }, { "value": "Lane", "count": 53, "truncated": false }, { "value": "impasse", "count": 53, "truncated": false }, { "value": "Court", "count": 46, "truncated": false }, { "value": "promenade", "count": 44, "truncated": false }, { "value": "allée", "count": 42, "truncated": false }, { "value": "Crescent", "count": 33, "truncated": false }, { "value": "autoroute", "count": 33, "truncated": false }, { "value": "Place", "count": 32, "truncated": false }, { "value": "côte", "count": 32, "truncated": false }, { "value": "Trail", "count": 31, "truncated": false }, { "value": "carré", "count": 29, "truncated": false }, { "value": "Highway", "count": 27, "truncated": false }, { "value": "Way", "count": 26, "truncated": false }, { "value": "Circle", "count": 20, "truncated": false }, { "value": "Terrace", "count": 19, "truncated": false }, { "value": "Parkway", "count": 17, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 3000, "minimum_length": 3, "maximum_length": 9, "mean_length": 5.81, "median_length": 6.0, "distinct_length_count": 7, "fixed_length": null, "length_distribution": [ { "length": 3, "count": 487, "percent": 16.23, "relative_percent": 51.92, "examples": [ { "value": "rue", "count": 461 }, { "value": "Way", "count": 26 } ] }, { "length": 4, "count": 308, "percent": 10.27, "relative_percent": 32.84, "examples": [ { "value": "rang", "count": 124 }, { "value": "Road", "count": 99 }, { "value": "Lane", "count": 53 }, { "value": "côte", "count": 32 } ] }, { "length": 5, "count": 491, "percent": 16.37, "relative_percent": 52.35, "examples": [ { "value": "route", "count": 152 }, { "value": "place", "count": 84 }, { "value": "Drive", "count": 75 }, { "value": "Court", "count": 46 }, { "value": "allée", "count": 42 }, { "value": "Place", "count": 32 }, { "value": "Trail", "count": 31 }, { "value": "carré", "count": 29 } ] }, { "length": 6, "count": 938, "percent": 31.27, "relative_percent": 100.0, "examples": [ { "value": "avenue", "count": 324 }, { "value": "Street", "count": 202 }, { "value": "chemin", "count": 189 }, { "value": "Avenue", "count": 121 }, { "value": "montée", "count": 82 }, { "value": "Circle", "count": 20 } ] }, { "length": 7, "count": 116, "percent": 3.87, "relative_percent": 12.37, "examples": [ { "value": "impasse", "count": 53 }, { "value": "Highway", "count": 27 }, { "value": "Terrace", "count": 19 }, { "value": "Parkway", "count": 17 } ] }, { "length": 8, "count": 104, "percent": 3.47, "relative_percent": 11.09, "examples": [ { "value": "terrasse", "count": 71 }, { "value": "Crescent", "count": 33 } ] }, { "length": 9, "count": 556, "percent": 18.53, "relative_percent": 59.28, "examples": [ { "value": "boulevard", "count": 311 }, { "value": "Boulevard", "count": 98 }, { "value": "croissant", "count": 70 }, { "value": "promenade", "count": 44 }, { "value": "autoroute", "count": 33 } ] } ], "representative_examples": [ "avenue", "boulevard", "route" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "chemin", "rue", "avenue", "route", "Street", "promenade", "Place", "Avenue", "Way", "croissant" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 31 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "chemin", "type": "string", "record": 1 }, "last": { "value": "avenue", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 185, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 2101, "mixed_case": 899, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 3, "max_length": 9, "mean_length": 5.808, "median_length": 6, "length_histogram": [ { "length": 3, "count": 487 }, { "length": 4, "count": 308 }, { "length": 5, "count": 491 }, { "length": 6, "count": 938 }, { "length": 7, "count": 116 }, { "length": 8, "count": 104 }, { "length": 9, "count": 556 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_11", "name": "nom_voie", "path": "nom_voie", "position": 11, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 9, "collapse_internal_whitespace_percent": 0.3, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 183, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 183, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 183, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 9, "changed_percent": 0.3, "distinct_count": 175, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 2987, "changed_percent": 99.57, "distinct_count": 166, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 611, "changed_percent": 20.37, "distinct_count": 160, "distinct_status": "complete" } ], "variant_group_count": 20, "variant_group_status": "complete", "variant_groups": [ { "key": "des melezes", "count": 79, "distinct_count": 2, "variants": [ { "value": "des Mélèzes", "count": 78 }, { "value": "des Mélèzes", "count": 1 } ], "truncated": false }, { "key": "des erables", "count": 67, "distinct_count": 2, "variants": [ { "value": "des Érables", "count": 65 }, { "value": "des erables", "count": 2 } ], "truncated": false }, { "key": "du belvedere", "count": 66, "distinct_count": 2, "variants": [ { "value": "du Belvédère", "count": 65 }, { "value": "du Belvedere", "count": 1 } ], "truncated": false }, { "key": "des champs", "count": 63, "distinct_count": 3, "variants": [ { "value": "des Champs", "count": 60 }, { "value": "des champs", "count": 2 }, { "value": "des Champs", "count": 1 } ], "truncated": false }, { "key": "de la riviere", "count": 62, "distinct_count": 3, "variants": [ { "value": "de la Rivière", "count": 60 }, { "value": "de la Riviere", "count": 1 }, { "value": "de la riviere", "count": 1 } ], "truncated": false }, { "key": "des lilas", "count": 62, "distinct_count": 2, "variants": [ { "value": "des Lilas", "count": 61 }, { "value": "des lilas", "count": 1 } ], "truncated": false }, { "key": "des peupliers", "count": 58, "distinct_count": 2, "variants": [ { "value": "des Peupliers", "count": 57 }, { "value": "des Peupliers", "count": 1 } ], "truncated": false }, { "key": "du boise", "count": 57, "distinct_count": 2, "variants": [ { "value": "du Boisé", "count": 56 }, { "value": "du Boisé", "count": 1 } ], "truncated": false }, { "key": "des hirondelles", "count": 54, "distinct_count": 2, "variants": [ { "value": "des Hirondelles", "count": 53 }, { "value": "des hirondelles", "count": 1 } ], "truncated": false }, { "key": "de l'aube", "count": 49, "distinct_count": 3, "variants": [ { "value": "de l'Aube", "count": 47 }, { "value": "de l'Aube", "count": 1 }, { "value": "de l'aube", "count": 1 } ], "truncated": false }, { "key": "des cedres", "count": 48, "distinct_count": 2, "variants": [ { "value": "des Cèdres", "count": 47 }, { "value": "des Cedres", "count": 1 } ], "truncated": false }, { "key": "de la colline", "count": 47, "distinct_count": 2, "variants": [ { "value": "de la Colline", "count": 46 }, { "value": "de la Colline", "count": 1 } ], "truncated": false }, { "key": "de la clairiere", "count": 46, "distinct_count": 2, "variants": [ { "value": "de la Clairière", "count": 45 }, { "value": "de la Clairiere", "count": 1 } ], "truncated": false }, { "key": "des vents", "count": 39, "distinct_count": 2, "variants": [ { "value": "des Vents", "count": 38 }, { "value": "des vents", "count": 1 } ], "truncated": false }, { "key": "oak", "count": 33, "distinct_count": 2, "variants": [ { "value": "Oak", "count": 32 }, { "value": "oak", "count": 1 } ], "truncated": false }, { "key": "du rocher", "count": 29, "distinct_count": 2, "variants": [ { "value": "du Rocher", "count": 27 }, { "value": "du Rocher", "count": 2 } ], "truncated": false }, { "key": "highland", "count": 29, "distinct_count": 2, "variants": [ { "value": "Highland", "count": 28 }, { "value": "highland", "count": 1 } ], "truncated": false }, { "key": "des frenes", "count": 26, "distinct_count": 2, "variants": [ { "value": "des Frênes", "count": 25 }, { "value": "des Frenes", "count": 1 } ], "truncated": false }, { "key": "forest", "count": 20, "distinct_count": 2, "variants": [ { "value": "Forest", "count": 19 }, { "value": "forest", "count": 1 } ], "truncated": false }, { "key": "des trois-lacs", "count": 17, "distinct_count": 2, "variants": [ { "value": "des Trois-Lacs", "count": 16 }, { "value": "des Trois-Lacs", "count": 1 } ], "truncated": false } ], "variant_groups_truncated": false }, "distinct_count": 175, "examples": [ "des Mélèzes", "du Ruisseau", "du Lac" ], "value_profile": { "selection": "diverse_sample", "sampled_distinct_count": 100, "values": [ { "value": "des Mélèzes", "count": 79, "truncated": false }, { "value": "du Ruisseau", "count": 73, "truncated": false }, { "value": "du Lac", "count": 72, "truncated": false }, { "value": "Cedar", "count": 43, "truncated": false }, { "value": "Oak", "count": 32, "truncated": false }, { "value": "Brookside", "count": 25, "truncated": false }, { "value": "Northgate", "count": 18, "truncated": false }, { "value": "School", "count": 17, "truncated": false }, { "value": "du Vieux-Pont", "count": 14, "truncated": false }, { "value": "Eastwood", "count": 13, "truncated": false }, { "value": "Church", "count": 10, "truncated": false }, { "value": "Foxglove", "count": 7, "truncated": false }, { "value": "Evergreen", "count": 1, "truncated": false }, { "value": "MMaple", "count": 1, "truncated": false }, { "value": "Mouuntainview", "count": 1, "truncated": false }, { "value": "Pnie", "count": 1, "truncated": false }, { "value": "dez Sommets", "count": 1, "truncated": false }, { "value": "du aLc", "count": 1, "truncated": false }, { "value": "e la Rivière", "count": 1, "truncated": false }, { "value": "highland", "count": 1, "truncated": false } ] }, "semantic_type": null, "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 3000, "minimum_length": 3, "maximum_length": 18, "mean_length": 9.82, "median_length": 10.0, "distinct_length_count": 16, "fixed_length": null, "length_distribution": [ { "length": 3, "count": 34, "percent": 1.13, "relative_percent": 7.1, "examples": [ { "value": "Oak", "count": 32 }, { "value": "oak", "count": 1 } ] }, { "length": 4, "count": 33, "percent": 1.1, "relative_percent": 6.89, "examples": [ { "value": "Pine", "count": 22 }, { "value": "Mill", "count": 8 }, { "value": "Milg", "count": 1 }, { "value": "Pnie", "count": 1 } ] }, { "length": 5, "count": 124, "percent": 4.13, "relative_percent": 25.89, "examples": [ { "value": "Birch", "count": 45 }, { "value": "Cedar", "count": 43 }, { "value": "Maple", "count": 35 } ] }, { "length": 6, "count": 295, "percent": 9.83, "relative_percent": 61.59, "examples": [ { "value": "du Lac", "count": 72 }, { "value": "Spring", "count": 35 }, { "value": "Meadow", "count": 32 }, { "value": "Sunset", "count": 28 }, { "value": "Willow", "count": 28 }, { "value": "Forest", "count": 19 }, { "value": "Garden", "count": 19 }, { "value": "Market", "count": 17 }, { "value": "School", "count": 17 }, { "value": "du Cap", "count": 13 } ] }, { "length": 7, "count": 114, "percent": 3.8, "relative_percent": 23.8, "examples": [ { "value": "du Parc", "count": 48 }, { "value": "Orchard", "count": 17 }, { "value": "Station", "count": 16 }, { "value": "Harbour", "count": 12 }, { "value": "Redwood", "count": 10 }, { "value": "Railway", "count": 7 }, { "value": "Meeadow", "count": 1 } ] }, { "length": 8, "count": 334, "percent": 11.13, "relative_percent": 69.73, "examples": [ { "value": "des Pins", "count": 63 }, { "value": "du Boisé", "count": 57 }, { "value": "du Havre", "count": 33 }, { "value": "Highland", "count": 28 }, { "value": "Lakeview", "count": 26 }, { "value": "Parkside", "count": 26 }, { "value": "Bluebird", "count": 24 }, { "value": "Westwood", "count": 20 }, { "value": "Eastwood", "count": 13 }, { "value": "Rosewood", "count": 13 } ] }, { "length": 9, "count": 479, "percent": 15.97, "relative_percent": 100.0, "examples": [ { "value": "du Moulin", "count": 69 }, { "value": "des Lilas", "count": 61 }, { "value": "de l'Aube", "count": 48 }, { "value": "du Marais", "count": 39 }, { "value": "des Vents", "count": 38 }, { "value": "Riverside", "count": 35 }, { "value": "Hillcrest", "count": 29 }, { "value": "du Rocher", "count": 29 }, { "value": "Brookside", "count": 25 }, { "value": "de l'Anse", "count": 25 } ] }, { "length": 10, "count": 388, "percent": 12.93, "relative_percent": 81.0, "examples": [ { "value": "des Champs", "count": 61 }, { "value": "des Cèdres", "count": 47 }, { "value": "des Chênes", "count": 30 }, { "value": "Kingfisher", "count": 25 }, { "value": "des Frênes", "count": 25 }, { "value": "du Versant", "count": 25 }, { "value": "Greenfield", "count": 21 }, { "value": "Valleyview", "count": 20 }, { "value": "du Plateau", "count": 19 }, { "value": "des Saules", "count": 17 } ] }, { "length": 11, "count": 353, "percent": 11.77, "relative_percent": 73.7, "examples": [ { "value": "des Mélèzes", "count": 79 }, { "value": "du Ruisseau", "count": 73 }, { "value": "des Érables", "count": 65 }, { "value": "des Sommets", "count": 53 }, { "value": "des Tulipes", "count": 40 }, { "value": "Stonebridge", "count": 14 }, { "value": "de l'Église", "count": 13 }, { "value": "des Jardins", "count": 6 }, { "value": "dess Champs", "count": 2 }, { "value": "Morningstar", "count": 1 } ] }, { "length": 12, "count": 262, "percent": 8.73, "relative_percent": 54.7, "examples": [ { "value": "des Bouleaux", "count": 71 }, { "value": "du Belvédère", "count": 65 }, { "value": "des Prairies", "count": 42 }, { "value": "des Cascades", "count": 23 }, { "value": "Mountainview", "count": 21 }, { "value": "de la Pinède", "count": 19 }, { "value": "de la Vallée", "count": 14 }, { "value": "de la Source", "count": 3 }, { "value": "du Belvedere", "count": 1 }, { "value": "e la Rivière", "count": 1 } ] }, { "length": 13, "count": 320, "percent": 10.67, "relative_percent": 66.81, "examples": [ { "value": "de la Rivière", "count": 60 }, { "value": "des Peupliers", "count": 58 }, { "value": "des Pionniers", "count": 53 }, { "value": "de la Colline", "count": 47 }, { "value": "des Trilliums", "count": 33 }, { "value": "des Épinettes", "count": 30 }, { "value": "de la Falaise", "count": 16 }, { "value": "du Vieux-Pont", "count": 14 }, { "value": "Mouuntainview", "count": 1 }, { "value": "de la Riviere", "count": 1 } ] }, { "length": 14, "count": 38, "percent": 1.27, "relative_percent": 7.93, "examples": [ { "value": "de la Traverse", "count": 19 }, { "value": "des Trois-Lacs", "count": 17 }, { "value": "de la Rivièrre", "count": 1 }, { "value": "dees Épinettes", "count": 1 } ] }, { "length": 15, "count": 183, "percent": 6.1, "relative_percent": 38.2, "examples": [ { "value": "des Hirondelles", "count": 53 }, { "value": "de la Clairière", "count": 45 }, { "value": "des Laurentides", "count": 44 }, { "value": "des Geais-Bleus", "count": 38 }, { "value": "de la Clairiere", "count": 1 }, { "value": "des hirondelles", "count": 1 } ] }, { "length": 16, "count": 22, "percent": 0.73, "relative_percent": 4.59, "examples": [ { "value": "du Soleil-Levant", "count": 12 }, { "value": "de la Côte-Verte", "count": 8 } ] }, { "length": 17, "count": 8, "percent": 0.27, "relative_percent": 1.67, "examples": [ { "value": "des Deux-Rivières", "count": 8 } ] }, { "length": 18, "count": 13, "percent": 0.43, "relative_percent": 2.71, "examples": [ { "value": "de la Grande-Allée", "count": 13 } ] } ], "representative_examples": [ "du Moulin", "des Champs", "des Mélèzes" ] }, "numeric": null, "detectors": [], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "des Tulipes", "type": "string", "record": 1 }, "last": { "value": "du Parc", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 611, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 9, "uppercase": 0, "lowercase": 13, "mixed_case": 2987, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 3, "max_length": 18, "mean_length": 9.823666666666666, "median_length": 10, "length_histogram": [ { "length": 3, "count": 34 }, { "length": 4, "count": 33 }, { "length": 5, "count": 124 }, { "length": 6, "count": 295 }, { "length": 7, "count": 114 }, { "length": 8, "count": 334 }, { "length": 9, "count": 479 }, { "length": 10, "count": 388 }, { "length": 11, "count": 353 }, { "length": 12, "count": 262 }, { "length": 13, "count": 320 }, { "length": 14, "count": 38 }, { "length": 15, "count": 183 }, { "length": 16, "count": 22 }, { "length": 17, "count": 8 }, { "length": 18, "count": 13 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_12", "name": "orientation", "path": "orientation", "position": 12, "inferred_type": "text", "type_counts": { "text": 720 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 2280, "missing_percent": 76.0, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 8, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 8, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 8, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 8, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 720, "changed_percent": 24.0, "distinct_count": 8, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 8, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 8, "examples": [ "Ouest", "Nord", "Sud" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 8, "values": [ { "value": "Ouest", "count": 141, "truncated": false }, { "value": "Nord", "count": 139, "truncated": false }, { "value": "Sud", "count": 130, "truncated": false }, { "value": "Est", "count": 108, "truncated": false }, { "value": "West", "count": 61, "truncated": false }, { "value": "North", "count": 54, "truncated": false }, { "value": "South", "count": 48, "truncated": false }, { "value": "East", "count": 39, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "very_short", "present_count": 720, "minimum_length": 3, "maximum_length": 5, "mean_length": 4.01, "median_length": 4.0, "distinct_length_count": 3, "fixed_length": null, "length_distribution": [ { "length": 3, "count": 238, "percent": 33.06, "relative_percent": 97.94, "examples": [ { "value": "Sud", "count": 130 }, { "value": "Est", "count": 108 } ] }, { "length": 4, "count": 239, "percent": 33.19, "relative_percent": 98.35, "examples": [ { "value": "Nord", "count": 139 }, { "value": "West", "count": 61 }, { "value": "East", "count": 39 } ] }, { "length": 5, "count": 243, "percent": 33.75, "relative_percent": 100.0, "examples": [ { "value": "Ouest", "count": 141 }, { "value": "North", "count": 54 }, { "value": "South", "count": 48 } ] } ], "representative_examples": [ "Ouest", "Nord", "Sud" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 720, "matched_count": 720, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 720, "tested": 720, "matched": 720, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "Ouest", "Nord", "Est", "West", "South", "North", "Sud", "East" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 8 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 720, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 2280, "blank": 0, "marker": 0, "content": 720 }, "missing": { "count": 2280, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 2280, "blank": 0, "marker": 0 } }, "first": { "value": "Ouest", "type": "string", "record": 8 }, "last": { "value": "Nord", "type": "string", "record": 2997 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 0, "mixed_case": 720, "no_letters": 0 }, "string_lengths": { "count": 720, "min_length": 3, "max_length": 5, "mean_length": 4.006944444444445, "median_length": 4, "length_histogram": [ { "length": 3, "count": 238 }, { "length": 4, "count": 239 }, { "length": 5, "count": 243 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_13", "name": "appartement", "path": "appartement", "position": 13, "inferred_type": "integer", "type_counts": { "integer": 1072 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 1928, "missing_percent": 64.27, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 665, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 665, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 665, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 665, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 665, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 665, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 665, "examples": [ "791", "795", "958" ], "value_profile": { "selection": "random_sample", "sampled_distinct_count": 100, "values": [ { "value": "791", "count": 5, "truncated": false }, { "value": "795", "count": 5, "truncated": false }, { "value": "958", "count": 5, "truncated": false }, { "value": "703", "count": 4, "truncated": false }, { "value": "244", "count": 2, "truncated": false }, { "value": "655", "count": 2, "truncated": false }, { "value": "883", "count": 2, "truncated": false }, { "value": "959", "count": 2, "truncated": false }, { "value": "996", "count": 2, "truncated": false }, { "value": "243", "count": 1, "truncated": false }, { "value": "320", "count": 1, "truncated": false }, { "value": "367", "count": 1, "truncated": false }, { "value": "395", "count": 1, "truncated": false }, { "value": "518", "count": 1, "truncated": false }, { "value": "533", "count": 1, "truncated": false }, { "value": "585", "count": 1, "truncated": false }, { "value": "600", "count": 1, "truncated": false }, { "value": "607", "count": 1, "truncated": false }, { "value": "757", "count": 1, "truncated": false }, { "value": "870", "count": 1, "truncated": false } ] }, "semantic_type": null, "exposure": null, "date_profile": null, "string_profile": null, "numeric": { "minimum": 1.0, "maximum": 998.0, "range": 997.0, "mean": 508.12779850746267, "median": 501.0 }, "detectors": [ { "id": "number", "status": "complete", "primary": true, "eligible_count": 1072, "matched_count": 1072, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [ { "format": "0", "count": 1072, "percent": 100.0 } ], "coverage": { "eligible": 1072, "tested": 1072, "matched": 1072, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "245", "405", "519", "358", "557", "991", "244", "283", "868", "791" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "ambiguity": { "count": 0, "candidates": [], "evidence": { "comma": 0, "dot": 0 }, "resolution": null } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 1072, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 1928, "blank": 0, "marker": 0, "content": 1072 }, "missing": { "count": 1928, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 1928, "blank": 0, "marker": 0 } }, "first": { "value": "245", "type": "string", "record": 1 }, "last": { "value": "261", "type": "string", "record": 2997 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 0, "mixed_case": 0, "no_letters": 1072 }, "string_lengths": { "count": 1072, "min_length": 1, "max_length": 3, "mean_length": 2.903917910447761, "median_length": 3, "length_histogram": [ { "length": 1, "count": 9 }, { "length": 2, "count": 85 }, { "length": 3, "count": 978 } ] }, "numeric": { "count": 1072, "native_count": 0, "text_count": 1072, "min": 1, "max": 998, "sum": 544713, "mean": 508.12779850746267, "population_variance": 79940.20661530268, "population_std": 282.73699194711446, "positive": 1072, "negative": 0, "zero": 0, "integral_decimals": 0, "median": { "status": "complete", "value": 501 } }, "booleans": null, "temporal": null } }, { "id": "column_14", "name": "ville", "path": "ville", "position": 14, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 7, "collapse_internal_whitespace_percent": 0.23, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 137, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 137, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 137, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 7, "changed_percent": 0.23, "distinct_count": 135, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 2986, "changed_percent": 99.53, "distinct_count": 128, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 812, "changed_percent": 27.07, "distinct_count": 122, "distinct_status": "complete" } ], "variant_group_count": 13, "variant_group_status": "complete", "variant_groups": [ { "key": "montreal", "count": 321, "distinct_count": 3, "variants": [ { "value": "Montréal", "count": 318 }, { "value": "montreal", "count": 2 }, { "value": "Montreal", "count": 1 } ], "truncated": false }, { "key": "quebec", "count": 184, "distinct_count": 2, "variants": [ { "value": "Québec", "count": 183 }, { "value": "quebec", "count": 1 } ], "truncated": false }, { "key": "toronto", "count": 102, "distinct_count": 2, "variants": [ { "value": "Toronto", "count": 101 }, { "value": "toronto", "count": 1 } ], "truncated": false }, { "key": "longueuil", "count": 100, "distinct_count": 2, "variants": [ { "value": "Longueuil", "count": 98 }, { "value": "longueuil", "count": 2 } ], "truncated": false }, { "key": "levis", "count": 97, "distinct_count": 2, "variants": [ { "value": "Lévis", "count": 96 }, { "value": "Levis", "count": 1 } ], "truncated": false }, { "key": "trois-rivieres", "count": 70, "distinct_count": 2, "variants": [ { "value": "Trois-Rivières", "count": 69 }, { "value": "trois-rivieres", "count": 1 } ], "truncated": false }, { "key": "saint-jerome", "count": 49, "distinct_count": 2, "variants": [ { "value": "Saint-Jérôme", "count": 48 }, { "value": "saint-jerome", "count": 1 } ], "truncated": false }, { "key": "chateauguay", "count": 32, "distinct_count": 3, "variants": [ { "value": "Châteauguay", "count": 30 }, { "value": "Chateauguay", "count": 1 }, { "value": "chateauguay", "count": 1 } ], "truncated": false }, { "key": "alma", "count": 24, "distinct_count": 2, "variants": [ { "value": "Alma", "count": 23 }, { "value": "alma", "count": 1 } ], "truncated": false }, { "key": "joliette", "count": 21, "distinct_count": 2, "variants": [ { "value": "Joliette", "count": 20 }, { "value": "joliette", "count": 1 } ], "truncated": false }, { "key": "la tuque", "count": 20, "distinct_count": 2, "variants": [ { "value": "La Tuque", "count": 19 }, { "value": "La Tuque", "count": 1 } ], "truncated": false }, { "key": "kelowna", "count": 8, "distinct_count": 2, "variants": [ { "value": "Kelowna", "count": 7 }, { "value": "kelowna", "count": 1 } ], "truncated": false }, { "key": "toront o", "count": 2, "distinct_count": 2, "variants": [ { "value": "Toront o", "count": 1 }, { "value": "Toront o", "count": 1 } ], "truncated": false } ], "variant_groups_truncated": false }, "distinct_count": 135, "examples": [ "Montréal", "Québec", "Laval" ], "value_profile": { "selection": "diverse_sample", "sampled_distinct_count": 100, "values": [ { "value": "Montréal", "count": 318, "truncated": false }, { "value": "Québec", "count": 183, "truncated": false }, { "value": "Laval", "count": 144, "truncated": false }, { "value": "Châteauguay", "count": 30, "truncated": false }, { "value": "Alma", "count": 23, "truncated": false }, { "value": "Gaspé", "count": 19, "truncated": false }, { "value": "Val-d'Or", "count": 19, "truncated": false }, { "value": "Baie-Comeau", "count": 12, "truncated": false }, { "value": "St. John's", "count": 12, "truncated": false }, { "value": "Charlottetown", "count": 7, "truncated": false }, { "value": "Prince George", "count": 5, "truncated": false }, { "value": "Montréla", "count": 2, "truncated": false }, { "value": "Blainvville", "count": 1, "truncated": false }, { "value": "Brosssard", "count": 1, "truncated": false }, { "value": "La Tuqse", "count": 1, "truncated": false }, { "value": "Lévib", "count": 1, "truncated": false }, { "value": "Quuébec", "count": 1, "truncated": false }, { "value": "Repenttigny", "count": 1, "truncated": false }, { "value": "Rimmouski", "count": 1, "truncated": false }, { "value": "Sherbroo ke", "count": 1, "truncated": false } ] }, "semantic_type": null, "exposure": null, "date_profile": null, "string_profile": { "status": "medium", "present_count": 3000, "minimum_length": 4, "maximum_length": 24, "mean_length": 9.0, "median_length": 8.0, "distinct_length_count": 16, "fixed_length": null, "length_distribution": [ { "length": 4, "count": 24, "percent": 0.8, "relative_percent": 2.78, "examples": [ { "value": "Alma", "count": 23 }, { "value": "alma", "count": 1 } ] }, { "length": 5, "count": 281, "percent": 9.37, "relative_percent": 32.52, "examples": [ { "value": "Laval", "count": 144 }, { "value": "Lévis", "count": 96 }, { "value": "Gaspé", "count": 19 }, { "value": "Magog", "count": 18 }, { "value": "Laavl", "count": 1 }, { "value": "Lavul", "count": 1 }, { "value": "Levis", "count": 1 }, { "value": "Lévib", "count": 1 } ] }, { "length": 6, "count": 376, "percent": 12.53, "relative_percent": 43.52, "examples": [ { "value": "Québec", "count": 183 }, { "value": "Ottawa", "count": 78 }, { "value": "London", "count": 40 }, { "value": "Granby", "count": 37 }, { "value": "Surrey", "count": 18 }, { "value": "Regina", "count": 12 }, { "value": "Sydney", "count": 3 }, { "value": "LLaval", "count": 1 }, { "value": "Lava l", "count": 1 }, { "value": "Léviss", "count": 1 } ] }, { "length": 7, "count": 257, "percent": 8.57, "relative_percent": 29.75, "examples": [ { "value": "Toronto", "count": 101 }, { "value": "Calgary", "count": 34 }, { "value": "Mirabel", "count": 34 }, { "value": "Moncton", "count": 26 }, { "value": "Halifax", "count": 21 }, { "value": "Beloeil", "count": 17 }, { "value": "Kelowna", "count": 7 }, { "value": "Brandon", "count": 4 }, { "value": "Iqaluit", "count": 4 }, { "value": "Brosard", "count": 1 } ] }, { "length": 8, "count": 864, "percent": 28.8, "relative_percent": 100.0, "examples": [ { "value": "Montréal", "count": 318 }, { "value": "Gatineau", "count": 125 }, { "value": "Saguenay", "count": 71 }, { "value": "Brossard", "count": 59 }, { "value": "Hamilton", "count": 40 }, { "value": "Edmonton", "count": 39 }, { "value": "Brampton", "count": 33 }, { "value": "Rimouski", "count": 30 }, { "value": "Winnipeg", "count": 29 }, { "value": "Waterloo", "count": 22 } ] }, { "length": 9, "count": 207, "percent": 6.9, "relative_percent": 23.96, "examples": [ { "value": "Longueuil", "count": 98 }, { "value": "Vancouver", "count": 39 }, { "value": "Mascouche", "count": 26 }, { "value": "Sept-Îles", "count": 23 }, { "value": "Saskatoon", "count": 7 }, { "value": "longueuil", "count": 2 }, { "value": "Br ampton", "count": 1 }, { "value": "Bra mpton", "count": 1 }, { "value": "Brosssard", "count": 1 }, { "value": "G atineau", "count": 1 } ] }, { "length": 10, "count": 372, "percent": 12.4, "relative_percent": 43.06, "examples": [ { "value": "Sherbrooke", "count": 96 }, { "value": "Terrebonne", "count": 81 }, { "value": "Repentigny", "count": 60 }, { "value": "Shawinigan", "count": 58 }, { "value": "Blainville", "count": 40 }, { "value": "St. John's", "count": 12 }, { "value": "Saint John", "count": 10 }, { "value": "Lethbridge", "count": 8 }, { "value": "Whitehorse", "count": 5 }, { "value": "Misissauga", "count": 1 } ] }, { "length": 11, "count": 151, "percent": 5.03, "relative_percent": 17.48, "examples": [ { "value": "Mississauga", "count": 52 }, { "value": "Châteauguay", "count": 30 }, { "value": "Sorel-Tracy", "count": 28 }, { "value": "Fredericton", "count": 20 }, { "value": "Baie-Comeau", "count": 12 }, { "value": "Yellowknife", "count": 2 }, { "value": "Blainvville", "count": 1 }, { "value": "Chateauguay", "count": 1 }, { "value": "RRepentigny", "count": 1 }, { "value": "Repenttigny", "count": 1 } ] }, { "length": 12, "count": 60, "percent": 2.0, "relative_percent": 6.94, "examples": [ { "value": "Saint-Jérôme", "count": 48 }, { "value": "Sainte-Julie", "count": 11 } ] }, { "length": 13, "count": 163, "percent": 5.43, "relative_percent": 18.87, "examples": [ { "value": "Drummondville", "count": 60 }, { "value": "Victoriaville", "count": 41 }, { "value": "Rouyn-Noranda", "count": 25 }, { "value": "Grand Sudbury", "count": 22 }, { "value": "Charlottetown", "count": 7 }, { "value": "Prince George", "count": 5 }, { "value": "Grand Sudubry", "count": 1 }, { "value": "krummondville", "count": 1 } ] }, { "length": 14, "count": 71, "percent": 2.37, "relative_percent": 8.22, "examples": [ { "value": "Trois-Rivières", "count": 69 }, { "value": "DDrummondville", "count": 1 }, { "value": "trois-rivieres", "count": 1 } ] }, { "length": 15, "count": 51, "percent": 1.7, "relative_percent": 5.9, "examples": [ { "value": "Saint-Hyacinthe", "count": 33 }, { "value": "Rivière-du-Loup", "count": 18 } ] }, { "length": 16, "count": 17, "percent": 0.57, "relative_percent": 1.97, "examples": [ { "value": "Vaudreuil-Dorion", "count": 17 } ] }, { "length": 19, "count": 27, "percent": 0.9, "relative_percent": 3.12, "examples": [ { "value": "Dollard-des-Ormeaux", "count": 27 } ] }, { "length": 20, "count": 1, "percent": 0.03, "relative_percent": 0.12, "examples": [ { "value": "Doll ard-des-Ormeaux", "count": 1 } ] }, { "length": 24, "count": 78, "percent": 2.6, "relative_percent": 9.03, "examples": [ { "value": "Saint-Jean-sur-Richelieu", "count": 60 }, { "value": "Salaberry-de-Valleyfield", "count": 16 } ] } ], "representative_examples": [ "Montréal", "Québec", "Sherbrooke" ] }, "numeric": null, "detectors": [], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "Montréal", "type": "string", "record": 1 }, "last": { "value": "Gatineau", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 812, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 7, "uppercase": 0, "lowercase": 14, "mixed_case": 2986, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 4, "max_length": 24, "mean_length": 8.995666666666667, "median_length": 8, "length_histogram": [ { "length": 4, "count": 24 }, { "length": 5, "count": 281 }, { "length": 6, "count": 376 }, { "length": 7, "count": 257 }, { "length": 8, "count": 864 }, { "length": 9, "count": 207 }, { "length": 10, "count": 372 }, { "length": 11, "count": 151 }, { "length": 12, "count": 60 }, { "length": 13, "count": 163 }, { "length": 14, "count": 71 }, { "length": 15, "count": 51 }, { "length": 16, "count": 17 }, { "length": 19, "count": 27 }, { "length": 20, "count": 1 }, { "length": 24, "count": 78 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_15", "name": "province_code", "path": "province_code", "position": 15, "inferred_type": "text", "type_counts": { "text": 2997 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 3, "missing_percent": 0.1, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 16, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 16, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 16, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 16, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 2974, "changed_percent": 99.13, "distinct_count": 13, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 13, "distinct_status": "complete" } ], "variant_group_count": 3, "variant_group_status": "complete", "variant_groups": [ { "key": "qc", "count": 2242, "distinct_count": 2, "variants": [ { "value": "QC", "count": 2224 }, { "value": "qc", "count": 18 } ], "truncated": false }, { "key": "on", "count": 410, "distinct_count": 2, "variants": [ { "value": "ON", "count": 407 }, { "value": "on", "count": 3 } ], "truncated": false }, { "key": "ab", "count": 94, "distinct_count": 2, "variants": [ { "value": "AB", "count": 92 }, { "value": "ab", "count": 2 } ], "truncated": false } ], "variant_groups_truncated": false }, "distinct_count": 16, "examples": [ "QC", "ON", "AB" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 16, "values": [ { "value": "QC", "count": 2224, "truncated": false }, { "value": "ON", "count": 407, "truncated": false }, { "value": "AB", "count": 92, "truncated": false }, { "value": "BC", "count": 86, "truncated": false }, { "value": "NB", "count": 56, "truncated": false }, { "value": "MB", "count": 32, "truncated": false }, { "value": "NS", "count": 24, "truncated": false }, { "value": "SK", "count": 23, "truncated": false }, { "value": "qc", "count": 18, "truncated": false }, { "value": "NL", "count": 12, "truncated": false }, { "value": "PE", "count": 7, "truncated": false }, { "value": "YT", "count": 5, "truncated": false }, { "value": "NU", "count": 4, "truncated": false }, { "value": "on", "count": 3, "truncated": false }, { "value": "NT", "count": 2, "truncated": false }, { "value": "ab", "count": 2, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "very_short", "present_count": 2997, "minimum_length": 2, "maximum_length": 2, "mean_length": 2.0, "median_length": 2.0, "distinct_length_count": 1, "fixed_length": 2, "length_distribution": [ { "length": 2, "count": 2997, "percent": 100.0, "relative_percent": 100.0, "examples": [ { "value": "QC", "count": 2224 }, { "value": "ON", "count": 407 }, { "value": "AB", "count": 92 }, { "value": "BC", "count": 86 }, { "value": "NB", "count": 56 }, { "value": "MB", "count": 32 }, { "value": "NS", "count": 24 }, { "value": "SK", "count": 23 }, { "value": "qc", "count": 18 }, { "value": "NL", "count": 12 } ] } ], "representative_examples": [ "QC" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 2997, "matched_count": 2997, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 2997, "tested": 2997, "matched": 2997, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "QC", "MB", "ON", "NB", "NS", "PE", "AB", "BC", "SK", "qc" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 16 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 2997, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 3, "blank": 0, "marker": 0, "content": 2997 }, "missing": { "count": 3, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 3, "blank": 0, "marker": 0 } }, "first": { "value": "QC", "type": "string", "record": 1 }, "last": { "value": "QC", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 2974, "lowercase": 23, "mixed_case": 0, "no_letters": 0 }, "string_lengths": { "count": 2997, "min_length": 2, "max_length": 2, "mean_length": 2, "median_length": 2, "length_histogram": [ { "length": 2, "count": 2997 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_16", "name": "province_nom", "path": "province_nom", "position": 16, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 18, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 18, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 18, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 18, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 2988, "changed_percent": 99.6, "distinct_count": 15, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 2254, "changed_percent": 75.13, "distinct_count": 13, "distinct_status": "complete" } ], "variant_group_count": 4, "variant_group_status": "complete", "variant_groups": [ { "key": "quebec", "count": 2244, "distinct_count": 3, "variants": [ { "value": "Québec", "count": 2224 }, { "value": "Quebec", "count": 10 }, { "value": "quebec", "count": 10 } ], "truncated": false }, { "key": "ontario", "count": 410, "distinct_count": 2, "variants": [ { "value": "Ontario", "count": 409 }, { "value": "ontario", "count": 1 } ], "truncated": false }, { "key": "colombie-britannique", "count": 86, "distinct_count": 2, "variants": [ { "value": "Colombie-Britannique", "count": 85 }, { "value": "colombie-britannique", "count": 1 } ], "truncated": false }, { "key": "nouvelle-ecosse", "count": 24, "distinct_count": 2, "variants": [ { "value": "Nouvelle-Écosse", "count": 23 }, { "value": "Nouvelle-Ecosse", "count": 1 } ], "truncated": false } ], "variant_groups_truncated": false }, "distinct_count": 18, "examples": [ "Québec", "Ontario", "Alberta" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 18, "values": [ { "value": "Québec", "count": 2224, "truncated": false }, { "value": "Ontario", "count": 409, "truncated": false }, { "value": "Alberta", "count": 95, "truncated": false }, { "value": "Colombie-Britannique", "count": 85, "truncated": false }, { "value": "Nouveau-Brunswick", "count": 56, "truncated": false }, { "value": "Manitoba", "count": 32, "truncated": false }, { "value": "Nouvelle-Écosse", "count": 23, "truncated": false }, { "value": "Saskatchewan", "count": 23, "truncated": false }, { "value": "Terre-Neuve-et-Labrador", "count": 12, "truncated": false }, { "value": "Quebec", "count": 10, "truncated": false }, { "value": "quebec", "count": 10, "truncated": false }, { "value": "Île-du-Prince-Édouard", "count": 7, "truncated": false }, { "value": "Yukon", "count": 5, "truncated": false }, { "value": "Nunavut", "count": 4, "truncated": false }, { "value": "Territoires du Nord-Ouest", "count": 2, "truncated": false }, { "value": "Nouvelle-Ecosse", "count": 1, "truncated": false }, { "value": "colombie-britannique", "count": 1, "truncated": false }, { "value": "ontario", "count": 1, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "medium", "present_count": 3000, "minimum_length": 5, "maximum_length": 25, "mean_length": 7.03, "median_length": 6.0, "distinct_length_count": 11, "fixed_length": null, "length_distribution": [ { "length": 5, "count": 5, "percent": 0.17, "relative_percent": 0.22, "examples": [ { "value": "Yukon", "count": 5 } ] }, { "length": 6, "count": 2244, "percent": 74.8, "relative_percent": 100.0, "examples": [ { "value": "Québec", "count": 2224 }, { "value": "Quebec", "count": 10 }, { "value": "quebec", "count": 10 } ] }, { "length": 7, "count": 509, "percent": 16.97, "relative_percent": 22.68, "examples": [ { "value": "Ontario", "count": 409 }, { "value": "Alberta", "count": 95 }, { "value": "Nunavut", "count": 4 }, { "value": "ontario", "count": 1 } ] }, { "length": 8, "count": 32, "percent": 1.07, "relative_percent": 1.43, "examples": [ { "value": "Manitoba", "count": 32 } ] }, { "length": 12, "count": 23, "percent": 0.77, "relative_percent": 1.02, "examples": [ { "value": "Saskatchewan", "count": 23 } ] }, { "length": 15, "count": 24, "percent": 0.8, "relative_percent": 1.07, "examples": [ { "value": "Nouvelle-Écosse", "count": 23 }, { "value": "Nouvelle-Ecosse", "count": 1 } ] }, { "length": 17, "count": 56, "percent": 1.87, "relative_percent": 2.5, "examples": [ { "value": "Nouveau-Brunswick", "count": 56 } ] }, { "length": 20, "count": 86, "percent": 2.87, "relative_percent": 3.83, "examples": [ { "value": "Colombie-Britannique", "count": 85 }, { "value": "colombie-britannique", "count": 1 } ] }, { "length": 21, "count": 7, "percent": 0.23, "relative_percent": 0.31, "examples": [ { "value": "Île-du-Prince-Édouard", "count": 7 } ] }, { "length": 23, "count": 12, "percent": 0.4, "relative_percent": 0.53, "examples": [ { "value": "Terre-Neuve-et-Labrador", "count": 12 } ] }, { "length": 25, "count": 2, "percent": 0.07, "relative_percent": 0.09, "examples": [ { "value": "Territoires du Nord-Ouest", "count": 2 } ] } ], "representative_examples": [ "Québec", "Ontario", "Colombie-Britannique" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "Québec", "Manitoba", "Ontario", "quebec", "Nouveau-Brunswick", "Nouvelle-Écosse", "Île-du-Prince-Édouard", "Alberta", "Colombie-Britannique", "Saskatchewan" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 18 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "Québec", "type": "string", "record": 1 }, "last": { "value": "Québec", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 2254, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 12, "mixed_case": 2988, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 5, "max_length": 25, "mean_length": 7.0296666666666665, "median_length": 6, "length_histogram": [ { "length": 5, "count": 5 }, { "length": 6, "count": 2244 }, { "length": 7, "count": 509 }, { "length": 8, "count": 32 }, { "length": 12, "count": 23 }, { "length": 15, "count": 24 }, { "length": 17, "count": 56 }, { "length": 20, "count": 86 }, { "length": 21, "count": 7 }, { "length": 23, "count": 12 }, { "length": 25, "count": 2 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_17", "name": "code_postal", "path": "code_postal", "position": 17, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 54, "collapse_internal_whitespace_percent": 1.8, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2965, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2965, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2965, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 54, "changed_percent": 1.8, "distinct_count": 2962, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 3000, "changed_percent": 100.0, "distinct_count": 2962, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2962, "distinct_status": "complete" } ], "variant_group_count": 3, "variant_group_status": "complete", "variant_groups": [ { "key": "h2x 9m5", "count": 2, "distinct_count": 2, "variants": [ { "value": "H2X 9M5", "count": 1 }, { "value": "H2X 9M5", "count": 1 } ], "truncated": false }, { "key": "h3g 1y7", "count": 2, "distinct_count": 2, "variants": [ { "value": "H3G 1Y7", "count": 1 }, { "value": "H3G 1Y7", "count": 1 } ], "truncated": false }, { "key": "j6w 2c0", "count": 2, "distinct_count": 2, "variants": [ { "value": "J6W 2C0", "count": 1 }, { "value": "J6W 2C0", "count": 1 } ], "truncated": false } ], "variant_groups_truncated": false }, "distinct_count": 2962, "examples": [ "E2L 6H3", "G1R 3T5", "G1R 7N8" ], "value_profile": { "selection": "diverse_sample", "sampled_distinct_count": 100, "values": [ { "value": "E2L 6H3", "count": 2, "truncated": false }, { "value": "G1R 3T5", "count": 2, "truncated": false }, { "value": "G1R 7N8", "count": 2, "truncated": false }, { "value": "E1A 5A2", "count": 1, "truncated": false }, { "value": "G1R 3P9", "count": 1, "truncated": false }, { "value": "G4Z 8E2", "count": 1, "truncated": false }, { "value": "G7J 0N0", "count": 1, "truncated": false }, { "value": "H3G 4V0", "count": 1, "truncated": false }, { "value": "H4A 7G3", "count": 1, "truncated": false }, { "value": "H7N 6X1", "count": 1, "truncated": false }, { "value": "J1H 4K8", "count": 1, "truncated": false }, { "value": "J6K 5X7", "count": 1, "truncated": false }, { "value": "J8X 9W5", "count": 1, "truncated": false }, { "value": "L5B 6M8", "count": 1, "truncated": false }, { "value": "M5V 7V2", "count": 1, "truncated": false }, { "value": "P3E 1H5", "count": 1, "truncated": false }, { "value": "R3C 2W4", "count": 1, "truncated": false }, { "value": "T2P 2S2", "count": 1, "truncated": false }, { "value": "V2L 9T6", "count": 1, "truncated": false }, { "value": "V5K 8S5", "count": 1, "truncated": false } ] }, "semantic_type": "postal_code", "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 3000, "minimum_length": 6, "maximum_length": 7, "mean_length": 6.99, "median_length": 7.0, "distinct_length_count": 2, "fixed_length": null, "length_distribution": [ { "length": 6, "count": 21, "percent": 0.7, "relative_percent": 0.7, "examples": [ { "value": "1K 1T8", "count": 1 }, { "value": "2B 1E5", "count": 1 }, { "value": "3R 3R3", "count": 1 }, { "value": "6K 0E0", "count": 1 }, { "value": "6X 9V4", "count": 1 }, { "value": "7H 8B4", "count": 1 }, { "value": "7N 1L5", "count": 1 }, { "value": "8X 4H4", "count": 1 }, { "value": "9P 7L8", "count": 1 } ] }, { "length": 7, "count": 2979, "percent": 99.3, "relative_percent": 100.0, "examples": [ { "value": "E2L 6H3", "count": 2 }, { "value": "G1R 3T5", "count": 2 }, { "value": "G1R 7N8", "count": 2 }, { "value": "G1R 8J9", "count": 2 }, { "value": "G1V 3E5", "count": 2 }, { "value": "G2B 9E0", "count": 2 }, { "value": "G2B 9H7", "count": 2 }, { "value": "G5R 0V8", "count": 2 }, { "value": "G6W 4V2", "count": 2 }, { "value": "G8Z 1V5", "count": 2 } ] } ], "representative_examples": [ "E2L 6H3", "1K 1T8" ] }, "numeric": null, "detectors": [ { "id": "postal_code", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 2979, "matched_percent": 99.3, "ambiguous_count": 0, "invalid_count": 0, "formats": [ { "format": "A9A 9A9", "count": 2979, "percent": 99.3 } ], "coverage": { "eligible": 3000, "tested": 3000, "matched": 2979, "ambiguous": 0, "invalid": 0, "not_matched": 21, "not_tested": 0, "share_tested": 0.993, "share_eligible": 0.993 }, "evidence": { "matched": [ "H4A 9M3", "G6V 8P2", "J2H 0H3", "J5Y 2J3", "G2B 7V8", "R3C 4S8", "G6V 8A4", "G6W 9E4", "M6G 7M3", "H4A 4S8" ], "ambiguous": [], "invalid": [], "not_matched": [ "T3A 95", "T5J 60", "J1 5M4", "G9 5R1", "6K 0E0", "J7 4B4", "L6X 51", "3R 3R3", "7N 1L5", "H3 6C7" ] }, "details": { "regions": { "ca": 2979, "us": 0 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "H4A 9M3", "type": "string", "record": 1 }, "last": { "value": "J8Y 1Z0", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 54, "uppercase": 3000, "lowercase": 0, "mixed_case": 0, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 6, "max_length": 7, "mean_length": 6.993, "median_length": 7, "length_histogram": [ { "length": 6, "count": 21 }, { "length": 7, "count": 2979 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_18", "name": "pays_code", "path": "pays_code", "position": 18, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 2978, "changed_percent": 99.27, "distinct_count": 1, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 1, "distinct_status": "complete" } ], "variant_group_count": 1, "variant_group_status": "complete", "variant_groups": [ { "key": "ca", "count": 3000, "distinct_count": 2, "variants": [ { "value": "CA", "count": 2978 }, { "value": "ca", "count": 22 } ], "truncated": false } ], "variant_groups_truncated": false }, "distinct_count": 2, "examples": [ "CA", "ca" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 2, "values": [ { "value": "CA", "count": 2978, "truncated": false }, { "value": "ca", "count": 22, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "very_short", "present_count": 3000, "minimum_length": 2, "maximum_length": 2, "mean_length": 2.0, "median_length": 2.0, "distinct_length_count": 1, "fixed_length": 2, "length_distribution": [ { "length": 2, "count": 3000, "percent": 100.0, "relative_percent": 100.0, "examples": [ { "value": "CA", "count": 2978 }, { "value": "ca", "count": 22 } ] } ], "representative_examples": [ "CA" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "CA", "ca" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 2 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "CA", "type": "string", "record": 1 }, "last": { "value": "CA", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 2978, "lowercase": 22, "mixed_case": 0, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 2, "max_length": 2, "mean_length": 2, "median_length": 2, "length_histogram": [ { "length": 2, "count": 3000 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_19", "name": "courriel", "path": "courriel", "position": 19, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 6, "collapse_internal_whitespace_percent": 0.2, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2992, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2992, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2992, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 6, "changed_percent": 0.2, "distinct_count": 2992, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2992, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2992, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2992, "examples": [ "aaa9999@aaaaa.aaaaaaa", "aaa999@aaaaa.aaaaaaa", "aaa99@aaaaa.aaaaaaa" ], "value_profile": { "selection": "random_sample", "sampled_distinct_count": 100, "values": [ { "value": "aaa9999@aaaaa.aaaaaaa", "count": 82, "truncated": false }, { "value": "aaa999@aaaaa.aaaaaaa", "count": 74, "truncated": false }, { "value": "aaa99@aaaaa.aaaaaaa", "count": 54, "truncated": false }, { "value": "aaa99@aaaaaaa.aaaaaaa", "count": 50, "truncated": false }, { "value": "aaaaaaa@aaaa.aaaaaaa", "count": 6, "truncated": false }, { "value": "aaaaaa-aaaaaaaa@aaaaa.aaaaaaa", "count": 5, "truncated": false }, { "value": "aaaaaaa_aaaaaaaa@aaaaaaa.aaaaa...", "count": 5, "truncated": true }, { "value": "aaaaa_aaaaaa@aaaaaa.aaaaaaa", "count": 3, "truncated": false }, { "value": "aaaaaa_aaaaaaaa@aaaaaa.aaaaaaa", "count": 3, "truncated": false }, { "value": "aa99@aaaaaaaaa.aaaaaaa", "count": 2, "truncated": false }, { "value": "aaaa_aaaaaaaaa@aaaaa.aaaaaaa", "count": 2, "truncated": false }, { "value": "aaaaa-aaaaaaaa@aaaaa.aaaaaaa", "count": 2, "truncated": false }, { "value": "aaaaa.aaaaaa@aaaa.aaaaaaa", "count": 2, "truncated": false }, { "value": "aaaaaa.aaa@aaaaaaa.aaaaaaa", "count": 2, "truncated": false }, { "value": "aaaaaa.aaaaaaaaaa@aaaaa.aaaaaa...", "count": 1, "truncated": true }, { "value": "aaaaaaa_aaaa@aaaaaaaaa.aaaaaaa", "count": 1, "truncated": false }, { "value": "aaaaaaaa99@aaaaaaaaa.aaaaaaa", "count": 1, "truncated": false }, { "value": "aaaaaaaaa_aaaaaaa@aaaaaaa.aaaa...", "count": 1, "truncated": true }, { "value": "aaaaaaaaaa.aaaaaaa@aaaaaa.aaaa...", "count": 1, "truncated": true }, { "value": "aaaaaaaaaaaa.aaaaaaa@aaaaaa.aa...", "count": 1, "truncated": true } ] }, "semantic_type": "email", "exposure": "mask", "date_profile": null, "string_profile": { "status": "medium", "present_count": 3000, "minimum_length": 17, "maximum_length": 38, "mean_length": 25.34, "median_length": 25.0, "distinct_length_count": 22, "fixed_length": null, "length_distribution": [ { "length": 17, "count": 2, "percent": 0.07, "relative_percent": 0.72, "examples": [] }, { "length": 18, "count": 27, "percent": 0.9, "relative_percent": 9.75, "examples": [ { "value": "aa99@aaaaa.aaaaaaa", "count": 20 } ] }, { "length": 19, "count": 100, "percent": 3.33, "relative_percent": 36.1, "examples": [ { "value": "aaa99@aaaaa.aaaaaaa", "count": 54 }, { "value": "aa999@aaaaa.aaaaaaa", "count": 21 }, { "value": "aaaaa@aaaaa.aaaaaaa", "count": 11 } ] }, { "length": 20, "count": 181, "percent": 6.03, "relative_percent": 65.34, "examples": [ { "value": "aaa999@aaaaa.aaaaaaa", "count": 74 }, { "value": "aa9999@aaaaa.aaaaaaa", "count": 22 }, { "value": "aaa99@aaaaaa.aaaaaaa", "count": 21 }, { "value": "aa99@aaaaaaa.aaaaaaa", "count": 19 }, { "value": "aaaaaa@aaaaa.aaaaaaa", "count": 11 }, { "value": "aaaa99@aaaaa.aaaaaaa", "count": 9 }, { "value": "aaaaaaa@aaaa.aaaaaaa", "count": 6 } ] }, { "length": 21, "count": 277, "percent": 9.23, "relative_percent": 100.0, "examples": [ { "value": "aaa9999@aaaaa.aaaaaaa", "count": 82 }, { "value": "aaa99@aaaaaaa.aaaaaaa", "count": 50 }, { "value": "aaaaa99@aaaaa.aaaaaaa", "count": 27 }, { "value": "aaaaaaa@aaaaa.aaaaaaa", "count": 21 }, { "value": "aaaa999@aaaaa.aaaaaaa", "count": 18 }, { "value": "aa999@aaaaaaa.aaaaaaa", "count": 15 }, { "value": "aaaaaa@aaaaaa.aaaaaaa", "count": 15 }, { "value": "aaa999@aaaaaa.aaaaaaa", "count": 14 }, { "value": "aaaaa@aaaaaaa.aaaaaaa", "count": 10 }, { "value": "aa9999@aaaaaa.aaaaaaa", "count": 8 } ] }, { "length": 22, "count": 235, "percent": 7.83, "relative_percent": 84.84, "examples": [ { "value": "aaa999@aaaaaaa.aaaaaaa", "count": 49 }, { "value": "aaaaaa99@aaaaa.aaaaaaa", "count": 27 }, { "value": "aa9999@aaaaaaa.aaaaaaa", "count": 25 }, { "value": "aaaaa999@aaaaa.aaaaaaa", "count": 22 }, { "value": "aaaaaaaa@aaaaa.aaaaaaa", "count": 21 }, { "value": "aaaaaaa@aaaaaa.aaaaaaa", "count": 17 }, { "value": "aaaaaa@aaaaaaa.aaaaaaa", "count": 16 }, { "value": "aaa9999@aaaaaa.aaaaaaa", "count": 15 }, { "value": "aaaa99@aaaaaaa.aaaaaaa", "count": 11 }, { "value": "aaaa9999@aaaaa.aaaaaaa", "count": 9 } ] }, { "length": 23, "count": 264, "percent": 8.8, "relative_percent": 95.31, "examples": [ { "value": "aaa9999@aaaaaaa.aaaaaaa", "count": 52 }, { "value": "aaaaaa999@aaaaa.aaaaaaa", "count": 37 }, { "value": "aaaaaaaaa@aaaaa.aaaaaaa", "count": 25 }, { "value": "aaaaa9999@aaaaa.aaaaaaa", "count": 23 }, { "value": "aaaaaaa@aaaaaaa.aaaaaaa", "count": 22 }, { "value": "aaaaa99@aaaaaaa.aaaaaaa", "count": 18 }, { "value": "aaaa999@aaaaaaa.aaaaaaa", "count": 14 }, { "value": "aaaaaaa99@aaaaa.aaaaaaa", "count": 14 }, { "value": "aaaaa999@aaaaaa.aaaaaaa", "count": 11 }, { "value": "aaaaaa99@aaaaaa.aaaaaaa", "count": 9 } ] }, { "length": 24, "count": 227, "percent": 7.57, "relative_percent": 81.95, "examples": [ { "value": "aaaaaa9999@aaaaa.aaaaaaa", "count": 33 }, { "value": "aaaaaaa999@aaaaa.aaaaaaa", "count": 25 }, { "value": "aaaaaa99@aaaaaaa.aaaaaaa", "count": 20 }, { "value": "aaaaa999@aaaaaaa.aaaaaaa", "count": 18 }, { "value": "aaaaaaaa99@aaaaa.aaaaaaa", "count": 16 }, { "value": "aaaaaaaa@aaaaaaa.aaaaaaa", "count": 16 }, { "value": "aaaaaaaaaa@aaaaa.aaaaaaa", "count": 14 }, { "value": "aaaaaa999@aaaaaa.aaaaaaa", "count": 9 }, { "value": "aaaaaaaaa@aaaaaa.aaaaaaa", "count": 9 }, { "value": "aaaa9999@aaaaaaa.aaaaaaa", "count": 8 } ] }, { "length": 25, "count": 276, "percent": 9.2, "relative_percent": 99.64, "examples": [ { "value": "aaaaaa999@aaaaaaa.aaaaaaa", "count": 29 }, { "value": "aaaaaaa9999@aaaaa.aaaaaaa", "count": 28 }, { "value": "aaaaaaaa999@aaaaa.aaaaaaa", "count": 26 }, { "value": "aaaaaaaaaaa@aaaaa.aaaaaaa", "count": 21 }, { "value": "aaaaa9999@aaaaaaa.aaaaaaa", "count": 18 }, { "value": "aaaaaaaaa@aaaaaaa.aaaaaaa", "count": 17 }, { "value": "aaaaa.aaaaa@aaaaa.aaaaaaa", "count": 14 }, { "value": "aaaaaaa99@aaaaaaa.aaaaaaa", "count": 10 }, { "value": "aaaa.aaaaaa@aaaaa.aaaaaaa", "count": 9 }, { "value": "aaaaaa9999@aaaaaa.aaaaaaa", "count": 9 } ] }, { "length": 26, "count": 261, "percent": 8.7, "relative_percent": 94.22, "examples": [ { "value": "aaaaaa9999@aaaaaaa.aaaaaaa", "count": 29 }, { "value": "aaaaaaaa9999@aaaaa.aaaaaaa", "count": 27 }, { "value": "aaaaaaaaaaaa@aaaaa.aaaaaaa", "count": 25 }, { "value": "aaaaaaaaaaa@aaaaaa.aaaaaaa", "count": 17 }, { "value": "aaaaaaaaaa@aaaaaaa.aaaaaaa", "count": 16 }, { "value": "aaaaaa.aaaaa@aaaaa.aaaaaaa", "count": 14 }, { "value": "aaaaa.aaaaaa@aaaaa.aaaaaaa", "count": 12 }, { "value": "aaaa.aaaaa@aaaaaaa.aaaaaaa", "count": 10 }, { "value": "aaaaaaaa99@aaaaaaa.aaaaaaa", "count": 10 }, { "value": "aaaaaaaaa999@aaaaa.aaaaaaa", "count": 9 } ] }, { "length": 27, "count": 248, "percent": 8.27, "relative_percent": 89.53, "examples": [ { "value": "aaaaaa.aaaaaa@aaaaa.aaaaaaa", "count": 21 }, { "value": "aaaaaaaa999@aaaaaaa.aaaaaaa", "count": 16 }, { "value": "aaaaaaaaa9999@aaaaa.aaaaaaa", "count": 16 }, { "value": "aaaaaaaaaaaaa@aaaaa.aaaaaaa", "count": 15 }, { "value": "aaaaaaaaaaa@aaaaaaa.aaaaaaa", "count": 12 }, { "value": "aaaaaaaaa99@aaaaaaa.aaaaaaa", "count": 11 }, { "value": "aaaaaaa9999@aaaaaaa.aaaaaaa", "count": 10 }, { "value": "aaaaaaaaaaaa@aaaaaa.aaaaaaa", "count": 10 }, { "value": "aaaaa.aaaaa@aaaaaaa.aaaaaaa", "count": 9 }, { "value": "aaaaa.aaaaaa@aaaaaa.aaaaaaa", "count": 9 } ] }, { "length": 28, "count": 229, "percent": 7.63, "relative_percent": 82.67, "examples": [ { "value": "aaaaaaaaaaaaaa@aaaaa.aaaaaaa", "count": 24 }, { "value": "aaaaaaaaaaaa@aaaaaaa.aaaaaaa", "count": 23 }, { "value": "aaaaa.aaaaaa@aaaaaaa.aaaaaaa", "count": 15 }, { "value": "aaaaaaaa9999@aaaaaaa.aaaaaaa", "count": 12 }, { "value": "aaaaa.aaaaaaaa@aaaaa.aaaaaaa", "count": 11 }, { "value": "aaaaaa.aaaaaaa@aaaaa.aaaaaaa", "count": 9 }, { "value": "aaaaaaaa.aaaaa@aaaaa.aaaaaaa", "count": 9 }, { "value": "aaaaaa.aaaaaa@aaaaaa.aaaaaaa", "count": 3 }, { "value": "aaaa.aaaaa@aaaaaaaaa.aaaaaaa", "count": 2 }, { "value": "aaaa_aaaaaaaaa@aaaaa.aaaaaaa", "count": 2 } ] }, { "length": 29, "count": 197, "percent": 6.57, "relative_percent": 71.12, "examples": [ { "value": "aaaaaa.aaaaaa@aaaaaaa.aaaaaaa", "count": 17 }, { "value": "aaaaaaaaaaaaaaa@aaaaa.aaaaaaa", "count": 14 }, { "value": "aaaaaaaaaaaaa@aaaaaaa.aaaaaaa", "count": 13 }, { "value": "aaaaaa.aaaaaaaa@aaaaa.aaaaaaa", "count": 10 }, { "value": "aaaaaa-aaaaaaaa@aaaaa.aaaaaaa", "count": 5 }, { "value": "aaaaa_aaaaaaaa@aaaaaa.aaaaaaa", "count": 4 }, { "value": "aaa.aaaaaaaaa@aaaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaa-aaaaaaaa@aaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaa_aaaaaaaaa@aaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaaa_aaaaaaa@aaaa.aaaaaaa", "count": 1 } ] }, { "length": 30, "count": 171, "percent": 5.7, "relative_percent": 61.73, "examples": [ { "value": "aaaaaaaaaaaaaa@aaaaaaa.aaaaaaa", "count": 21 }, { "value": "aaaaaa.aaaaaaa@aaaaaaa.aaaaaaa", "count": 9 }, { "value": "aaaaaaa.aaaaaa@aaaaaaa.aaaaaaa", "count": 9 }, { "value": "aaaaa.aaaaaa@aaaaaaaaa.aaaaaaa", "count": 3 }, { "value": "aaaaaa_aaaaaaaa@aaaaaa.aaaaaaa", "count": 3 }, { "value": "aaaaaaaa_aaaaaaa@aaaaa.aaaaaaa", "count": 3 }, { "value": "aaaaaaaa_aaaaa@aaaaaaa.aaaaaaa", "count": 2 }, { "value": "aaaaa_aaaaaa@aaaaaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaa-aaaaaaaaa@aaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaa_aaaa@aaaaaaaaa.aaaaaaa", "count": 1 } ] }, { "length": 31, "count": 129, "percent": 4.3, "relative_percent": 46.57, "examples": [ { "value": "aaaaaaaa.aaaaaa@aaaaaaa.aaaaaaa", "count": 11 }, { "value": "aaaaaa.aaaaaaaa@aaaaaaa.aaaaaaa", "count": 10 }, { "value": "aaaaaaa.aaaaaaa@aaaaaaa.aaaaaaa", "count": 9 }, { "value": "aaaaaaaa.aaaaaaaa@aaaaa.aaaaaaa", "count": 5 }, { "value": "aaaaaaaaa_aaaaaa@aaaaaa.aaaaaaa", "count": 3 }, { "value": "aaaaa.aaaaaaaaa@aaaaaaa.aaaaaaa", "count": 2 }, { "value": "aaaa_aaaaaaaa@aaaaaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaa.aaaaaaaaaa@aaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaa-aaaaaaaa@aaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaaa_aaaaaa@aaaaaaa.aaaaaaa", "count": 1 } ] }, { "length": 32, "count": 74, "percent": 2.47, "relative_percent": 26.71, "examples": [ { "value": "aaaaaaa.aaaaaaaa@aaaaaaa.aaaaaaa", "count": 7 }, { "value": "aaaaaaa_aaaaaaaa@aaaaaaa.aaaaaaa", "count": 5 }, { "value": "aaaaaaaaa-aaaaaaaa@aaaaa.aaaaaaa", "count": 2 }, { "value": "aaaaaa.aaaaaaaaaaa@aaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaaaaa9999@aaaaaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaaaaaaaaaaaa@aaaaaa.aaaaaaa", "count": 1 } ] }, { "length": 33, "count": 46, "percent": 1.53, "relative_percent": 16.61, "examples": [ { "value": "aaaaaaaaaaaaaaaaa@aaaaaaa.aaaaaaa", "count": 7 }, { "value": "aaaaaaaa.aaaaaa@aaaaaaaaa.aaaaaaa", "count": 3 }, { "value": "aaaaaaaaa-aaaaaaa@aaaaaaa.aaaaaaa", "count": 2 }, { "value": "aaaaaaaa_aaaaaaaa@aaaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaaaa.aaaaa@aaaaaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaaaa_aaaaaaa@aaaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaaaaa.aaaaaaa@aaaaaa.aaaaaaa", "count": 1 } ] }, { "length": 34, "count": 27, "percent": 0.9, "relative_percent": 9.75, "examples": [] }, { "length": 35, "count": 20, "percent": 0.67, "relative_percent": 7.22, "examples": [ { "value": "aaaaaaaaa.aaaaaaa@aaaaaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaaaaaa_aaaaaaa@aaaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaaaaaaa.aaaa@aaaaaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaaaaaaa.aaaaaaa@aaaaaa.aaaaaaa", "count": 1 }, { "value": "aaaaaaaaaaaaaaaaa@aaaaaaaaa.aaaaaaa", "count": 1 } ] }, { "length": 36, "count": 5, "percent": 0.17, "relative_percent": 1.81, "examples": [] }, { "length": 37, "count": 2, "percent": 0.07, "relative_percent": 0.72, "examples": [] }, { "length": 38, "count": 2, "percent": 0.07, "relative_percent": 0.72, "examples": [] } ], "representative_examples": [ "aaa9999@aaaaa.aaaaaaa", "aaaaaa999@aaaaaaa.aaaaaaa", "aaa9999@aaaaaaa.aaaaaaa" ] }, "numeric": null, "detectors": [ { "id": "email", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 2988, "matched_percent": 99.6, "ambiguous_count": 0, "invalid_count": 12, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 2988, "ambiguous": 0, "invalid": 12, "not_matched": 0, "not_tested": 0, "share_tested": 0.996, "share_eligible": 0.996 }, "evidence": { "matched": [ "aa9999@aaaaa.aaaaaaa", "aaa9999@aaaaaaa.aaaaaaa", "aaa99@aaaaa.aaaaaaa", "aaaaaa.aaaaaaa@aaaaaaa.aaaaaaa", "aaaaaaaaaaaaaa@aaaaaaa.aaaaaaa", "aaaaa@aaaaaaa.aaaaaaa", "aaaaa.aaaaaa@aaaaaaa.aaaaaaa", "aaaaaa@aaaaa.aaaaaaa", "aaaa99@aaaaaaa.aaaaaaa" ], "ambiguous": [], "invalid": [ "aaaa.aaaaaa@aaaaa. aaaaaaa", "aaaaaaaaa@ aaaaa.aaaaaaa", "aaaaaaa@aaaaaaaaa.aaaaaa a", "aaaaaaaaaaaaaaaa@aaaaaaa .aaaaaaa", "aaaa@aaaaaa.aaaaaa a", "aaaaaaaaaa@aaaaaa.a aaaaaa", "aaaaa@aaaaa.aaaaaa a", "aaaaaaaaaaaaaaaaaa@aaaa aa.aaaaaaa", "aaaaaaaaa999@aaaaaaa.a aaaaaa", "aaaaaa99@a aaaa.aaaaaaa" ], "not_matched": [] }, "details": { "domains": { "status": "complete", "value": { "distinct": 5, "listed": [ { "value": "aaaaa.aaaaaaa", "count": 1271 }, { "value": "aaaaaaa.aaaaaaa", "count": 1044 }, { "value": "aaaaaa.aaaaaaa", "count": 437 }, { "value": "aaaaaaaaa.aaaaaaa", "count": 149 }, { "value": "aaaa.aaaaaaa", "count": 87 } ], "truncated": false } } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "aa9999@aaaaa.aaaaaaa", "type": "string", "record": 1 }, "last": { "value": "aaa999@aaaaa.aaaaaaa", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 6, "uppercase": 0, "lowercase": 3000, "mixed_case": 0, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 17, "max_length": 38, "mean_length": 25.339, "median_length": 25, "length_histogram": [ { "length": 17, "count": 2 }, { "length": 18, "count": 27 }, { "length": 19, "count": 100 }, { "length": 20, "count": 181 }, { "length": 21, "count": 277 }, { "length": 22, "count": 235 }, { "length": 23, "count": 264 }, { "length": 24, "count": 227 }, { "length": 25, "count": 276 }, { "length": 26, "count": 261 }, { "length": 27, "count": 248 }, { "length": 28, "count": 229 }, { "length": 29, "count": 197 }, { "length": 30, "count": 171 }, { "length": 31, "count": 129 }, { "length": 32, "count": 74 }, { "length": 33, "count": 46 }, { "length": 34, "count": 27 }, { "length": 35, "count": 20 }, { "length": 36, "count": 5 }, { "length": 37, "count": 2 }, { "length": 38, "count": 2 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_20", "name": "telephone", "path": "telephone", "position": 20, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 42, "collapse_internal_whitespace_percent": 1.4, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 1604, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 1604, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 1604, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 42, "changed_percent": 1.4, "distinct_count": 1604, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 1604, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 1604, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 1604, "examples": [ "+9-999-999-9999", "+9 999-999-9999" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 2, "values": [ { "value": "+9-999-999-9999", "count": 2958, "truncated": false }, { "value": "+9 999-999-9999", "count": 42, "truncated": false } ] }, "semantic_type": "phone", "exposure": "mask", "date_profile": null, "string_profile": { "status": "short", "present_count": 3000, "minimum_length": 15, "maximum_length": 15, "mean_length": 15.0, "median_length": 15.0, "distinct_length_count": 1, "fixed_length": 15, "length_distribution": [ { "length": 15, "count": 3000, "percent": 100.0, "relative_percent": 100.0, "examples": [ { "value": "+9-999-999-9999", "count": 2958 }, { "value": "+9 999-999-9999", "count": 42 } ] } ], "representative_examples": [ "+9-999-999-9999" ] }, "numeric": null, "detectors": [ { "id": "phone", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [ { "format": "+1-999-999-9999", "count": 2958, "percent": 98.6 }, { "format": "+1 999-999-9999", "count": 42, "percent": 1.4 } ], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "+9-999-999-9999" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "regions": { "fr": 0, "nanp": 3000 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "+9-999-999-9999", "type": "string", "record": 1 }, "last": { "value": "+9-999-999-9999", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 42, "uppercase": 0, "lowercase": 0, "mixed_case": 0, "no_letters": 3000 }, "string_lengths": { "count": 3000, "min_length": 15, "max_length": 15, "mean_length": 15, "median_length": 15, "length_histogram": [ { "length": 15, "count": 3000 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_21", "name": "id_contrat", "path": "id_contrat", "position": 21, "inferred_type": "text", "type_counts": { "text": 2991 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 9, "missing_percent": 0.3, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2983, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2983, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2983, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2983, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 2991, "changed_percent": 99.7, "distinct_count": 2983, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2983, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2983, "examples": [ "CTR-1000002347", "CTR-1000055908", "CTR-1000090070" ], "value_profile": { "selection": "diverse_sample", "sampled_distinct_count": 100, "values": [ { "value": "CTR-1000002347", "count": 2, "truncated": false }, { "value": "CTR-1000055908", "count": 2, "truncated": false }, { "value": "CTR-1000090070", "count": 2, "truncated": false }, { "value": "CTR-1000004325", "count": 1, "truncated": false }, { "value": "CTR-1000028230", "count": 1, "truncated": false }, { "value": "CTR-1000029899", "count": 1, "truncated": false }, { "value": "CTR-1000036863", "count": 1, "truncated": false }, { "value": "CTR-1000101140", "count": 1, "truncated": false }, { "value": "CTR-1000116266", "count": 1, "truncated": false }, { "value": "CTR-1000118311", "count": 1, "truncated": false }, { "value": "CTR-1000157343", "count": 1, "truncated": false }, { "value": "CTR-1000170981", "count": 1, "truncated": false }, { "value": "CTR-1000181674", "count": 1, "truncated": false }, { "value": "CTR-1000188457", "count": 1, "truncated": false }, { "value": "CTR-2000012419", "count": 1, "truncated": false }, { "value": "CTR-3000017673", "count": 1, "truncated": false }, { "value": "CTR-3000031071", "count": 1, "truncated": false }, { "value": "CTR-3000035905", "count": 1, "truncated": false }, { "value": "CTR-3000046742", "count": 1, "truncated": false }, { "value": "CTR-3000049168", "count": 1, "truncated": false } ] }, "semantic_type": null, "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 2991, "minimum_length": 13, "maximum_length": 15, "mean_length": 14.0, "median_length": 14.0, "distinct_length_count": 3, "fixed_length": null, "length_distribution": [ { "length": 13, "count": 22, "percent": 0.74, "relative_percent": 0.74, "examples": [] }, { "length": 14, "count": 2955, "percent": 98.8, "relative_percent": 100.0, "examples": [ { "value": "CTR-1000002347", "count": 2 }, { "value": "CTR-1000055908", "count": 2 }, { "value": "CTR-1000090070", "count": 2 }, { "value": "CTR-1000103032", "count": 2 }, { "value": "CTR-1000141576", "count": 2 }, { "value": "CTR-1000190952", "count": 2 }, { "value": "CTR-1000194194", "count": 2 }, { "value": "CTR-2000011035", "count": 2 }, { "value": "CTR-1000000020", "count": 1 }, { "value": "CTR-1000000281", "count": 1 } ] }, { "length": 15, "count": 14, "percent": 0.47, "relative_percent": 0.47, "examples": [ { "value": "CTR--1000004074", "count": 1 }, { "value": "CTR--1000010341", "count": 1 }, { "value": "CTR--1000032846", "count": 1 }, { "value": "CTR--1000046408", "count": 1 }, { "value": "CTR--1000086238", "count": 1 }, { "value": "CTR--1000108584", "count": 1 }, { "value": "CTR--1000159993", "count": 1 }, { "value": "CTR--1000173817", "count": 1 }, { "value": "CTR--1000184622", "count": 1 }, { "value": "CTR--1000191870", "count": 1 } ] } ], "representative_examples": [ "CTR-1000002347", "CTR--1000004074" ] }, "numeric": null, "detectors": [], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 2991, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 9, "blank": 0, "marker": 0, "content": 2991 }, "missing": { "count": 9, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 9, "blank": 0, "marker": 0 } }, "first": { "value": "CTR-1000000281", "type": "string", "record": 1 }, "last": { "value": "CTR-3000049871", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 2991, "lowercase": 0, "mixed_case": 0, "no_letters": 0 }, "string_lengths": { "count": 2991, "min_length": 13, "max_length": 15, "mean_length": 13.997325309261116, "median_length": 14, "length_histogram": [ { "length": 13, "count": 22 }, { "length": 14, "count": 2955 }, { "length": 15, "count": 14 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_22", "name": "type_contrat", "path": "type_contrat", "position": 22, "inferred_type": "text", "type_counts": { "text": 2998 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 2, "missing_percent": 0.07, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 6, "changed_percent": 0.2, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 6, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 6, "examples": [ "auto", "habitation", "voyage" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 6, "values": [ { "value": "auto", "count": 1228, "truncated": false }, { "value": "habitation", "count": 910, "truncated": false }, { "value": "voyage", "count": 505, "truncated": false }, { "value": "vie", "count": 349, "truncated": false }, { "value": "habitation_X", "count": 5, "truncated": false }, { "value": "voyage_X", "count": 1, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 2998, "minimum_length": 3, "maximum_length": 12, "mean_length": 6.06, "median_length": 4.0, "distinct_length_count": 6, "fixed_length": null, "length_distribution": [ { "length": 3, "count": 349, "percent": 11.64, "relative_percent": 28.42, "examples": [ { "value": "vie", "count": 349 } ] }, { "length": 4, "count": 1228, "percent": 40.96, "relative_percent": 100.0, "examples": [ { "value": "auto", "count": 1228 } ] }, { "length": 6, "count": 505, "percent": 16.84, "relative_percent": 41.12, "examples": [ { "value": "voyage", "count": 505 } ] }, { "length": 8, "count": 1, "percent": 0.03, "relative_percent": 0.08, "examples": [ { "value": "voyage_X", "count": 1 } ] }, { "length": 10, "count": 910, "percent": 30.35, "relative_percent": 74.1, "examples": [ { "value": "habitation", "count": 910 } ] }, { "length": 12, "count": 5, "percent": 0.17, "relative_percent": 0.41, "examples": [ { "value": "habitation_X", "count": 5 } ] } ], "representative_examples": [ "auto", "habitation", "voyage" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 2998, "matched_count": 2998, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 2998, "tested": 2998, "matched": 2998, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "auto", "vie", "voyage", "habitation", "voyage_X", "habitation_X" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 6 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 2998, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 2, "blank": 0, "marker": 0, "content": 2998 }, "missing": { "count": 2, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 2, "blank": 0, "marker": 0 } }, "first": { "value": "auto", "type": "string", "record": 1 }, "last": { "value": "auto", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 2992, "mixed_case": 6, "no_letters": 0 }, "string_lengths": { "count": 2998, "min_length": 3, "max_length": 12, "mean_length": 6.0563709139426285, "median_length": 4, "length_histogram": [ { "length": 3, "count": 349 }, { "length": 4, "count": 1228 }, { "length": 6, "count": 505 }, { "length": 8, "count": 1 }, { "length": 10, "count": 910 }, { "length": 12, "count": 5 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_23", "name": "date_debut", "path": "date_debut", "position": 23, "inferred_type": "date", "type_counts": { "date": 2993, "text": 7 }, "type_confidence": 0.9977, "type_error_count": 7, "type_error_percent": 0.23, "missing_count": 0, "missing_percent": 0.0, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2409, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2409, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2409, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2409, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2409, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2409, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2409, "examples": [ "2017-10-09", "2024-03-23", "2026-05-02" ], "value_profile": { "selection": "random_sample", "sampled_distinct_count": 100, "values": [ { "value": "2017-10-09", "count": 5, "truncated": false }, { "value": "2024-03-23", "count": 5, "truncated": false }, { "value": "2026-05-02", "count": 5, "truncated": false }, { "value": "2020-10-10", "count": 3, "truncated": false }, { "value": "2022-02-28", "count": 3, "truncated": false }, { "value": "04-06-2023", "count": 1, "truncated": false }, { "value": "19-08-2022", "count": 1, "truncated": false }, { "value": "2017-11-08", "count": 1, "truncated": false }, { "value": "2019-02-07", "count": 1, "truncated": false }, { "value": "2020-02-14", "count": 1, "truncated": false }, { "value": "2020-03-30", "count": 1, "truncated": false }, { "value": "2020-04-03", "count": 1, "truncated": false }, { "value": "2020-06-30", "count": 1, "truncated": false }, { "value": "2021-12-05", "count": 1, "truncated": false }, { "value": "2022-01-01", "count": 1, "truncated": false }, { "value": "2022-07-08", "count": 1, "truncated": false }, { "value": "2024-08-26", "count": 1, "truncated": false }, { "value": "2027-06-13", "count": 1, "truncated": false }, { "value": "2027-06-17", "count": 1, "truncated": false }, { "value": "24-08-2020", "count": 1, "truncated": false } ] }, "semantic_type": "date", "exposure": null, "date_profile": { "status": "mixed", "present_count": 3000, "valid_count": 2658, "valid_percent": 88.6, "ambiguous_count": 335, "ambiguous_percent": 11.17, "invalid_date_count": 7, "invalid_date_percent": 0.23, "not_date_count": 0, "not_date_percent": 0.0, "resolved_ambiguous_order": null, "ambiguous_order_source": null, "ambiguity_evidence": { "DMY": 340, "MDY": 142 }, "formats": [ { "format": "YYYY-MM-DD", "order": "YMD", "separator": "-", "count": 2170, "percent": 72.33, "iso": true }, { "format": "DD-MM-YYYY", "order": "DMY", "separator": "-", "count": 338, "percent": 11.27, "iso": false }, { "format": "MM-DD-YYYY", "order": "MDY", "separator": "-", "count": 142, "percent": 4.73, "iso": false }, { "format": "YYYY/MM/DD", "order": "YMD", "separator": "/", "count": 6, "percent": 0.2, "iso": false }, { "format": "DD/MM/YYYY", "order": "DMY", "separator": "/", "count": 2, "percent": 0.07, "iso": false } ], "format_count": 5, "breakdown": [ { "label": "YYYY-MM-DD", "category": "valid", "count": 2170, "percent": 72.33 }, { "label": "DD-MM-YYYY", "category": "valid", "count": 338, "percent": 11.27 }, { "label": "Ambiguous: DD-MM-YYYY or MM-DD-YYYY", "category": "ambiguous", "count": 335, "percent": 11.17 }, { "label": "MM-DD-YYYY", "category": "valid", "count": 142, "percent": 4.73 }, { "label": "YYYY/MM/DD", "category": "valid", "count": 6, "percent": 0.2 }, { "label": "DD/MM/YYYY", "category": "valid", "count": 2, "percent": 0.07 }, { "label": "Invalid date", "category": "invalid", "count": 7, "percent": 0.23 }, { "label": "Not a date", "category": "not_date", "count": 0, "percent": 0.0 } ] }, "string_profile": null, "numeric": null, "detectors": [ { "id": "date", "status": "complete", "primary": false, "eligible_count": 3000, "matched_count": 2658, "matched_percent": 88.6, "ambiguous_count": 335, "invalid_count": 7, "formats": [ { "format": "YYYY-MM-DD", "count": 2170, "percent": 72.33 }, { "format": "DD-MM-YYYY", "count": 338, "percent": 11.27 }, { "format": "MM-DD-YYYY", "count": 142, "percent": 4.73 }, { "format": "YYYY/MM/DD", "count": 6, "percent": 0.2 }, { "format": "DD/MM/YYYY", "count": 2, "percent": 0.07 } ], "coverage": { "eligible": 3000, "tested": 3000, "matched": 2658, "ambiguous": 335, "invalid": 7, "not_matched": 0, "not_tested": 0, "share_tested": 0.886, "share_eligible": 0.886 }, "evidence": { "matched": [ "2020-07-16", "2027-06-02", "2016-09-30", "2023-03-29", "2017-05-26", "2025-05-17", "2025-03-16", "2018-07-30", "2022-06-11", "2022-09-27" ], "ambiguous": [ "04-12-2025", "12-12-2021", "06-12-2018", "02-04-2025", "11-12-2025", "12-04-2017", "11-07-2025", "09-08-2022", "01-02-2017", "01-03-2026" ], "invalid": [ "2026-13-40", "13-40-2026" ], "not_matched": [] }, "details": { "ambiguity": { "count": 335, "candidates": [ { "formats": [ "DD-MM-YYYY", "MM-DD-YYYY" ], "count": 335 } ], "evidence": { "DMY": 340, "MDY": 142 }, "resolution": null } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "2020-07-16", "type": "string", "record": 1 }, "last": { "value": "25-04-2026", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 0, "mixed_case": 0, "no_letters": 3000 }, "string_lengths": { "count": 3000, "min_length": 10, "max_length": 10, "mean_length": 10, "median_length": 10, "length_histogram": [ { "length": 10, "count": 3000 } ] }, "numeric": null, "booleans": null, "temporal": { "count": 2658, "ambiguous": 335, "kinds": [ { "kind": "date", "count": 2658, "min": "2016-09-19", "max": "2027-08-30", "years": [ { "year": 2016, "count": 74 }, { "year": 2017, "count": 244 }, { "year": 2018, "count": 215 }, { "year": 2019, "count": 234 }, { "year": 2020, "count": 256 }, { "year": 2021, "count": 269 }, { "year": 2022, "count": 261 }, { "year": 2023, "count": 280 }, { "year": 2024, "count": 267 }, { "year": 2025, "count": 311 }, { "year": 2026, "count": 232 }, { "year": 2027, "count": 15 } ] } ] } } }, { "id": "column_24", "name": "date_fin", "path": "date_fin", "position": 24, "inferred_type": "date", "type_counts": { "date": 2495, "text": 3 }, "type_confidence": 0.9988, "type_error_count": 3, "type_error_percent": 0.12, "missing_count": 502, "missing_percent": 16.73, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 1177, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 1177, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 1177, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 1177, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 1177, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 1177, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 1177, "examples": [ "2026-12-29", "2027-01-09", "2027-06-03" ], "value_profile": { "selection": "random_sample", "sampled_distinct_count": 100, "values": [ { "value": "2026-12-29", "count": 12, "truncated": false }, { "value": "2027-01-09", "count": 11, "truncated": false }, { "value": "2027-06-03", "count": 10, "truncated": false }, { "value": "2027-02-09", "count": 6, "truncated": false }, { "value": "2026-10-27", "count": 5, "truncated": false }, { "value": "06-12-2026", "count": 3, "truncated": false }, { "value": "2026-11-29", "count": 3, "truncated": false }, { "value": "2026-12-27", "count": 3, "truncated": false }, { "value": "10-11-2026", "count": 2, "truncated": false }, { "value": "15-05-2027", "count": 2, "truncated": false }, { "value": "16-12-2026", "count": 2, "truncated": false }, { "value": "07-10-2027", "count": 1, "truncated": false }, { "value": "11-24-2026", "count": 1, "truncated": false }, { "value": "2022-07-16", "count": 1, "truncated": false }, { "value": "2022-09-27", "count": 1, "truncated": false }, { "value": "2024-04-05", "count": 1, "truncated": false }, { "value": "2024-06-05", "count": 1, "truncated": false }, { "value": "2025-09-16", "count": 1, "truncated": false }, { "value": "2026-08-21", "count": 1, "truncated": false }, { "value": "2026-11-11", "count": 1, "truncated": false } ] }, "semantic_type": "date", "exposure": null, "date_profile": { "status": "mixed", "present_count": 2498, "valid_count": 2221, "valid_percent": 88.91, "ambiguous_count": 274, "ambiguous_percent": 10.97, "invalid_date_count": 3, "invalid_date_percent": 0.12, "not_date_count": 0, "not_date_percent": 0.0, "resolved_ambiguous_order": null, "ambiguous_order_source": null, "ambiguity_evidence": { "DMY": 291, "MDY": 125 }, "formats": [ { "format": "YYYY-MM-DD", "order": "YMD", "separator": "-", "count": 1803, "percent": 72.18, "iso": true }, { "format": "DD-MM-YYYY", "order": "DMY", "separator": "-", "count": 289, "percent": 11.57, "iso": false }, { "format": "MM-DD-YYYY", "order": "MDY", "separator": "-", "count": 124, "percent": 4.96, "iso": false }, { "format": "DD/MM/YYYY", "order": "DMY", "separator": "/", "count": 2, "percent": 0.08, "iso": false }, { "format": "YYYY/MM/DD", "order": "YMD", "separator": "/", "count": 2, "percent": 0.08, "iso": false }, { "format": "MM/DD/YYYY", "order": "MDY", "separator": "/", "count": 1, "percent": 0.04, "iso": false } ], "format_count": 6, "breakdown": [ { "label": "YYYY-MM-DD", "category": "valid", "count": 1803, "percent": 72.18 }, { "label": "DD-MM-YYYY", "category": "valid", "count": 289, "percent": 11.57 }, { "label": "Ambiguous: DD-MM-YYYY or MM-DD-YYYY", "category": "ambiguous", "count": 271, "percent": 10.85 }, { "label": "MM-DD-YYYY", "category": "valid", "count": 124, "percent": 4.96 }, { "label": "Ambiguous: DD/MM/YYYY or MM/DD/YYYY", "category": "ambiguous", "count": 3, "percent": 0.12 }, { "label": "DD/MM/YYYY", "category": "valid", "count": 2, "percent": 0.08 }, { "label": "YYYY/MM/DD", "category": "valid", "count": 2, "percent": 0.08 }, { "label": "MM/DD/YYYY", "category": "valid", "count": 1, "percent": 0.04 }, { "label": "Invalid date", "category": "invalid", "count": 3, "percent": 0.12 }, { "label": "Not a date", "category": "not_date", "count": 0, "percent": 0.0 } ] }, "string_profile": null, "numeric": null, "detectors": [ { "id": "date", "status": "complete", "primary": false, "eligible_count": 2498, "matched_count": 2221, "matched_percent": 88.91, "ambiguous_count": 274, "invalid_count": 3, "formats": [ { "format": "YYYY-MM-DD", "count": 1803, "percent": 72.18 }, { "format": "DD-MM-YYYY", "count": 289, "percent": 11.57 }, { "format": "MM-DD-YYYY", "count": 124, "percent": 4.96 }, { "format": "DD/MM/YYYY", "count": 2, "percent": 0.08 }, { "format": "YYYY/MM/DD", "count": 2, "percent": 0.08 }, { "format": "MM/DD/YYYY", "count": 1, "percent": 0.04 } ], "coverage": { "eligible": 2498, "tested": 2498, "matched": 2221, "ambiguous": 274, "invalid": 3, "not_matched": 0, "not_tested": 0, "share_tested": 0.8891, "share_eligible": 0.8891 }, "evidence": { "matched": [ "2026-12-28", "2021-11-27", "2022-07-20", "2027-05-07", "2018-11-19", "2026-07-30", "2027-01-30", "2027-05-13", "2027-07-11", "2027-04-23" ], "ambiguous": [ "12-05-2026", "05-09-2027", "06-05-2027", "05-08-2026", "03-07-2027", "07-11-2020", "09-06-2026", "08-10-2027", "07-10-2021", "11-11-2026" ], "invalid": [ "2026-13-40", "40-13-2026" ], "not_matched": [] }, "details": { "ambiguity": { "count": 274, "candidates": [ { "formats": [ "DD-MM-YYYY", "MM-DD-YYYY" ], "count": 271 }, { "formats": [ "DD/MM/YYYY", "MM/DD/YYYY" ], "count": 3 } ], "evidence": { "DMY": 291, "MDY": 125 }, "resolution": null } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 2498, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 502, "blank": 0, "marker": 0, "content": 2498 }, "missing": { "count": 502, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 502, "blank": 0, "marker": 0 } }, "first": { "value": "2026-12-28", "type": "string", "record": 1 }, "last": { "value": "05-05-2026", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 0, "mixed_case": 0, "no_letters": 2498 }, "string_lengths": { "count": 2498, "min_length": 10, "max_length": 10, "mean_length": 10, "median_length": 10, "length_histogram": [ { "length": 10, "count": 2498 } ] }, "numeric": null, "booleans": null, "temporal": { "count": 2221, "ambiguous": 274, "kinds": [ { "kind": "date", "count": 2221, "min": "2017-05-20", "max": "2027-09-16", "years": [ { "year": 2017, "count": 4 }, { "year": 2018, "count": 9 }, { "year": 2019, "count": 16 }, { "year": 2020, "count": 27 }, { "year": 2021, "count": 29 }, { "year": 2022, "count": 30 }, { "year": 2023, "count": 53 }, { "year": 2024, "count": 81 }, { "year": 2025, "count": 110 }, { "year": 2026, "count": 555 }, { "year": 2027, "count": 1307 } ] } ] } } }, { "id": "column_25", "name": "statut_contrat", "path": "statut_contrat", "position": 25, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 5, "changed_percent": 0.17, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 527, "changed_percent": 17.57, "distinct_count": 6, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 6, "examples": [ "actif", "expiré", "suspendu" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 6, "values": [ { "value": "actif", "count": 2279, "truncated": false }, { "value": "expiré", "count": 373, "truncated": false }, { "value": "suspendu", "count": 190, "truncated": false }, { "value": "résilié", "count": 153, "truncated": false }, { "value": "actif_X", "count": 4, "truncated": false }, { "value": "expiré_X", "count": 1, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 3000, "minimum_length": 5, "maximum_length": 8, "mean_length": 5.42, "median_length": 5.0, "distinct_length_count": 4, "fixed_length": null, "length_distribution": [ { "length": 5, "count": 2279, "percent": 75.97, "relative_percent": 100.0, "examples": [ { "value": "actif", "count": 2279 } ] }, { "length": 6, "count": 373, "percent": 12.43, "relative_percent": 16.37, "examples": [ { "value": "expiré", "count": 373 } ] }, { "length": 7, "count": 157, "percent": 5.23, "relative_percent": 6.89, "examples": [ { "value": "résilié", "count": 153 }, { "value": "actif_X", "count": 4 } ] }, { "length": 8, "count": 191, "percent": 6.37, "relative_percent": 8.38, "examples": [ { "value": "suspendu", "count": 190 }, { "value": "expiré_X", "count": 1 } ] } ], "representative_examples": [ "actif", "expiré", "suspendu" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "actif", "résilié", "expiré", "suspendu", "actif_X", "expiré_X" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 6 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "actif", "type": "string", "record": 1 }, "last": { "value": "résilié", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 527, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 2995, "mixed_case": 5, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 5, "max_length": 8, "mean_length": 5.42, "median_length": 5, "length_histogram": [ { "length": 5, "count": 2279 }, { "length": 6, "count": 373 }, { "length": 7, "count": 157 }, { "length": 8, "count": 191 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_26", "name": "prime_annuelle", "path": "prime_annuelle", "position": 26, "inferred_type": "number", "type_counts": { "number": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2975, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2975, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2975, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2975, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2975, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2975, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2975, "examples": [ "2556.06", "1019.34", "1026.39" ], "value_profile": { "selection": "random_sample", "sampled_distinct_count": 100, "values": [ { "value": "2556.06", "count": 3, "truncated": false }, { "value": "1019.34", "count": 2, "truncated": false }, { "value": "1026.39", "count": 2, "truncated": false }, { "value": "1281.15", "count": 1, "truncated": false }, { "value": "1728.39", "count": 1, "truncated": false }, { "value": "1746.20", "count": 1, "truncated": false }, { "value": "201.78", "count": 1, "truncated": false }, { "value": "2101.66", "count": 1, "truncated": false }, { "value": "2518.08", "count": 1, "truncated": false }, { "value": "2545.65", "count": 1, "truncated": false }, { "value": "274.27", "count": 1, "truncated": false }, { "value": "2871.97", "count": 1, "truncated": false }, { "value": "3211.30", "count": 1, "truncated": false }, { "value": "400.24", "count": 1, "truncated": false }, { "value": "496.16", "count": 1, "truncated": false }, { "value": "549.16", "count": 1, "truncated": false }, { "value": "780.67", "count": 1, "truncated": false }, { "value": "842.26", "count": 1, "truncated": false }, { "value": "931.03", "count": 1, "truncated": false }, { "value": "952.12", "count": 1, "truncated": false } ] }, "semantic_type": null, "exposure": null, "date_profile": null, "string_profile": null, "numeric": { "minimum": -3097.96, "maximum": 4948.16, "range": 8046.12, "mean": 1224.0938066666668, "median": 1101.34 }, "detectors": [ { "id": "number", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [ { "format": "0.0", "count": 3000, "percent": 100.0 } ], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "1234.18", "1123.69", "379.29", "-744.79", "241.17", "695.97", "1144.35", "433.12", "1509.17", "405.78" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "ambiguity": { "count": 0, "candidates": [], "evidence": { "comma": 0, "dot": 3000 }, "resolution": null } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "1234.18", "type": "string", "record": 1 }, "last": { "value": "1971.55", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 0, "mixed_case": 0, "no_letters": 3000 }, "string_lengths": { "count": 3000, "min_length": 5, "max_length": 8, "mean_length": 6.558666666666666, "median_length": 7, "length_histogram": [ { "length": 5, "count": 18 }, { "length": 6, "count": 1300 }, { "length": 7, "count": 1670 }, { "length": 8, "count": 12 } ] }, "numeric": { "count": 3000, "native_count": 0, "text_count": 3000, "min": -3097.96, "max": 4948.16, "sum": 3672281.42, "mean": 1224.0938066666668, "population_variance": 681687.0128881093, "population_std": 825.6433932928364, "positive": 2975, "negative": 25, "zero": 0, "integral_decimals": 23, "median": { "status": "complete", "value": 1101.34 } }, "booleans": null, "temporal": null } }, { "id": "column_27", "name": "frequence_paiement", "path": "frequence_paiement", "position": 27, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 3, "changed_percent": 0.1, "distinct_count": 6, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 6, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 6, "examples": [ "mensuelle", "annuelle", "trimestrielle" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 6, "values": [ { "value": "mensuelle", "count": 1959, "truncated": false }, { "value": "annuelle", "count": 609, "truncated": false }, { "value": "trimestrielle", "count": 294, "truncated": false }, { "value": "semestrielle", "count": 135, "truncated": false }, { "value": "annuelle_X", "count": 2, "truncated": false }, { "value": "mensuelle_X", "count": 1, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 3000, "minimum_length": 8, "maximum_length": 13, "mean_length": 9.33, "median_length": 9.0, "distinct_length_count": 6, "fixed_length": null, "length_distribution": [ { "length": 8, "count": 609, "percent": 20.3, "relative_percent": 31.09, "examples": [ { "value": "annuelle", "count": 609 } ] }, { "length": 9, "count": 1959, "percent": 65.3, "relative_percent": 100.0, "examples": [ { "value": "mensuelle", "count": 1959 } ] }, { "length": 10, "count": 2, "percent": 0.07, "relative_percent": 0.1, "examples": [ { "value": "annuelle_X", "count": 2 } ] }, { "length": 11, "count": 1, "percent": 0.03, "relative_percent": 0.05, "examples": [ { "value": "mensuelle_X", "count": 1 } ] }, { "length": 12, "count": 135, "percent": 4.5, "relative_percent": 6.89, "examples": [ { "value": "semestrielle", "count": 135 } ] }, { "length": 13, "count": 294, "percent": 9.8, "relative_percent": 15.01, "examples": [ { "value": "trimestrielle", "count": 294 } ] } ], "representative_examples": [ "mensuelle", "annuelle", "trimestrielle" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "mensuelle", "annuelle", "trimestrielle", "semestrielle", "annuelle_X", "mensuelle_X" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 6 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "mensuelle", "type": "string", "record": 1 }, "last": { "value": "mensuelle", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 2997, "mixed_case": 3, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 8, "max_length": 13, "mean_length": 9.325333333333333, "median_length": 9, "length_histogram": [ { "length": 8, "count": 609 }, { "length": 9, "count": 1959 }, { "length": 10, "count": 2 }, { "length": 11, "count": 1 }, { "length": 12, "count": 135 }, { "length": 13, "count": 294 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_28", "name": "mode_paiement", "path": "mode_paiement", "position": 28, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 9, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 9, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 9, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 9, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 8, "changed_percent": 0.27, "distinct_count": 9, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 1792, "changed_percent": 59.73, "distinct_count": 7, "distinct_status": "complete" } ], "variant_group_count": 2, "variant_group_status": "complete", "variant_groups": [ { "key": "prelevement", "count": 1649, "distinct_count": 2, "variants": [ { "value": "prélèvement", "count": 1633 }, { "value": "prelevement", "count": 16 } ], "truncated": false }, { "key": "cheque", "count": 157, "distinct_count": 2, "variants": [ { "value": "chèque", "count": 156 }, { "value": "cheque", "count": 1 } ], "truncated": false } ], "variant_groups_truncated": false }, "distinct_count": 9, "examples": [ "prélèvement", "carte", "virement" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 9, "values": [ { "value": "prélèvement", "count": 1633, "truncated": false }, { "value": "carte", "count": 741, "truncated": false }, { "value": "virement", "count": 445, "truncated": false }, { "value": "chèque", "count": 156, "truncated": false }, { "value": "prelevement", "count": 16, "truncated": false }, { "value": "carte_X", "count": 3, "truncated": false }, { "value": "prélèvement_X", "count": 3, "truncated": false }, { "value": "virement_X", "count": 2, "truncated": false }, { "value": "cheque", "count": 1, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 3000, "minimum_length": 5, "maximum_length": 13, "mean_length": 8.81, "median_length": 11.0, "distinct_length_count": 7, "fixed_length": null, "length_distribution": [ { "length": 5, "count": 741, "percent": 24.7, "relative_percent": 44.94, "examples": [ { "value": "carte", "count": 741 } ] }, { "length": 6, "count": 157, "percent": 5.23, "relative_percent": 9.52, "examples": [ { "value": "chèque", "count": 156 }, { "value": "cheque", "count": 1 } ] }, { "length": 7, "count": 3, "percent": 0.1, "relative_percent": 0.18, "examples": [ { "value": "carte_X", "count": 3 } ] }, { "length": 8, "count": 445, "percent": 14.83, "relative_percent": 26.99, "examples": [ { "value": "virement", "count": 445 } ] }, { "length": 10, "count": 2, "percent": 0.07, "relative_percent": 0.12, "examples": [ { "value": "virement_X", "count": 2 } ] }, { "length": 11, "count": 1649, "percent": 54.97, "relative_percent": 100.0, "examples": [ { "value": "prélèvement", "count": 1633 }, { "value": "prelevement", "count": 16 } ] }, { "length": 13, "count": 3, "percent": 0.1, "relative_percent": 0.18, "examples": [ { "value": "prélèvement_X", "count": 3 } ] } ], "representative_examples": [ "prélèvement", "carte", "virement" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "chèque", "prélèvement", "carte", "virement", "prélèvement_X", "prelevement", "carte_X", "cheque", "virement_X" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 9 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "chèque", "type": "string", "record": 1 }, "last": { "value": "virement", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 1792, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 2992, "mixed_case": 8, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 5, "max_length": 13, "mean_length": 8.808666666666667, "median_length": 11, "length_histogram": [ { "length": 5, "count": 741 }, { "length": 6, "count": 157 }, { "length": 7, "count": 3 }, { "length": 8, "count": 445 }, { "length": 10, "count": 2 }, { "length": 11, "count": 1649 }, { "length": 13, "count": 3 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_29", "name": "agence_code", "path": "agence_code", "position": 29, "inferred_type": "text", "type_counts": { "text": 3000 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 0, "missing_percent": 0.0, "with_issues": false, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 27, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 27, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 27, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 27, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 3000, "changed_percent": 100.0, "distinct_count": 27, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 27, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 27, "examples": [ "AG-PR-001", "AG-PR-002", "AG-PR-005" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 27, "values": [ { "value": "AG-PR-001", "count": 618, "truncated": false }, { "value": "AG-PR-002", "count": 382, "truncated": false }, { "value": "AG-PR-005", "count": 246, "truncated": false }, { "value": "AG-PR-003", "count": 225, "truncated": false }, { "value": "AG-PR-004", "count": 224, "truncated": false }, { "value": "AG-QC-001", "count": 199, "truncated": false }, { "value": "AG-PR-007", "count": 170, "truncated": false }, { "value": "AG-PR-006", "count": 165, "truncated": false }, { "value": "AG-QC-002", "count": 128, "truncated": false }, { "value": "AG-PR-008", "count": 124, "truncated": false }, { "value": "AG-ON-001", "count": 91, "truncated": false }, { "value": "AG-QC-004", "count": 67, "truncated": false }, { "value": "AG-QC-003", "count": 66, "truncated": false }, { "value": "AG-QC-005", "count": 66, "truncated": false }, { "value": "AG-QC-006", "count": 46, "truncated": false }, { "value": "AG-ON-002", "count": 38, "truncated": false }, { "value": "AG-ON-004", "count": 38, "truncated": false }, { "value": "AG-ON-003", "count": 37, "truncated": false }, { "value": "AG-ON-005", "count": 33, "truncated": false }, { "value": "AG-ON-006", "count": 21, "truncated": false }, { "value": "AG--PR-001", "count": 5, "truncated": false }, { "value": "AG--PR-002", "count": 4, "truncated": false }, { "value": "AG--PR-003", "count": 2, "truncated": false }, { "value": "AG--QC-001", "count": 2, "truncated": false }, { "value": "AG--PR-004", "count": 1, "truncated": false }, { "value": "AG--PR-007", "count": 1, "truncated": false }, { "value": "AG--QC-002", "count": 1, "truncated": false } ] }, "semantic_type": "enumeration", "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 3000, "minimum_length": 9, "maximum_length": 10, "mean_length": 9.01, "median_length": 9.0, "distinct_length_count": 2, "fixed_length": null, "length_distribution": [ { "length": 9, "count": 2984, "percent": 99.47, "relative_percent": 100.0, "examples": [ { "value": "AG-PR-001", "count": 618 }, { "value": "AG-PR-002", "count": 382 }, { "value": "AG-PR-005", "count": 246 }, { "value": "AG-PR-003", "count": 225 }, { "value": "AG-PR-004", "count": 224 }, { "value": "AG-QC-001", "count": 199 }, { "value": "AG-PR-007", "count": 170 }, { "value": "AG-PR-006", "count": 165 }, { "value": "AG-QC-002", "count": 128 }, { "value": "AG-PR-008", "count": 124 } ] }, { "length": 10, "count": 16, "percent": 0.53, "relative_percent": 0.54, "examples": [ { "value": "AG--PR-001", "count": 5 }, { "value": "AG--PR-002", "count": 4 }, { "value": "AG--PR-003", "count": 2 }, { "value": "AG--QC-001", "count": 2 }, { "value": "AG--PR-004", "count": 1 }, { "value": "AG--PR-007", "count": 1 }, { "value": "AG--QC-002", "count": 1 } ] } ], "representative_examples": [ "AG-PR-001", "AG--PR-001" ] }, "numeric": null, "detectors": [ { "id": "enumeration", "status": "complete", "primary": true, "eligible_count": 3000, "matched_count": 3000, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [], "coverage": { "eligible": 3000, "tested": 3000, "matched": 3000, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "AG-PR-001", "AG-PR-003", "AG-PR-004", "AG-PR-008", "AG-PR-005", "AG-PR-006", "AG-PR-007", "AG-PR-002", "AG-ON-004", "AG--PR-002" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "distinct": { "status": "complete", "value": 27 } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "AG-PR-001", "type": "string", "record": 1 }, "last": { "value": "AG-QC-005", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 3000, "lowercase": 0, "mixed_case": 0, "no_letters": 0 }, "string_lengths": { "count": 3000, "min_length": 9, "max_length": 10, "mean_length": 9.005333333333333, "median_length": 9, "length_histogram": [ { "length": 9, "count": 2984 }, { "length": 10, "count": 16 } ] }, "numeric": null, "booleans": null, "temporal": null } }, { "id": "column_30", "name": "date_creation", "path": "date_creation", "position": 30, "inferred_type": "date", "type_counts": { "date": 2994, "text": 6 }, "type_confidence": 0.998, "type_error_count": 6, "type_error_percent": 0.2, "missing_count": 0, "missing_percent": 0.0, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2361, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2361, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2361, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2361, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2361, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2361, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2361, "examples": [ "2020-10-23", "2017-08-19", "2018-09-13" ], "value_profile": { "selection": "random_sample", "sampled_distinct_count": 100, "values": [ { "value": "2020-10-23", "count": 5, "truncated": false }, { "value": "2017-08-19", "count": 4, "truncated": false }, { "value": "2018-09-13", "count": 4, "truncated": false }, { "value": "2020-06-23", "count": 2, "truncated": false }, { "value": "2026-04-19", "count": 2, "truncated": false }, { "value": "09-12-2020", "count": 1, "truncated": false }, { "value": "13-02-2017", "count": 1, "truncated": false }, { "value": "17-03-2024", "count": 1, "truncated": false }, { "value": "2016-12-10", "count": 1, "truncated": false }, { "value": "2017-06-08", "count": 1, "truncated": false }, { "value": "2019-06-03", "count": 1, "truncated": false }, { "value": "2019-10-25", "count": 1, "truncated": false }, { "value": "2019-10-29", "count": 1, "truncated": false }, { "value": "2020-06-19", "count": 1, "truncated": false }, { "value": "2022-07-21", "count": 1, "truncated": false }, { "value": "2024-06-28", "count": 1, "truncated": false }, { "value": "2025-04-14", "count": 1, "truncated": false }, { "value": "2026-08-30", "count": 1, "truncated": false }, { "value": "28-04-2020", "count": 1, "truncated": false }, { "value": "30-11-2025", "count": 1, "truncated": false } ] }, "semantic_type": "date", "exposure": null, "date_profile": { "status": "mixed", "present_count": 3000, "valid_count": 2695, "valid_percent": 89.83, "ambiguous_count": 299, "ambiguous_percent": 9.97, "invalid_date_count": 6, "invalid_date_percent": 0.2, "not_date_count": 0, "not_date_percent": 0.0, "resolved_ambiguous_order": null, "ambiguous_order_source": null, "ambiguity_evidence": { "DMY": 359, "MDY": 159 }, "formats": [ { "format": "YYYY-MM-DD", "order": "YMD", "separator": "-", "count": 2169, "percent": 72.3, "iso": true }, { "format": "DD-MM-YYYY", "order": "DMY", "separator": "-", "count": 359, "percent": 11.97, "iso": false }, { "format": "MM-DD-YYYY", "order": "MDY", "separator": "-", "count": 159, "percent": 5.3, "iso": false }, { "format": "YYYY/MM/DD", "order": "YMD", "separator": "/", "count": 8, "percent": 0.27, "iso": false } ], "format_count": 4, "breakdown": [ { "label": "YYYY-MM-DD", "category": "valid", "count": 2169, "percent": 72.3 }, { "label": "DD-MM-YYYY", "category": "valid", "count": 359, "percent": 11.97 }, { "label": "Ambiguous: DD-MM-YYYY or MM-DD-YYYY", "category": "ambiguous", "count": 298, "percent": 9.93 }, { "label": "MM-DD-YYYY", "category": "valid", "count": 159, "percent": 5.3 }, { "label": "YYYY/MM/DD", "category": "valid", "count": 8, "percent": 0.27 }, { "label": "Ambiguous: DD/MM/YYYY or MM/DD/YYYY", "category": "ambiguous", "count": 1, "percent": 0.03 }, { "label": "Invalid date", "category": "invalid", "count": 6, "percent": 0.2 }, { "label": "Not a date", "category": "not_date", "count": 0, "percent": 0.0 } ] }, "string_profile": null, "numeric": null, "detectors": [ { "id": "date", "status": "complete", "primary": false, "eligible_count": 3000, "matched_count": 2695, "matched_percent": 89.83, "ambiguous_count": 299, "invalid_count": 6, "formats": [ { "format": "YYYY-MM-DD", "count": 2169, "percent": 72.3 }, { "format": "DD-MM-YYYY", "count": 359, "percent": 11.97 }, { "format": "MM-DD-YYYY", "count": 159, "percent": 5.3 }, { "format": "YYYY/MM/DD", "count": 8, "percent": 0.27 } ], "coverage": { "eligible": 3000, "tested": 3000, "matched": 2695, "ambiguous": 299, "invalid": 6, "not_matched": 0, "not_tested": 0, "share_tested": 0.8983, "share_eligible": 0.8983 }, "evidence": { "matched": [ "2020-07-08", "2021-11-09", "2016-09-16", "2023-03-04", "2017-05-12", "2025-04-17", "2025-02-28", "2018-07-08", "2022-06-10", "2022-09-11" ], "ambiguous": [ "12-10-2021", "06-11-2026", "11-12-2025", "01-01-2017", "11-11-2017", "02-07-2021", "07-03-2020", "03-02-2018", "12-08-2016", "09-04-2022" ], "invalid": [ "2026-13-40", "13-40-2026", "40-13-2026" ], "not_matched": [] }, "details": { "ambiguity": { "count": 299, "candidates": [ { "formats": [ "DD-MM-YYYY", "MM-DD-YYYY" ], "count": 298 }, { "formats": [ "DD/MM/YYYY", "MM/DD/YYYY" ], "count": 1 } ], "evidence": { "DMY": 359, "MDY": 159 }, "resolution": null } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "2020-07-08", "type": "string", "record": 1 }, "last": { "value": "14-04-2026", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 0, "mixed_case": 0, "no_letters": 3000 }, "string_lengths": { "count": 3000, "min_length": 10, "max_length": 10, "mean_length": 10, "median_length": 10, "length_histogram": [ { "length": 10, "count": 3000 } ] }, "numeric": null, "booleans": null, "temporal": { "count": 2695, "ambiguous": 299, "kinds": [ { "kind": "date", "count": 2695, "min": "2016-08-24", "max": "2026-09-16", "years": [ { "year": 2016, "count": 82 }, { "year": 2017, "count": 232 }, { "year": 2018, "count": 220 }, { "year": 2019, "count": 249 }, { "year": 2020, "count": 264 }, { "year": 2021, "count": 260 }, { "year": 2022, "count": 265 }, { "year": 2023, "count": 289 }, { "year": 2024, "count": 281 }, { "year": 2025, "count": 331 }, { "year": 2026, "count": 222 } ] } ] } } }, { "id": "column_31", "name": "date_modification", "path": "date_modification", "position": 31, "inferred_type": "date", "type_counts": { "date": 2997, "text": 3 }, "type_confidence": 0.999, "type_error_count": 3, "type_error_percent": 0.1, "missing_count": 0, "missing_percent": 0.0, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 2035, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2035, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2035, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2035, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2035, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 2035, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 2035, "examples": [ "2026-09-06", "2025-05-28", "2026-06-27" ], "value_profile": { "selection": "random_sample", "sampled_distinct_count": 100, "values": [ { "value": "2026-09-06", "count": 8, "truncated": false }, { "value": "2025-05-28", "count": 7, "truncated": false }, { "value": "2026-06-27", "count": 7, "truncated": false }, { "value": "2024-10-02", "count": 3, "truncated": false }, { "value": "12-04-2026", "count": 2, "truncated": false }, { "value": "2022-05-05", "count": 2, "truncated": false }, { "value": "2024-11-04", "count": 2, "truncated": false }, { "value": "2025-01-04", "count": 2, "truncated": false }, { "value": "2025-06-26", "count": 2, "truncated": false }, { "value": "2025-09-06", "count": 2, "truncated": false }, { "value": "05-19-2024", "count": 1, "truncated": false }, { "value": "11-15-2025", "count": 1, "truncated": false }, { "value": "2018-12-15", "count": 1, "truncated": false }, { "value": "2019-03-26", "count": 1, "truncated": false }, { "value": "2021-11-24", "count": 1, "truncated": false }, { "value": "2024-01-14", "count": 1, "truncated": false }, { "value": "2024-03-16", "count": 1, "truncated": false }, { "value": "2024-05-22", "count": 1, "truncated": false }, { "value": "2024-09-06", "count": 1, "truncated": false }, { "value": "25-04-2021", "count": 1, "truncated": false } ] }, "semantic_type": "date", "exposure": null, "date_profile": { "status": "mixed", "present_count": 3000, "valid_count": 2684, "valid_percent": 89.47, "ambiguous_count": 313, "ambiguous_percent": 10.43, "invalid_date_count": 3, "invalid_date_percent": 0.1, "not_date_count": 0, "not_date_percent": 0.0, "resolved_ambiguous_order": null, "ambiguous_order_source": null, "ambiguity_evidence": { "DMY": 346, "MDY": 159 }, "formats": [ { "format": "YYYY-MM-DD", "order": "YMD", "separator": "-", "count": 2174, "percent": 72.47, "iso": true }, { "format": "DD-MM-YYYY", "order": "DMY", "separator": "-", "count": 345, "percent": 11.5, "iso": false }, { "format": "MM-DD-YYYY", "order": "MDY", "separator": "-", "count": 159, "percent": 5.3, "iso": false }, { "format": "YYYY/MM/DD", "order": "YMD", "separator": "/", "count": 5, "percent": 0.17, "iso": false }, { "format": "DD/MM/YYYY", "order": "DMY", "separator": "/", "count": 1, "percent": 0.03, "iso": false } ], "format_count": 5, "breakdown": [ { "label": "YYYY-MM-DD", "category": "valid", "count": 2174, "percent": 72.47 }, { "label": "DD-MM-YYYY", "category": "valid", "count": 345, "percent": 11.5 }, { "label": "Ambiguous: DD-MM-YYYY or MM-DD-YYYY", "category": "ambiguous", "count": 312, "percent": 10.4 }, { "label": "MM-DD-YYYY", "category": "valid", "count": 159, "percent": 5.3 }, { "label": "YYYY/MM/DD", "category": "valid", "count": 5, "percent": 0.17 }, { "label": "Ambiguous: DD/MM/YYYY or MM/DD/YYYY", "category": "ambiguous", "count": 1, "percent": 0.03 }, { "label": "DD/MM/YYYY", "category": "valid", "count": 1, "percent": 0.03 }, { "label": "Invalid date", "category": "invalid", "count": 3, "percent": 0.1 }, { "label": "Not a date", "category": "not_date", "count": 0, "percent": 0.0 } ] }, "string_profile": null, "numeric": null, "detectors": [ { "id": "date", "status": "complete", "primary": false, "eligible_count": 3000, "matched_count": 2684, "matched_percent": 89.47, "ambiguous_count": 313, "invalid_count": 3, "formats": [ { "format": "YYYY-MM-DD", "count": 2174, "percent": 72.47 }, { "format": "DD-MM-YYYY", "count": 345, "percent": 11.5 }, { "format": "MM-DD-YYYY", "count": 159, "percent": 5.3 }, { "format": "YYYY/MM/DD", "count": 5, "percent": 0.17 }, { "format": "DD/MM/YYYY", "count": 1, "percent": 0.03 } ], "coverage": { "eligible": 3000, "tested": 3000, "matched": 2684, "ambiguous": 313, "invalid": 3, "not_matched": 0, "not_tested": 0, "share_tested": 0.8947, "share_eligible": 0.8947 }, "evidence": { "matched": [ "2024-10-24", "2021-11-22", "2017-04-05", "2024-06-01", "2019-10-29", "2026-06-07", "2025-10-06", "2026-01-16", "2023-02-24", "2023-08-08" ], "ambiguous": [ "05-03-2026", "02-11-2022", "03-11-2020", "06-09-2025", "06-12-2020", "03-08-2026", "12-07-2025", "07-02-2025", "04-12-2025", "07-11-2023" ], "invalid": [ "2026-13-40", "40-13-2026" ], "not_matched": [] }, "details": { "ambiguity": { "count": 313, "candidates": [ { "formats": [ "DD-MM-YYYY", "MM-DD-YYYY" ], "count": 312 }, { "formats": [ "DD/MM/YYYY", "MM/DD/YYYY" ], "count": 1 } ], "evidence": { "DMY": 346, "MDY": 159 }, "resolution": null } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 3000, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 0, "blank": 0, "marker": 0, "content": 3000 }, "missing": { "count": 0, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 0, "blank": 0, "marker": 0 } }, "first": { "value": "2024-10-24", "type": "string", "record": 1 }, "last": { "value": "15-04-2026", "type": "string", "record": 3000 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 0, "mixed_case": 0, "no_letters": 3000 }, "string_lengths": { "count": 3000, "min_length": 10, "max_length": 10, "mean_length": 10, "median_length": 10, "length_histogram": [ { "length": 10, "count": 3000 } ] }, "numeric": null, "booleans": null, "temporal": { "count": 2684, "ambiguous": 313, "kinds": [ { "kind": "date", "count": 2684, "min": "2016-11-07", "max": "2026-09-16", "years": [ { "year": 2016, "count": 3 }, { "year": 2017, "count": 19 }, { "year": 2018, "count": 31 }, { "year": 2019, "count": 84 }, { "year": 2020, "count": 120 }, { "year": 2021, "count": 175 }, { "year": 2022, "count": 232 }, { "year": 2023, "count": 293 }, { "year": 2024, "count": 420 }, { "year": 2025, "count": 576 }, { "year": 2026, "count": 731 } ] } ] } } }, { "id": "column_32", "name": "date_reclamation", "path": "date_reclamation", "position": 32, "inferred_type": "date", "type_counts": { "date": 419, "text": 1 }, "type_confidence": 0.9976, "type_error_count": 1, "type_error_percent": 0.24, "missing_count": 2580, "missing_percent": 86.0, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 406, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 406, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 406, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 406, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 406, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 406, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 406, "examples": [ "10-12-2025", "12-06-2026", "2019-02-06" ], "value_profile": { "selection": "random_sample", "sampled_distinct_count": 100, "values": [ { "value": "10-12-2025", "count": 2, "truncated": false }, { "value": "12-06-2026", "count": 2, "truncated": false }, { "value": "2019-02-06", "count": 2, "truncated": false }, { "value": "2025-05-25", "count": 2, "truncated": false }, { "value": "09-04-2025", "count": 1, "truncated": false }, { "value": "09-28-2024", "count": 1, "truncated": false }, { "value": "14-07-2025", "count": 1, "truncated": false }, { "value": "17-08-2026", "count": 1, "truncated": false }, { "value": "2018-11-20", "count": 1, "truncated": false }, { "value": "2020-12-01", "count": 1, "truncated": false }, { "value": "2021-08-04", "count": 1, "truncated": false }, { "value": "2021-09-29", "count": 1, "truncated": false }, { "value": "2022-07-24", "count": 1, "truncated": false }, { "value": "2024-07-10", "count": 1, "truncated": false }, { "value": "2024-07-21", "count": 1, "truncated": false }, { "value": "2024-10-06", "count": 1, "truncated": false }, { "value": "2025-09-12", "count": 1, "truncated": false }, { "value": "2026-06-24", "count": 1, "truncated": false }, { "value": "26-12-2023", "count": 1, "truncated": false }, { "value": "28-01-2026", "count": 1, "truncated": false } ] }, "semantic_type": "date", "exposure": null, "date_profile": { "status": "mixed", "present_count": 420, "valid_count": 366, "valid_percent": 87.14, "ambiguous_count": 53, "ambiguous_percent": 12.62, "invalid_date_count": 1, "invalid_date_percent": 0.24, "not_date_count": 0, "not_date_percent": 0.0, "resolved_ambiguous_order": null, "ambiguous_order_source": null, "ambiguity_evidence": { "DMY": 46, "MDY": 24 }, "formats": [ { "format": "YYYY-MM-DD", "order": "YMD", "separator": "-", "count": 296, "percent": 70.48, "iso": true }, { "format": "DD-MM-YYYY", "order": "DMY", "separator": "-", "count": 46, "percent": 10.95, "iso": false }, { "format": "MM-DD-YYYY", "order": "MDY", "separator": "-", "count": 24, "percent": 5.71, "iso": false } ], "format_count": 3, "breakdown": [ { "label": "YYYY-MM-DD", "category": "valid", "count": 296, "percent": 70.48 }, { "label": "Ambiguous: DD-MM-YYYY or MM-DD-YYYY", "category": "ambiguous", "count": 53, "percent": 12.62 }, { "label": "DD-MM-YYYY", "category": "valid", "count": 46, "percent": 10.95 }, { "label": "MM-DD-YYYY", "category": "valid", "count": 24, "percent": 5.71 }, { "label": "Invalid date", "category": "invalid", "count": 1, "percent": 0.24 }, { "label": "Not a date", "category": "not_date", "count": 0, "percent": 0.0 } ] }, "string_profile": null, "numeric": null, "detectors": [ { "id": "date", "status": "complete", "primary": false, "eligible_count": 420, "matched_count": 366, "matched_percent": 87.14, "ambiguous_count": 53, "invalid_count": 1, "formats": [ { "format": "YYYY-MM-DD", "count": 296, "percent": 70.48 }, { "format": "DD-MM-YYYY", "count": 46, "percent": 10.95 }, { "format": "MM-DD-YYYY", "count": 24, "percent": 5.71 } ], "coverage": { "eligible": 420, "tested": 420, "matched": 366, "ambiguous": 53, "invalid": 1, "not_matched": 0, "not_tested": 0, "share_tested": 0.8714, "share_eligible": 0.8714 }, "evidence": { "matched": [ "2026-05-13", "2026-05-21", "2025-10-18", "2026-06-13", "2025-01-01", "2024-01-23", "2023-09-01", "2024-07-28", "2026-08-16", "2026-04-25" ], "ambiguous": [ "12-06-2026", "05-07-2025", "08-03-2026", "05-02-2025", "08-11-2021", "01-06-2022", "08-03-2024", "07-11-2024", "12-01-2025", "05-05-2023" ], "invalid": [ "2026-13-40" ], "not_matched": [] }, "details": { "ambiguity": { "count": 53, "candidates": [ { "formats": [ "DD-MM-YYYY", "MM-DD-YYYY" ], "count": 53 } ], "evidence": { "DMY": 46, "MDY": 24 }, "resolution": null } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 420, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 2580, "blank": 0, "marker": 0, "content": 420 }, "missing": { "count": 2580, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 2580, "blank": 0, "marker": 0 } }, "first": { "value": "2026-05-13", "type": "string", "record": 6 }, "last": { "value": "28-01-2026", "type": "string", "record": 2999 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 0, "mixed_case": 0, "no_letters": 420 }, "string_lengths": { "count": 420, "min_length": 10, "max_length": 10, "mean_length": 10, "median_length": 10, "length_histogram": [ { "length": 10, "count": 420 } ] }, "numeric": null, "booleans": null, "temporal": { "count": 366, "ambiguous": 53, "kinds": [ { "kind": "date", "count": 366, "min": "2017-10-11", "max": "2026-09-16", "years": [ { "year": 2017, "count": 2 }, { "year": 2018, "count": 7 }, { "year": 2019, "count": 17 }, { "year": 2020, "count": 22 }, { "year": 2021, "count": 16 }, { "year": 2022, "count": 30 }, { "year": 2023, "count": 43 }, { "year": 2024, "count": 55 }, { "year": 2025, "count": 78 }, { "year": 2026, "count": 96 } ] } ] } } }, { "id": "column_33", "name": "montant_reclamation", "path": "montant_reclamation", "position": 33, "inferred_type": "number", "type_counts": { "number": 349 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 2651, "missing_percent": 88.37, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 344, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 344, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 344, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 344, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 344, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 344, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 344, "examples": [ "0.00", "14731.85", "-63902.75" ], "value_profile": { "selection": "random_sample", "sampled_distinct_count": 100, "values": [ { "value": "0.00", "count": 5, "truncated": false }, { "value": "14731.85", "count": 2, "truncated": false }, { "value": "-63902.75", "count": 1, "truncated": false }, { "value": "11470.48", "count": 1, "truncated": false }, { "value": "12639.37", "count": 1, "truncated": false }, { "value": "129935.17", "count": 1, "truncated": false }, { "value": "19006.52", "count": 1, "truncated": false }, { "value": "24718.97", "count": 1, "truncated": false }, { "value": "27656.18", "count": 1, "truncated": false }, { "value": "36080.21", "count": 1, "truncated": false }, { "value": "38914.74", "count": 1, "truncated": false }, { "value": "38995.13", "count": 1, "truncated": false }, { "value": "4015.68", "count": 1, "truncated": false }, { "value": "4624.56", "count": 1, "truncated": false }, { "value": "6160.20", "count": 1, "truncated": false }, { "value": "81330.68", "count": 1, "truncated": false }, { "value": "8303.41", "count": 1, "truncated": false }, { "value": "91386.63", "count": 1, "truncated": false }, { "value": "9433.94", "count": 1, "truncated": false }, { "value": "9471.63", "count": 1, "truncated": false } ] }, "semantic_type": null, "exposure": null, "date_profile": null, "string_profile": null, "numeric": { "minimum": -63902.75, "maximum": 179995.88, "range": 243898.63, "mean": 28917.03323782235, "median": 19513.98 }, "detectors": [ { "id": "number", "status": "complete", "primary": true, "eligible_count": 349, "matched_count": 349, "matched_percent": 100.0, "ambiguous_count": 0, "invalid_count": 0, "formats": [ { "format": "0.0", "count": 349, "percent": 100.0 } ], "coverage": { "eligible": 349, "tested": 349, "matched": 349, "ambiguous": 0, "invalid": 0, "not_matched": 0, "not_tested": 0, "share_tested": 1.0, "share_eligible": 1.0 }, "evidence": { "matched": [ "24940.92", "4087.60", "25200.13", "13463.64", "13721.04", "15301.03", "19325.85", "56421.85", "24978.40", "6403.63" ], "ambiguous": [], "invalid": [], "not_matched": [] }, "details": { "ambiguity": { "count": 0, "candidates": [], "evidence": { "comma": 0, "dot": 349 }, "resolution": null } }, "adaptive": null } ], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 349, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 2651, "blank": 0, "marker": 0, "content": 349 }, "missing": { "count": 2651, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 2651, "blank": 0, "marker": 0 } }, "first": { "value": "24940.92", "type": "string", "record": 6 }, "last": { "value": "10654.50", "type": "string", "record": 2999 }, "string_characteristics": { "non_ascii": 0, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 0, "mixed_case": 0, "no_letters": 349 }, "string_lengths": { "count": 349, "min_length": 4, "max_length": 9, "mean_length": 7.819484240687679, "median_length": 8, "length_histogram": [ { "length": 4, "count": 5 }, { "length": 6, "count": 1 }, { "length": 7, "count": 59 }, { "length": 8, "count": 266 }, { "length": 9, "count": 18 } ] }, "numeric": { "count": 349, "native_count": 0, "text_count": 349, "min": -63902.75, "max": 179995.88, "sum": 10092044.6, "mean": 28917.03323782235, "population_variance": 834899485.7147342, "population_std": 28894.627281118097, "positive": 343, "negative": 1, "zero": 5, "integral_decimals": 12, "median": { "status": "complete", "value": 19513.98 } }, "booleans": null, "temporal": null } }, { "id": "column_34", "name": "reclamation_status", "path": "reclamation_status", "position": 34, "inferred_type": "text", "type_counts": { "text": 440 }, "type_confidence": 1.0, "type_error_count": 0, "type_error_percent": 0.0, "missing_count": 2560, "missing_percent": 85.33, "with_issues": true, "normalization": { "trim_count": 0, "trim_percent": 0.0, "collapse_internal_whitespace_count": 0, "collapse_internal_whitespace_percent": 0.0, "stages": [ { "stage": "raw", "enabled": true, "changed_count": null, "changed_percent": null, "distinct_count": 4, "distinct_status": "complete" }, { "stage": "nfc", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 4, "distinct_status": "complete" }, { "stage": "trim", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 4, "distinct_status": "complete" }, { "stage": "collapse_whitespace", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 4, "distinct_status": "complete" }, { "stage": "casefold", "enabled": true, "changed_count": 0, "changed_percent": 0.0, "distinct_count": 4, "distinct_status": "complete" }, { "stage": "strip_accents", "enabled": true, "changed_count": 247, "changed_percent": 8.23, "distinct_count": 4, "distinct_status": "complete" } ], "variant_group_count": 0, "variant_group_status": "complete", "variant_groups": [], "variant_groups_truncated": false }, "distinct_count": 4, "examples": [ "fermé", "en_cours", "ouvert" ], "value_profile": { "selection": "complete", "sampled_distinct_count": 4, "values": [ { "value": "fermé", "count": 218, "truncated": false }, { "value": "en_cours", "count": 127, "truncated": false }, { "value": "ouvert", "count": 66, "truncated": false }, { "value": "rejeté", "count": 29, "truncated": false } ] }, "semantic_type": null, "exposure": null, "date_profile": null, "string_profile": { "status": "short", "present_count": 440, "minimum_length": 5, "maximum_length": 8, "mean_length": 6.08, "median_length": 6.0, "distinct_length_count": 3, "fixed_length": null, "length_distribution": [ { "length": 5, "count": 218, "percent": 49.55, "relative_percent": 100.0, "examples": [ { "value": "fermé", "count": 218 } ] }, { "length": 6, "count": 95, "percent": 21.59, "relative_percent": 43.58, "examples": [ { "value": "ouvert", "count": 66 }, { "value": "rejeté", "count": 29 } ] }, { "length": 8, "count": 127, "percent": 28.86, "relative_percent": 58.26, "examples": [ { "value": "en_cours", "count": 127 } ] } ], "representative_examples": [ "fermé", "en_cours", "ouvert" ] }, "numeric": null, "detectors": [], "scan_details": { "first_record": 1, "occurrences": 3000, "value_count": 440, "presence": { "parent_type": "object", "parent_count": 3000, "present": 3000, "absent": 0 }, "native_types": { "string": 3000 }, "strings": { "count": 3000, "empty": 2560, "blank": 0, "marker": 0, "content": 440 }, "missing": { "count": 2560, "definition": [ "absent", "null", "empty", "blank", "marker" ], "components": { "absent": 0, "null": 0, "empty": 2560, "blank": 0, "marker": 0 } }, "first": { "value": "rejeté", "type": "string", "record": 6 }, "last": { "value": "fermé", "type": "string", "record": 2999 }, "string_characteristics": { "non_ascii": 247, "with_line_breaks": 0, "with_control_characters": 0, "with_surrounding_whitespace": 0, "with_repeated_whitespace": 0, "uppercase": 0, "lowercase": 440, "mixed_case": 0, "no_letters": 0 }, "string_lengths": { "count": 440, "min_length": 5, "max_length": 8, "mean_length": 6.081818181818182, "median_length": 6, "length_histogram": [ { "length": 5, "count": 218 }, { "length": 6, "count": 95 }, { "length": 8, "count": 127 } ] }, "numeric": null, "booleans": null, "temporal": null } } ], "issues": [ { "code": "duplicate_rows", "severity": "warning", "message": "Duplicate rows beyond their first occurrence", "count": 8, "column_ids": [], "row_numbers": [ 1521, 1814, 1999, 2064, 2268, 2527, 2543, 2627 ] }, { "code": "missing_values", "severity": "warning", "message": "Missing cells", "count": 12532, "column_ids": [ "column_4", "column_5", "column_6", "column_12", "column_13", "column_15", "column_21", "column_22", "column_24", "column_32", "column_33", "column_34" ], "row_numbers": [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] }, { "code": "trimmed_cells", "severity": "info", "message": "Cells changed by trimming surrounding whitespace", "count": 0, "column_ids": [], "row_numbers": [] }, { "code": "collapsed_whitespace", "severity": "info", "message": "Cells changed by collapsing repeated internal whitespace", "count": 129, "column_ids": [ "column_4", "column_5", "column_11", "column_14", "column_17", "column_19", "column_20" ], "row_numbers": [] }, { "code": "variant_groups", "severity": "info", "message": "Values written in several ways that normalization compares as equal", "count": 74, "column_ids": [ "column_4", "column_5", "column_10", "column_11", "column_14", "column_15", "column_16", "column_17", "column_18", "column_28" ], "row_numbers": [] }, { "code": "ambiguous_dates", "severity": "warning", "message": "Date values matching more than one day-month order", "count": 1630, "column_ids": [ "column_6", "column_23", "column_24", "column_30", "column_31", "column_32" ], "row_numbers": [] } ], "preview": [ { "row_number": 1, "values": [ "principal", "CLI-00000281", "Mme", "Lucie", "Roy", "1961-03-31", "F", "fr", "4682", "chemin", "des Tulipes", "", "245", "Montréal", "QC", "Québec", "H4A 9M3", "CA", "aa9999@aaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000000281", "auto", "2020-07-16", "2026-12-28", "actif", "1234.18", "mensuelle", "chèque", "AG-PR-001", "2020-07-08", "2024-10-24", "", "", "" ], "absent": [] }, { "row_number": 2, "values": [ "principal", "CLI-00000432", "Mme", "Suzanne", "Taylor", "1983-01-14", "F", "fr", "518", "rue", "des Trois-Lacs", "", "405", "Lévis", "QC", "Québec", "G6V 8P2", "CA", "aaa9999@aaaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000000432", "vie", "2027-06-02", "2021-11-27", "actif", "1123.69", "mensuelle", "prélèvement", "AG-PR-003", "2021-11-09", "2021-11-22", "", "", "" ], "absent": [] }, { "row_number": 3, "values": [ "principal", "CLI-00000538", "Mme", "Juliette", "Michaud", "1941-09-10", "F", "fr", "2943", "avenue", "des Vents", "", "", "Granby", "QC", "Québec", "J2H 0H3", "CA", "aaa99@aaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000000538", "voyage", "2016-09-30", "2022-07-20", "résilié", "379.29", "mensuelle", "prélèvement", "AG-PR-001", "2016-09-16", "2017-04-05", "", "", "" ], "absent": [] }, { "row_number": 4, "values": [ "principal", "CLI-0000072", "M.", "Oliivier", "Landry", "1936-12-13", "M", "fr", "6132", "route", "des Prairies", "", "519", "Repentigny", "QC", "Québec", "J5Y 2J3", "CA", "aaaaaa.aaaaaaa@aaaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000000726", "auto", "2023-03-29", "2027-05-07", "actif", "-744.79", "mensuelle", "prélèvement", "AG-PR-004", "2023-03-04", "2024-06-01", "", "", "" ], "absent": [] }, { "row_number": 5, "values": [ "principal", "CLI-00000892", "Mme", "Nicole", "Tremblay", "1943-04-16", "F", "fr", "9307", "chemin", "des Ormes", "", "", "Québec", "QC", "Québec", "G2B 7V8", "CA", "aaaaaaaaaaaaaa@aaaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000000892", "voyage", "2017-05-26", "2018-11-19", "résilié", "241.17", "mensuelle", "prélèvement", "AG-PR-004", "2017-05-12", "2019-10-29", "", "", "" ], "absent": [] }, { "row_number": 6, "values": [ "principal", "CLI-00001006", "M.", "Luke", "Pham", "1979-07-29", "M", "en", "2174", "Street", "Riverside", "", "", "Winnipeg", "MB", "Manitoba", "R3C 4S8", "CA", "aaaaa@aaaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000001006", "auto", "2025-05-17", "2026-07-30", "expiré", "695.97", "mensuelle", "prélèvement", "AG-PR-008", "2025-04-17", "2026-06-07", "2026-05-13", "24940.92", "rejeté" ], "absent": [] }, { "row_number": 7, "values": [ "principal", "CLI-00001095", "M.", "Émile", "Lavoie", "1996-03-27", "M", "fr", "909", "rue", "du Lac", "", "358", "Lévis", "QC", "Québec", "G6V 8A4", "CA", "aaaaa.aaaaaa@aaaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000001095", "auto", "2025-03-16", "2027-01-30", "actif", "1144.35", "annuelle", "prélèvement", "AG-PR-005", "2025-02-28", "2025-10-06", "", "", "" ], "absent": [] }, { "row_number": 8, "values": [ "principal", "CLI-00001384", "Mme", "Catherine", "Gagné", "1958-01-22", "F", "fr", "6362", "promenade", "des Geais-Bleus", "Ouest", "", "Lévis", "QC", "Québec", "G6W 9E4", "CA", "aaaaaa@aaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000001384", "voyage", "2018-07-30", "", "actif", "433.12", "mensuelle", "prélèvement", "AG-PR-001", "2018-07-08", "2026-01-16", "", "", "" ], "absent": [] }, { "row_number": 9, "values": [ "principal", "CLI-00001430", "M.", "Jack", "Chowdhury", "1987-11-05", "M", "en", "7641", "Place", "Pine", "", "", "Toronto", "ON", "Ontario", "M6G 7M3", "CA", "aaaa99@aaaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000001430", "habitation", "2022-06-11", "", "actif", "1509.17", "mensuelle", "prélèvement", "AG-PR-001", "2022-06-10", "2023-02-24", "", "", "" ], "absent": [] }, { "row_number": 10, "values": [ "principal", "CLI--00001642", "Mme", "Catherine", "Caron", "1981-09-04", "F", "fr", "528", "rue", "de l'Aube", "", "", "Montréal", "QC", "Québec", "H4A 4S8", "CA", "aaaaaaaaaaaaaa@aaaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000001642", "voyage", "2022-09-27", "2027-05-13", "actif", "405.78", "mensuelle", "prélèvement", "AG-PR-004", "2022-09-11", "2023-08-08", "", "", "" ], "absent": [] }, { "row_number": 11, "values": [ "principal", "CLI-00001668", "Mme", "sofia", "baker", "1942-02-06", "F", "en", "1544", "Avenue", "oak", "", "557", "chateauguay", "QC", "quebec", "J6J 3K7", "CA", "aaaaaaaaaa@aaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000001668", "vie", "2024-09-11", "2027-07-11", "actif", "1043.75", "mensuelle", "prélèvement", "AG-PR-006", "2024-08-24", "2026-04-01", "", "", "" ], "absent": [] }, { "row_number": 12, "values": [ "principal", "CLI-00001783", "Mme", "Aria", "Thompson", "1995-03-16", "F", "en", "876", "Avenue", "School", "", "", "Ottawg", "ON", "Ontario", "K1A 4T0", "CA", "aaaaaaaa99@aaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000001783", "auto", "2017-07-01", "2027-04-23", "actif", "672.10", "annuelle", "prélèvement", "AG-PR-004", "2017-06-04", "2019-07-31", "", "", "" ], "absent": [] }, { "row_number": 13, "values": [ "principal", "CLI-00001927", "M.", "Jean", "Côté", "1994-09-21", "M", "fr", "2629", "route", "de la Traverse", "Nord", "991", "Mnotréal", "QC", "Québec", "H2X 4P4", "CA", "aaaaaaaa@aaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000001927", "habitation", "2021-02-26", "2027-02-23", "actif", "2727.70", "annuelle", "chèque", "AG-PR-007", "2021-02-03", "2022-11-27", "", "", "" ], "absent": [] }, { "row_number": 14, "values": [ "principal", "CLI-00002289", "M.", "Maxime", "Gagnon", "1959-11-12", "M", "fr", "5066", "avenue", "du Parc", "", "244", "Québec", "QC", "Québec", "G2B 5E5", "CA", "aaaaaaaaaaaa@aaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000002289", "auto", "2026-01-07", "2026-12-24", "actif", "1428.63", "mensuelle", "prélèvement", "AG-PR-001", "2025-12-16", "2026-02-28", "", "", "" ], "absent": [] }, { "row_number": 15, "values": [ "principal", "CLI-00002347", "M.", "Émile", "Rodriguez", "1996-05-21", "M", "fr", "2985", "rue", "des Saules", "", "283", "Québec", "QC", "Québec", "G2B 9H7", "CA", "aaaaa.aaaaaaaaa@aaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000002347", "voyage", "2023-02-16", "", "actif", "652.13", "mensuelle", "prélèvement", "AG-PR-004", "2023-02-05", "2026-02-01", "", "", "" ], "absent": [] }, { "row_number": 16, "values": [ "principal", "CLI-00002991", "M.", "Michael", "Walker", "2001-11-15", "M", "en", "9868", "Way", "Spring", "", "", "Québec", "QC", "Québec", "G2B 2E7", "CA", "aaaaaaa_aaaaaa@aaaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000002991", "vie", "2025-08-01", "2027-03-08", "actif", "2798.92", "mensuelle", "prélèvement", "AG-PR-005", "2025-08-01", "2026-01-05", "", "", "" ], "absent": [] }, { "row_number": 17, "values": [ "principal", "CLI-00003000", "Mme", "Marie", "Patel", "1979-11-10", "F", "fr", "4453", "rue", "du Havre", "", "868", "Québec", "QC", "Québec", "G1V 4H0", "CA", "aaaaa9999@aaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000003000", "habitation", "2020-01-28", "2027-03-15", "actif", "2147.32", "mensuelle", "prélèvement", "AG-PR-006", "2020-01-16", "2022-09-15", "", "", "" ], "absent": [] }, { "row_number": 18, "values": [ "principal", "CLI-00003159", "Mme", "Anne", "Paquette", "1943-03-15", "F", "fr", "2897", "croissant", "du Moulin", "", "", "Montréal", "QC", "Québec", "H4A 3C2", "CA", "aaaa99@aaaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000003159", "auto", "2024-12-20", "2027-04-15", "actif", "1731.59", "mensuelle", "carte", "AG-PR-007", "2024-12-08", "2026-02-09", "", "", "" ], "absent": [] }, { "row_number": 19, "values": [ "principal", "CLI-00003200", "M.", "Sylvain", "Silva", "1966-09-14", "M", "fr", "26", "carré", "des Lilas", "", "", "Hamilton", "ON", "Ontario", "L8S 1B2", "CA", "aaaaaaa_aaaaa@aaaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000003200", "vie", "2026-06-14", "2027-05-14", "actif", "4319.82", "mensuelle", "prélèvement", "AG-PR-003", "2026-05-19", "2026-06-08", "", "", "" ], "absent": [] }, { "row_number": 20, "values": [ "principal", "CLI-00003271", "M.", "Jean-Philippe", "Ouellet", "1978-04-11", "M", "fr", "6502", "avenue", "des Champs", "Ouest", "", "Fredericton", "NB", "Nouveau-Brunswick", "E3B 3G8", "CA", "aaaaaaaaaaaa.aaaaaaa@aaaaaaa.aaaaaaa", "+9-999-999-9999", "CTR-1000003271", "vie", "2024-02-22", "2026-11-10", "actif", "1253.03", "mensuelle", "prélèvement", "AG-PR-001", "2024-02-04", "2025-05-28", "", "", "" ], "absent": [] } ], "limits": { "measures": [], "untracked_observations": 0, "depth_truncated_observations": 0, "diagnostics": [] }, "structure": null } ] }