csv-detective 0.7.5.dev1180__py3-none-any.whl → 0.7.5.dev1209__py3-none-any.whl

csv_detective/utils.py

@@ -1,15 +1,6 @@
-from typing import Callable, Optional, Union
-import json
-import pandas as pd
 import logging
-from time import time
-from datetime import date, datetime
-
-from csv_detective.detect_fields.other.booleen import bool_casting
-from csv_detective.detect_fields.other.float import float_casting
-from csv_detective.detect_fields.temp.date import date_casting
-
-logging.basicConfig(level=logging.INFO)
+import math
+from typing import Optional
 
 
 def display_logs_depending_process_time(prompt: str, duration: float):
@@ -25,193 +16,20 @@ def display_logs_depending_process_time(prompt: str, duration: float):
     if duration < threshold_warn:
         logging.info(prompt)
     elif duration < threshold_critical:
-        logging.warn(prompt)
+        logging.warning(prompt)
     else:
         logging.critical(prompt)
 
 
-def test_col_val(
-    serie: pd.Series,
-    test_func: Callable,
-    proportion: float = 0.9,
-    skipna: bool = True,
-    limited_output: bool = False,
-    verbose: bool = False,
-):
-    """Tests values of the serie using test_func.
-         - skipna : if True indicates that NaNs are not counted as False
-         - proportion :  indicates the proportion of values that have to pass the test
-    for the serie to be detected as a certain format
-    """
-    if verbose:
-        start = time()
-
-    # TODO : change for a cleaner method and only test columns in modules labels
-    def apply_test_func(serie: pd.Series, test_func: Callable, _range: int):
-        return serie.sample(n=_range).apply(test_func)
-    try:
-        if skipna:
-            serie = serie[serie.notnull()]
-        ser_len = len(serie)
-        if ser_len == 0:
-            return 0.0
-        if not limited_output:
-            result = apply_test_func(serie, test_func, ser_len).sum() / ser_len
-            return result if result >= proportion else 0.0
-        else:
-            if proportion == 1:  # Then try first 1 value, then 5, then all
-                for _range in [
-                    min(1, ser_len),
-                    min(5, ser_len),
-                    ser_len,
-                ]:  # Pour ne pas faire d'opérations inutiles, on commence par 1,
-                    # puis 5 valeurs puis la serie complète
-                    if all(apply_test_func(serie, test_func, _range)):
-                        # print(serie.name, ': check OK')
-                        pass
-                    else:
-                        return 0.0
-                return 1.0
-            else:
-                # if we have a proportion, statistically it's OK to analyse up to 10k rows
-                # (arbitrary number) and get a significant result
-                to_analyse = min(ser_len, 10000)
-                result = apply_test_func(serie, test_func, to_analyse).sum() / to_analyse
-                return result if result >= proportion else 0.0
-    finally:
-        if verbose and time() - start > 3:
-            display_logs_depending_process_time(
-                f"\t/!\\ Column '{serie.name}' took too long ({round(time() - start, 3)}s)",
-                time() - start
-            )
-
-
-def test_col_label(label: str, test_func: Callable, proportion: float = 1, limited_output: bool = False):
-    """Tests label (from header) using test_func.
-    - proportion :  indicates the minimum score to pass the test for the serie
-    to be detected as a certain format
-    """
-    if not limited_output:
-        return test_func(label)
-    else:
-        result = test_func(label)
-        return result if result >= proportion else 0
-
-
-def test_col(table: pd.DataFrame, all_tests: list, limited_output: bool, skipna: bool = True, verbose: bool = False):
-    # Initialising dict for tests
-    if verbose:
-        start = time()
-        logging.info("Testing columns to get types")
-    test_funcs = dict()
-    for test in all_tests:
-        name = test.__name__.split(".")[-1]
-        test_funcs[name] = {"func": test._is, "prop": test.PROPORTION}
-    return_table = pd.DataFrame(columns=table.columns)
-    for idx, (key, value) in enumerate(test_funcs.items()):
-        if verbose:
-            start_type = time()
-            logging.info(f"\t- Starting with type '{key}'")
-        # improvement lead : put the longest tests behind and make them only if previous tests not satisfactory
-        # => the following needs to change, "apply" means all columns are tested for one type at once
-        return_table.loc[key] = table.apply(
-            lambda serie: test_col_val(
-                serie,
-                value["func"],
-                value["prop"],
-                skipna=skipna,
-                limited_output=limited_output,
-                verbose=verbose,
-            )
-        )
-        if verbose:
-            display_logs_depending_process_time(
-                f'\t> Done with type "{key}" in {round(time() - start_type, 3)}s ({idx+1}/{len(test_funcs)})',
-                time() - start_type
-            )
-    if verbose:
-        display_logs_depending_process_time(f"Done testing columns in {round(time() - start, 3)}s", time() - start)
-    return return_table
-
-
-def test_label(table: pd.DataFrame, all_tests: list, limited_output: bool, verbose: bool = False):
-    # Initialising dict for tests
-    if verbose:
-        start = time()
-        logging.info("Testing labels to get types")
-    test_funcs = dict()
-    for test in all_tests:
-        name = test.__name__.split(".")[-1]
-        test_funcs[name] = {"func": test._is, "prop": test.PROPORTION}
-
-    return_table = pd.DataFrame(columns=table.columns)
-    for idx, (key, value) in enumerate(test_funcs.items()):
-        if verbose:
-            start_type = time()
-        return_table.loc[key] = [
-            test_col_label(
-                col_name, value["func"], value["prop"], limited_output=limited_output
-            )
-            for col_name in table.columns
-        ]
-        if verbose:
-            display_logs_depending_process_time(
-                f'\t- Done with type "{key}" in {round(time() - start_type, 3)}s ({idx+1}/{len(test_funcs)})',
-                time() - start_type
-            )
-    if verbose:
-        display_logs_depending_process_time(f"Done testing labels in {round(time() - start, 3)}s", time() - start)
-    return return_table
+def is_url(file_path: str) -> bool:
+    # could be more sophisticated if needed
+    return file_path.startswith('http')
 
 
-def prepare_output_dict(return_table: pd.DataFrame, limited_output: bool):
-    return_dict_cols = return_table.to_dict("dict")
-    return_dict_cols_intermediary = {}
-    for column_name in return_dict_cols:
-        return_dict_cols_intermediary[column_name] = []
-        for detected_value_type in return_dict_cols[column_name]:
-            if return_dict_cols[column_name][detected_value_type] == 0:
-                continue
-            dict_tmp = {}
-            dict_tmp["format"] = detected_value_type
-            dict_tmp["score"] = return_dict_cols[column_name][detected_value_type]
-            return_dict_cols_intermediary[column_name].append(dict_tmp)
-
-        # Clean dict using priorities
-        formats_detected = {
-            x["format"] for x in return_dict_cols_intermediary[column_name]
-        }
-        formats_to_remove = set()
-        # Deprioritise float and int detection vs others
-        if len(formats_detected - {"float", "int"}) > 0:
-            formats_to_remove = formats_to_remove.union({"float", "int"})
-        if "int" in formats_detected:
-            formats_to_remove.add("float")
-        if "latitude_wgs_fr_metropole" in formats_detected:
-            formats_to_remove.add("latitude_l93")
-            formats_to_remove.add("latitude_wgs")
-        if "longitude_wgs_fr_metropole" in formats_detected:
-            formats_to_remove.add("longitude_l93")
-            formats_to_remove.add("longitude_wgs")
-        if "longitude_wgs" in formats_detected:
-            formats_to_remove.add("longitude_l93")
-        if "code_region" in formats_detected:
-            formats_to_remove.add("code_departement")
-
-        formats_to_keep = formats_detected - formats_to_remove
-
-        detections = return_dict_cols_intermediary[column_name]
-        detections = [x for x in detections if x["format"] in formats_to_keep]
-        if not limited_output:
-            return_dict_cols_intermediary[column_name] = detections
-        else:
-            return_dict_cols_intermediary[column_name] = (
-                max(detections, key=lambda x: x["score"])
-                if len(detections) > 0
-                else {"format": "string", "score": 1.0}
-            )
-
-    return return_dict_cols_intermediary
+def prevent_nan(value: float) -> Optional[float]:
+    if math.isnan(value):
+        return None
+    return value
 
 
 def full_word_strictly_inside_string(word: str, string: str):
@@ -221,47 +39,3 @@ def full_word_strictly_inside_string(word: str, string: str):
         or (string.startswith(word + " "))
         or (string.endswith(" " + word))
     )
-
-
-def cast(value: str, _type: str) -> Optional[Union[str, float, bool, date, datetime]]:
-    if not isinstance(value, str) or not value:
-        # None is the current default value in hydra, should we keep this?
-        return None
-    if _type == "float":
-        return float_casting(value)
-    if _type == "bool":
-        return bool_casting(value)
-    if _type == "json":
-        # in hydra json are given to postgres as strings, conversion is done by postgres
-        return json.loads(value)
-    if _type == "date":
-        _date = date_casting(value)
-        return _date.date() if _date else None
-    if _type == "datetime":
-        return date_casting(value)
-    raise ValueError(f"Unknown type `{_type}`")
-
-
-def cast_df(df: pd.DataFrame, columns: dict, cast_json: bool = True, verbose: bool = False) -> pd.DataFrame:
-    if verbose:
-        start = time()
-    output_df = pd.DataFrame()
-    for col_name, detection in columns.items():
-        if detection["python_type"] == "string" or (detection["python_type"] == "json" and not cast_json):
-            # no change if detected type is string
-            output_df[col_name] = df[col_name].copy()
-        elif detection["python_type"] == "int":
-            # to allow having ints and NaN in the same column
-            output_df[col_name] = df[col_name].copy().astype(pd.Int64Dtype())
-        else:
-            output_df[col_name] = df[col_name].apply(
-                lambda col: cast(col, _type=detection["python_type"])
-            )
-        # to save RAM
-        del df[col_name]
-    if verbose:
-        display_logs_depending_process_time(
-            f'Casting columns completed in {round(time() - start, 3)}s',
-            time() - start,
-        )
-    return output_df

{csv_detective-0.7.5.dev1180.data → csv_detective-0.7.5.dev1209.data}/data/share/csv_detective/CHANGELOG.md

@@ -9,6 +9,9 @@
 - Raise an error if the encoding could not be guessed [#106](https://github.com/datagouv/csv-detective/pull/106)
 - Allow to only specify tests to skip ("all but...") [#108](https://github.com/datagouv/csv-detective/pull/108)
 - Fix bool casting [#109](https://github.com/datagouv/csv-detective/pull/109)
+- Handle csv.gz files [#110](https://github.com/datagouv/csv-detective/pull/110)
+- Refactor file tests [#110](https://github.com/datagouv/csv-detective/pull/110)
+- Restructure repo (breaking changes) [#111](https://github.com/datagouv/csv-detective/pull/111)
 
 ## 0.7.4 (2024-11-15)
 

{csv_detective-0.7.5.dev1180.dist-info → csv_detective-0.7.5.dev1209.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: csv_detective
-Version: 0.7.5.dev1180
+Version: 0.7.5.dev1209
 Summary: Detect CSV column content
 Home-page: https://github.com/etalab/csv_detective
 Author: Etalab
@@ -37,5 +37,6 @@ Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
+Dynamic: license-file
 Dynamic: requires-dist
 Dynamic: summary

{csv_detective-0.7.5.dev1180.dist-info → csv_detective-0.7.5.dev1209.dist-info}/RECORD

@@ -1,16 +1,12 @@
-csv_detective/__init__.py,sha256=Au4bNJ_Gi6P6o0uO4R56nYdshG7M6-7Rg_xX4whLmLI,143
+csv_detective/__init__.py,sha256=GCHgu0BhH5ACV7cf-1gDr9nRyvSoeQ1vRw9SjEHeMT4,143
 csv_detective/cli.py,sha256=Ua7SE1wMH2uFUsTmfumh4nJk7O06okpMd2gvjUDO1II,1048
-csv_detective/create_example.py,sha256=358e7Q7RWMrY_eEo3pUteJWmg2smFb5edJ_AzcQPrqA,8646
-csv_detective/detection.py,sha256=zrP8qvLDvhVXTHi7Ty8G_ga4zfZPjBhuyApqFQkPq2Y,22373
-csv_detective/explore_csv.py,sha256=BY1_X7OH2Lod08DTBwWaGvguc2OhpwOko4nlI8rf0HM,17470
-csv_detective/process_text.py,sha256=rsfk66BCmdpsCOd0kDJ8tmqMsEWd-OeBkEisWc4Ej9k,1246
+csv_detective/explore_csv.py,sha256=aJ2pG7lK4sgY9Pv31zEzFVGByxkfw4wwgrQqfgUtBOo,14903
 csv_detective/s3_utils.py,sha256=1cIVdQUYY2ovErbMwp72Gqtqx2bkB8nfVhn-QaOFTT0,1451
-csv_detective/schema_generation.py,sha256=D1Cq4QRajsKtY8EJSwbRTIB-T_Cb2ZpcmYtCrJ6DvJQ,13135
-csv_detective/utils.py,sha256=yO9INaLh-QX-FFL2A153AlMqftE04wb0hpN6HJvsKGg,10581
+csv_detective/utils.py,sha256=KAYfSJXnPuAXnSc38Jm57oQ_JP_0kUkmI1OV6gN5_ys,1116
 csv_detective/detect_fields/__init__.py,sha256=NVfE3BQVExgXb-BPbhDvlkM5-0naEVLpZ4aM_OGHYfE,931
 csv_detective/detect_fields/FR/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 csv_detective/detect_fields/FR/geo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_fields/FR/geo/adresse/__init__.py,sha256=e5JqMNOPxx0Ivju3zAHCGMopZroCpR4vr3DJKlQhMz4,1675
+csv_detective/detect_fields/FR/geo/adresse/__init__.py,sha256=NqV8ULf9gY9iFnA1deKR-1Yobr96WwCsn5JfbP_MjiY,1675
 csv_detective/detect_fields/FR/geo/code_commune_insee/__init__.py,sha256=tfHdqUnCQ0cv-fBo3Cy--8UNXzgjld4kseI5eQ_sR4E,187
 csv_detective/detect_fields/FR/geo/code_departement/__init__.py,sha256=unr-Y4zquKSM5PVUiQGnOm-zQvaN8qd3v_XHf0W2VH8,378
 csv_detective/detect_fields/FR/geo/code_fantoir/__init__.py,sha256=27bCkZP5w7tpsKUdOIXuiAG90DTdw066CWg3G5HtsKE,160
@@ -26,16 +22,16 @@ csv_detective/detect_fields/FR/geo/longitude_wgs_fr_metropole/__init__.py,sha256
 csv_detective/detect_fields/FR/geo/pays/__init__.py,sha256=2q5T4SmCK6ZFF1mrv7d-q9tOIQKBcROI24y_UYIuvz0,383
 csv_detective/detect_fields/FR/geo/region/__init__.py,sha256=JbFKDd4jAnd9yb7YqP36MoLdO1JFPm1cg60fGXt6ZvI,1074
 csv_detective/detect_fields/FR/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_fields/FR/other/code_csp_insee/__init__.py,sha256=X0NT6YbBg9PrxIcBwzUCQuBiv_QdDdqb3CJnrlent28,566
+csv_detective/detect_fields/FR/other/code_csp_insee/__init__.py,sha256=SRWJvg3Ikyjmop9iL14igTjxNGpO-QB3fpADI_bLYEY,566
 csv_detective/detect_fields/FR/other/code_csp_insee/code_csp_insee.txt,sha256=rbcjtMP6qTZ7BTU6ZegkiXKCruqY_m9Ep6ZgRabFS_E,2486
 csv_detective/detect_fields/FR/other/code_rna/__init__.py,sha256=Z0RjMBt1--ZL7Jd1RsHAQCCbTAQk_BnlnTq8VF1o_VA,146
 csv_detective/detect_fields/FR/other/code_waldec/__init__.py,sha256=g9n5sOjRlk4I9YFZjdaTYrXf8ftXRDunGZOUpYhN4fA,295
-csv_detective/detect_fields/FR/other/csp_insee/__init__.py,sha256=XacU_3rwXqtdbw_ULTSnu0OOtx0w_rKlviCrLmNdHjc,496
+csv_detective/detect_fields/FR/other/csp_insee/__init__.py,sha256=lvcaVKgOPrCaZb-Y1-wYCbLYB_CQjCJFNAzfWDwtTVE,496
 csv_detective/detect_fields/FR/other/csp_insee/csp_insee.txt,sha256=kgKaKc-5PHu5U4--ugLjpFyMNtTU9CGdZ9ANU3YAsM4,32879
 csv_detective/detect_fields/FR/other/date_fr/__init__.py,sha256=kMV52djlG0y4o0ELEZuvTv_FvooYOgTnV1aWhycFJDc,284
-csv_detective/detect_fields/FR/other/insee_ape700/__init__.py,sha256=4v3CiKogDt-bjSn3AvdnYp-5nAFrs3r3JGGSKC6z_Ag,519
+csv_detective/detect_fields/FR/other/insee_ape700/__init__.py,sha256=g8pOqJPKVpQiMd78zgrjXJWYeWkYhu8r3D4IQX519HQ,519
 csv_detective/detect_fields/FR/other/insee_ape700/insee_ape700.txt,sha256=nKgslakENwgE7sPkVNHqR23iXuxF02p9-v5MC2_ntx8,4398
-csv_detective/detect_fields/FR/other/sexe/__init__.py,sha256=hrgZ9Kd_c-cwMmD4w1D5NX10i5f-FzPFbxF4eajYhTU,269
+csv_detective/detect_fields/FR/other/sexe/__init__.py,sha256=iYkLe3MM51GWyBX_4BTq5PWDX_EeYRbEHWKMr8oE1MQ,269
 csv_detective/detect_fields/FR/other/siren/__init__.py,sha256=ohSwUL2rXqTXPG5WDAh2SP-lp1SzFCYgo4IhJ-PXmdk,442
 csv_detective/detect_fields/FR/other/siret/__init__.py,sha256=ThEeT6rXmS0EvHW8y4A_74bILyErDGxLe9v3elHOFs8,707
 csv_detective/detect_fields/FR/other/tel_fr/__init__.py,sha256=BF47aMTe0rUIx66iurIo7fM9Nrk0YorQ7WmFLnkWonI,343
@@ -65,7 +61,7 @@ csv_detective/detect_fields/other/twitter/__init__.py,sha256=qbwLKsTBRFQ4PyTNVeE
 csv_detective/detect_fields/other/url/__init__.py,sha256=9WaTqCglEsw_lJG_xZsBMdxJXg2yuQ92_fkX6CXWNV0,286
 csv_detective/detect_fields/other/uuid/__init__.py,sha256=3-z0fDax29SJc57zPjNGR6DPICJu6gfuNGC5L3jh4d0,223
 csv_detective/detect_fields/temp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_fields/temp/date/__init__.py,sha256=aFP1feFWFhCpR6Q9s_4BBwWxFtwFiMXY1iduSeQIjdA,943
+csv_detective/detect_fields/temp/date/__init__.py,sha256=1a_Ra9fmT4wgGMrcknXP7eN7A2QiaMF0Yjy0-BMihtA,987
 csv_detective/detect_fields/temp/datetime/__init__.py,sha256=Ykwhk2ospjY9P0KOG0AitgqN0sld6UmhOlbMz_XGQzQ,597
 csv_detective/detect_fields/temp/datetime_iso/__init__.py,sha256=DOfli-A7gPlZmiV2J6Ka5_yDUCaOgxis29LET_tfhA4,444
 csv_detective/detect_fields/temp/datetime_rfc822/__init__.py,sha256=JtUzg3BXYd-XJMLGxQ0P1OAJGOQ7DlYMD4fCU9yndg0,511
@@ -73,72 +69,90 @@ csv_detective/detect_fields/temp/year/__init__.py,sha256=RjsiIHoplnI4Odi5587TzRh
 csv_detective/detect_labels/__init__.py,sha256=BJjWlwTnnDe9nomABDUreu9EMu6IFG3T47d7YCJZbRc,878
 csv_detective/detect_labels/FR/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 csv_detective/detect_labels/FR/geo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/FR/geo/adresse/__init__.py,sha256=r14SVoVJiaabyr6lTahI_Qsk0EH3F8UVSi6TRnDQS7o,1063
-csv_detective/detect_labels/FR/geo/code_commune_insee/__init__.py,sha256=qJKvP6g98ceSxaFtd37-bI-9uFhQvdwFSh1n3MrzrOo,1096
-csv_detective/detect_labels/FR/geo/code_departement/__init__.py,sha256=FtPwHudArmsgkjCT_IM-I4_wALOsKjiK0-TEsYe9tw4,1025
-csv_detective/detect_labels/FR/geo/code_fantoir/__init__.py,sha256=irrBwY_TXAGRhOAcH1Xqi9D7P5Ajk2854ee1qXwuTnA,949
-csv_detective/detect_labels/FR/geo/code_postal/__init__.py,sha256=L74MwxadiT_MVrEEWUlMbhUsE_kk7xz_E2BHrZMUxMs,1070
-csv_detective/detect_labels/FR/geo/code_region/__init__.py,sha256=Di9j-AKCogKxavnPgGjA_P8hy8g6JyJ0GBOO0k4l-qY,1012
-csv_detective/detect_labels/FR/geo/commune/__init__.py,sha256=8Jhx4neUt5iyyK_b1D4WWsdxi3mpz7cNZQ28fFF4xaE,948
-csv_detective/detect_labels/FR/geo/departement/__init__.py,sha256=N8MYMhqhspoLAUgD25pIrsqDKRuwTGnXXm8Chr8wih8,1229
-csv_detective/detect_labels/FR/geo/insee_canton/__init__.py,sha256=8Tcqzjn-dGGjpxzo-2TqmEYpyfEhcqa1XNcQgMnqq88,957
-csv_detective/detect_labels/FR/geo/latitude_l93/__init__.py,sha256=nUT7SL4sKP_q9LTbiMBaCzJ029yBMP_phAD_CiOVHfc,1386
-csv_detective/detect_labels/FR/geo/latitude_wgs_fr_metropole/__init__.py,sha256=DCyN6-k1FH1kfTy4tFZWIH6lyaKeT-vgWnDh8TB7JhU,1381
-csv_detective/detect_labels/FR/geo/longitude_l93/__init__.py,sha256=Lcqc8Agjxy2dPulu65NRel4uxRLPcQrAGrLsBTYT8EQ,1139
-csv_detective/detect_labels/FR/geo/longitude_wgs_fr_metropole/__init__.py,sha256=xd_W-L9pkKpsMT1IZ0fVMdty1dmT75uS8gmekb_InAw,1144
-csv_detective/detect_labels/FR/geo/pays/__init__.py,sha256=HJ3hNV3xeAN46YP6c-tqQgHMNvltm-tgApfofR5FraE,1169
-csv_detective/detect_labels/FR/geo/region/__init__.py,sha256=ZPw8LXIuV8OvFVY_DA3MkvpAFzB6Rs749Ppr0Wc4lao,1164
+csv_detective/detect_labels/FR/geo/adresse/__init__.py,sha256=e5ROxhrXNCefLwL5lXTWHO0PEWwLHfqmowm7XoeqZ2I,1063
+csv_detective/detect_labels/FR/geo/code_commune_insee/__init__.py,sha256=D_9QFvAeX5Nwp4qtQ0NEpKR0jpRlDx-rNBSrlYrw4nw,1096
+csv_detective/detect_labels/FR/geo/code_departement/__init__.py,sha256=rpzxUVsZyazVVguOorLadiJv_Vz1n04ijm0RbVmRDts,1025
+csv_detective/detect_labels/FR/geo/code_fantoir/__init__.py,sha256=VUqv3G-JO-9CJU4-EX5DXs4O22Lqm75vuOy9MngoojA,949
+csv_detective/detect_labels/FR/geo/code_postal/__init__.py,sha256=USIYj7PiULI_WCfDxpzRCW9tv8-FNYKWopsVZ3H79mE,1070
+csv_detective/detect_labels/FR/geo/code_region/__init__.py,sha256=f9WroGVfB5jUzd_Rjs4XocZT2Ma-xZd2On9StUHy3F4,1012
+csv_detective/detect_labels/FR/geo/commune/__init__.py,sha256=iYD0UPhRVKYFv8DAEfe_RoQlE47igZ_MacsHxVLyYcM,948
+csv_detective/detect_labels/FR/geo/departement/__init__.py,sha256=fqNziX5ID6mVE5nVNviOsncVqkYyVvj7J_8hxN7_D1w,1229
+csv_detective/detect_labels/FR/geo/insee_canton/__init__.py,sha256=EAcQ2FqTKQdxhSYr5VCuEpjc7BdGwTdMkLL_VL6ay7Y,957
+csv_detective/detect_labels/FR/geo/latitude_l93/__init__.py,sha256=X3vGdh_DHzWZXuV2-L9QhuWTLjHyaPZyS__s9Y5yiNg,1386
+csv_detective/detect_labels/FR/geo/latitude_wgs_fr_metropole/__init__.py,sha256=cRYxeGnBkuxKwrDXpeoRhiCf6xkb533-_bNjk9MB818,1381
+csv_detective/detect_labels/FR/geo/longitude_l93/__init__.py,sha256=Pf00tBADr7HvJLeW_YqY3QU1EBVJDi365woheAzsNKY,1139
+csv_detective/detect_labels/FR/geo/longitude_wgs_fr_metropole/__init__.py,sha256=LfvgcrjVsXmxT6xC3X8eQIiQ_STvPRwjUbUQ4TyfJE0,1144
+csv_detective/detect_labels/FR/geo/pays/__init__.py,sha256=RsI_QXMJOZ5PpKcoKWy7AmUHFjehHXcUezquZyt1eq4,1169
+csv_detective/detect_labels/FR/geo/region/__init__.py,sha256=h9pE3xu2-PFw1jmDenkoKWmFkYmpK9-UgCboPlL7Aeg,1164
 csv_detective/detect_labels/FR/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/FR/other/code_csp_insee/__init__.py,sha256=rk5S6UGL0vND2X2ty1HJJH3qswUbaV6ZJHHKAywRa6o,939
-csv_detective/detect_labels/FR/other/code_rna/__init__.py,sha256=MBF9qZIGbX1dP3DJBI71pbqrGcgOR1xXAbGdiHX0pc4,1024
-csv_detective/detect_labels/FR/other/code_waldec/__init__.py,sha256=RDU8jDZgutfxnJl5lQkbqymJmGeeGXpR2i4CuGfqU10,934
-csv_detective/detect_labels/FR/other/csp_insee/__init__.py,sha256=-GoB9i83O3_rg81Ry3ZtLOdMhlrMPZ34he4hn9U6qDc,1043
-csv_detective/detect_labels/FR/other/date_fr/__init__.py,sha256=7eV737iM1X9MTHureWiCpnxAUJ2_YjI14Vs41MGEX2Q,975
-csv_detective/detect_labels/FR/other/insee_ape700/__init__.py,sha256=6UDx_6JRG__aSXTKKPq-2oBJR7ZiWg0HhSLDl4pETm4,1124
-csv_detective/detect_labels/FR/other/sexe/__init__.py,sha256=87BcCHmofOMqfHfHzmwZzIplcBMAm1AUMxVNvigigTQ,956
-csv_detective/detect_labels/FR/other/siren/__init__.py,sha256=oWkOquzLLbDwBlAs_hoic_UQu7LFOmFZ76570vwRgdc,1103
-csv_detective/detect_labels/FR/other/siret/__init__.py,sha256=Xx-oajnzxEe6pEAYafsnZo7S-mLfnB0pP3z5gv3kJy0,1040
-csv_detective/detect_labels/FR/other/tel_fr/__init__.py,sha256=WWglp7xmb_Wz8bxrYYmB46cRyCJKNNqguubziMktZZI,1143
-csv_detective/detect_labels/FR/other/uai/__init__.py,sha256=sVcw6fwQi9ocIEmLEJRi9m4WvTLg_ORwaW0KaJqeMB8,1316
+csv_detective/detect_labels/FR/other/code_csp_insee/__init__.py,sha256=lcLdEdNo4rhLvqzP3C0rmU_1PaQvTdpviXt9xGSaGFc,939
+csv_detective/detect_labels/FR/other/code_rna/__init__.py,sha256=DJykTRguggOlsIuyjYezJ99c8MGCSwwwCLcoQjfN40o,1024
+csv_detective/detect_labels/FR/other/code_waldec/__init__.py,sha256=idLo99rELzs1uc4mOcby9RLZLhhpsOp5AoTudT2jPwM,934
+csv_detective/detect_labels/FR/other/csp_insee/__init__.py,sha256=J5G8pldzBdXRaopYNzGDztRFIsI_7rdaAPQ_kSuz5PU,1043
+csv_detective/detect_labels/FR/other/date_fr/__init__.py,sha256=9EXCmzKSa5PSWrPbVeLscbJCaiwQEXX-1rCr79U8XLA,975
+csv_detective/detect_labels/FR/other/insee_ape700/__init__.py,sha256=9bq2171SrmDIHx4A0cAeSHfWyQl40e-dIR9_ur4cEHQ,1124
+csv_detective/detect_labels/FR/other/sexe/__init__.py,sha256=AEKBGWEKxDoT8k9BF-v9vl1SHc4DffiiFyhip-6tC78,956
+csv_detective/detect_labels/FR/other/siren/__init__.py,sha256=9w2VCs8kq-XVRmxxwqZYIynfCPwbFbl-pBPqXtnXx8Y,1103
+csv_detective/detect_labels/FR/other/siret/__init__.py,sha256=Yqrp7NDEN0WRA_oktMb0wWoLQ99rzIvNvJ8jVhBCRD8,1040
+csv_detective/detect_labels/FR/other/tel_fr/__init__.py,sha256=gdzclIAjhr_k-a04l_FDz9kQywBfSA6vqa0UQxdaqNw,1143
+csv_detective/detect_labels/FR/other/uai/__init__.py,sha256=mB0hC2JUKGnhGl6MUDFzSM_-t-Tvt3Vm21Gr_JXkL3k,1316
 csv_detective/detect_labels/FR/temp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/FR/temp/jour_de_la_semaine/__init__.py,sha256=a3fKjduxRIMNu7TF124pG--Mb21PIqZYnQwYU4APLBw,1074
-csv_detective/detect_labels/FR/temp/mois_de_annee/__init__.py,sha256=taNWDz1_0KE4cOS4SeJcC8igMSA2LBbv8TvbCg50-TY,934
+csv_detective/detect_labels/FR/temp/jour_de_la_semaine/__init__.py,sha256=FHXmOIjH4e5n_mahtScgOVYUAi_M4PeHAnsuIm5LxCA,1074
+csv_detective/detect_labels/FR/temp/mois_de_annee/__init__.py,sha256=hX0FPAia4x28GD398WvpeaBQ4_3F5G3xAhySmZBdi5w,934
 csv_detective/detect_labels/geo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/geo/iso_country_code_alpha2/__init__.py,sha256=ev8w1hySEoNiMcU1IhJy72IB5OliCvoUy-ytKWPG3oI,1065
-csv_detective/detect_labels/geo/iso_country_code_alpha3/__init__.py,sha256=ev8w1hySEoNiMcU1IhJy72IB5OliCvoUy-ytKWPG3oI,1065
-csv_detective/detect_labels/geo/iso_country_code_numeric/__init__.py,sha256=ev8w1hySEoNiMcU1IhJy72IB5OliCvoUy-ytKWPG3oI,1065
-csv_detective/detect_labels/geo/json_geojson/__init__.py,sha256=p6mXMb1GMkrs27WmoqRqPE3wCbs3iPL4FWfcc280bGA,1072
-csv_detective/detect_labels/geo/latitude_wgs/__init__.py,sha256=DCyN6-k1FH1kfTy4tFZWIH6lyaKeT-vgWnDh8TB7JhU,1381
-csv_detective/detect_labels/geo/latlon_wgs/__init__.py,sha256=xfzeQ1KXmEZAkpVQT_qAYsC4RnXKl11dTB9PoFExGgQ,1705
-csv_detective/detect_labels/geo/longitude_wgs/__init__.py,sha256=knv3HnIerZ6oUPrzGkW2GJjsiTnCklqZ9_koNJCG91I,1145
+csv_detective/detect_labels/geo/iso_country_code_alpha2/__init__.py,sha256=xKio-qy6EJbAowTiCo7-7fzMlD7s6z4O6_qJPVmlIDE,1065
+csv_detective/detect_labels/geo/iso_country_code_alpha3/__init__.py,sha256=xKio-qy6EJbAowTiCo7-7fzMlD7s6z4O6_qJPVmlIDE,1065
+csv_detective/detect_labels/geo/iso_country_code_numeric/__init__.py,sha256=xKio-qy6EJbAowTiCo7-7fzMlD7s6z4O6_qJPVmlIDE,1065
+csv_detective/detect_labels/geo/json_geojson/__init__.py,sha256=0sYS6bF_xmmhqsJ0Wrx7GC3qBAYjK7uhVud_ZbIQHHQ,1072
+csv_detective/detect_labels/geo/latitude_wgs/__init__.py,sha256=cRYxeGnBkuxKwrDXpeoRhiCf6xkb533-_bNjk9MB818,1381
+csv_detective/detect_labels/geo/latlon_wgs/__init__.py,sha256=SwR1NU0vpk8YdHTIk1wk9zQpNoUsoABq-K8GfRMY0fw,1705
+csv_detective/detect_labels/geo/longitude_wgs/__init__.py,sha256=z4rOrkCypI5JodgX9alTrV03IpetgAW4BGJuNvFlU4s,1145
 csv_detective/detect_labels/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/other/booleen/__init__.py,sha256=ahxzBUcJYc5f1J8aAeYDhtSc-URJHS6ruGTAbZXaoG8,987
-csv_detective/detect_labels/other/email/__init__.py,sha256=2pf0e8o3L57damyi4BLrqA9Opw0trZl2wWDHY88s41E,1148
-csv_detective/detect_labels/other/float/__init__.py,sha256=9JC0-B-aVqlLe3FeN8uH5HZjIc2V6hZ7JFStkSLsHW0,926
-csv_detective/detect_labels/other/int/__init__.py,sha256=i9xN8TYBy4C5b1vYO1l3Rkvn4uq_tft8Rip_ErSUIt8,933
+csv_detective/detect_labels/other/booleen/__init__.py,sha256=uvQ7yDVAlEO8AY44OMblh_ZrxPTOmdvFtbcQEanpWSo,987
+csv_detective/detect_labels/other/email/__init__.py,sha256=VRUYZXGn-hRqE2sY0JY-Oh_wtT568orDTBxBGYsgqxE,1148
+csv_detective/detect_labels/other/float/__init__.py,sha256=jIr1r9FFy8NWvi5fOuIhj52bc7cZmM3OeTo-c6TUWII,926
+csv_detective/detect_labels/other/int/__init__.py,sha256=G1GAlKNaOZH_l39Zpw85xkl7JcdnY5PlEEroyU78hlY,933
 csv_detective/detect_labels/other/money/__init__.py,sha256=kBEGuUy6kYkOI3vC_a7waBciG2ipyV9bhC330U8WaoI,279
 csv_detective/detect_labels/other/money/check_col_name.py,sha256=zgp5eUnf3XRQuxgdEGfxPfUnniO8Pzw19uK0ICr2pf8,414
-csv_detective/detect_labels/other/mongo_object_id/__init__.py,sha256=Y-inIGmeH3lZcN9kR6icE3QypS54qJWv8aE4GQUudpc,927
-csv_detective/detect_labels/other/twitter/__init__.py,sha256=D8G4vGsFL9a99OJz-03wp4HbZSvT-y1IxyRJiSsqxFc,959
-csv_detective/detect_labels/other/url/__init__.py,sha256=vqUQvn5o6JZU8iRsSG3AYqggjlhzagozVYWwpuSReV8,1202
-csv_detective/detect_labels/other/uuid/__init__.py,sha256=OdMUxqvqMdGaY5nph7CbIF_Q0LSxljxE72kCMT4m-Zk,931
+csv_detective/detect_labels/other/mongo_object_id/__init__.py,sha256=3TW59y4vo4Pkx_fQrmEs1-gZbdJeNiK7ip25cpR829U,927
+csv_detective/detect_labels/other/twitter/__init__.py,sha256=x3b522ov_g-kmcq4k4eoZ8FQqrXdnlRJJit5UbnzIrQ,959
+csv_detective/detect_labels/other/url/__init__.py,sha256=wVQsWQzOuBY-cD7wn_PXcWLVEkknBA2lBCu8SRWsQG4,1202
+csv_detective/detect_labels/other/uuid/__init__.py,sha256=ySxqFvtGHguoiOyD5A1YRFY3SuubkgBAEY_Ud5kZVPM,931
 csv_detective/detect_labels/temp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/temp/date/__init__.py,sha256=-R7VqlryozelSn4wH_7w9x6ks77DP1kw2XMBYSLrzXE,1322
-csv_detective/detect_labels/temp/datetime_iso/__init__.py,sha256=Ih9l56nBcdmGLyWDavVUWuUUuVZBz9QUDE1hHzADvVg,1157
-csv_detective/detect_labels/temp/datetime_rfc822/__init__.py,sha256=DQ_h4uDW1e6qu2rATEhgGKw6O-vVi7HbDhbEDDCT9uY,1175
-csv_detective/detect_labels/temp/year/__init__.py,sha256=zPF_mvhzhXMAlHPAskS8mhuxjLj2AlKpV4ss8Q4tDms,1150
-csv_detective-0.7.5.dev1180.data/data/share/csv_detective/CHANGELOG.md,sha256=j5OyYgmRMfYqQoEzY6In6OdivOZR3kpv9AlXkda5vpA,7366
-csv_detective-0.7.5.dev1180.data/data/share/csv_detective/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
-csv_detective-0.7.5.dev1180.data/data/share/csv_detective/README.md,sha256=Qr8xRXc-dxQ-tdXCpCTCKp1Uliqq84r0UOlPRNuGCpI,9506
+csv_detective/detect_labels/temp/date/__init__.py,sha256=CRv-S0figO6MOPdE0Lv5hWdjtIr6EmWzwlcjn5ofIxo,1322
+csv_detective/detect_labels/temp/datetime_iso/__init__.py,sha256=0lFdN5Z43m6Qm-wBqcyM_mceUmI4s3vqgLCM-Jlgoxw,1157
+csv_detective/detect_labels/temp/datetime_rfc822/__init__.py,sha256=4N0EGJA_2vXC1iFptvzpU6IN7AIJH5MFUrRY2p7Cjfs,1175
+csv_detective/detect_labels/temp/year/__init__.py,sha256=3U9j8Hux432KdGtIyArq_-vScn-5eYFwpn976WM9N4M,1150
+csv_detective/detection/columns.py,sha256=vfE-DKESA6J9Rfsl-a8tjgZfE21VmzArO5TrbzL0KmE,2905
+csv_detective/detection/encoding.py,sha256=tpjJEMNM_2TcLXDzn1lNQPnSRnsWYjs83tQ8jNwTj4E,973
+csv_detective/detection/engine.py,sha256=HiIrU-l9EO5Fbc2Vh8W_Uy5-dpKcQQzlxCqMuWc09LY,1530
+csv_detective/detection/headers.py,sha256=wrVII2RQpsVmHhrO1DHf3dmiu8kbtOjBlskf41cnQmc,1172
+csv_detective/detection/rows.py,sha256=3qvsbsBcMxiqqfSYYkOgsRpX777rk22tnRHDwUA97kU,742
+csv_detective/detection/separator.py,sha256=XjeDBqhiBxVfkCPJKem9BAgJqs_hOgQltc_pxrH_-Tg,1547
+csv_detective/detection/variables.py,sha256=3qEMtjZ_zyIFXvTnFgK7ZMDx8C12uQXKfFjEj2moyJc,3558
+csv_detective/output/dataframe.py,sha256=89iQRE59cHQyQQEsujQVIKP2YAUYpPklWkdDOqZE-wE,2183
+csv_detective/output/example.py,sha256=i8PkdXxidF7qR_9aK8vh12JpZdJQryhBgyrMS8iy5rk,8642
+csv_detective/output/profile.py,sha256=B8YU541T_YPDezJGh4dkHckOShiwHSrZd9GS8jbmz7A,2919
+csv_detective/output/schema.py,sha256=ZDBWDOD8IYp7rcB0_n8l9JXGIhOQ6bTZHFWfTmnNNEQ,13480
+csv_detective/output/utils.py,sha256=HbmvCCCmFo7NJxhD_UsJIveuw-rrfhrvYckv1CJn_10,2301
+csv_detective/parsing/columns.py,sha256=Oj0Ddp2fPZeL70GDWdF7GY2RmhiVdz0IEvoBJFt-wao,5701
+csv_detective/parsing/compression.py,sha256=Fnw5tj-PpBNI8NYsWj5gD-DUoWcVLnsVpiKm9MpxmIA,350
+csv_detective/parsing/csv.py,sha256=11mibDnJhIjykXLGZvA5ZEU5U7KgxIrbyO6BNv6jlro,1626
+csv_detective/parsing/excel.py,sha256=AslE2S1e67o8yTIAIhp-lAnJ6-XqeBBRz1-VMFqhZBM,7055
+csv_detective/parsing/load.py,sha256=SpP0pfxswOAPPpwbZfoP1blh0EKV5VMs0TpTgQJKzjs,3621
+csv_detective/parsing/text.py,sha256=rsfk66BCmdpsCOd0kDJ8tmqMsEWd-OeBkEisWc4Ej9k,1246
+csv_detective-0.7.5.dev1209.data/data/share/csv_detective/CHANGELOG.md,sha256=povo1ufNJvsxJLkzdjYLgkTy9E-MNFWTg6elXe2nyqU,7625
+csv_detective-0.7.5.dev1209.data/data/share/csv_detective/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
+csv_detective-0.7.5.dev1209.data/data/share/csv_detective/README.md,sha256=Qr8xRXc-dxQ-tdXCpCTCKp1Uliqq84r0UOlPRNuGCpI,9506
+csv_detective-0.7.5.dev1209.dist-info/licenses/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
 tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/test_example.py,sha256=0NfChooJQlFxTo2nY5FOQIcsK4zzWA_SBmt2LwVQovY,2014
-tests/test_fields.py,sha256=_96htvTzvM7u-W57RpOBbsacWirIm4R36PP7JhPEaYQ,11123
-tests/test_file.py,sha256=HO-Zqv0ZDFy3d0ZrpjWQPXBrwgUmzesseoEofy8G2UU,7529
+tests/test_fields.py,sha256=fcgycaFxacOcN0WdwuUvxef_ejd6tRHNpkD5pxMjMXE,11141
+tests/test_file.py,sha256=EleTssys5fCP4N0W1eTZN35uijzoF15e3dIcuIlrMsk,7865
 tests/test_labels.py,sha256=6MOKrGznkwU5fjZ_3oiB6Scmb480Eu-9geBJs0UDLds,159
 tests/test_structure.py,sha256=SVsnluVoIIprYw_67I1_gB3cp9m1wlO8C7SpdsLW8cM,1161
-csv_detective-0.7.5.dev1180.dist-info/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
-csv_detective-0.7.5.dev1180.dist-info/METADATA,sha256=MPk6yPPa_Xm0K9edLe_7DfXGCVniEP8cs1tHQqJGzvo,1364
-csv_detective-0.7.5.dev1180.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
-csv_detective-0.7.5.dev1180.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
-csv_detective-0.7.5.dev1180.dist-info/top_level.txt,sha256=M0Nv646VHo-49zWjPkwo2C48UmtfddV8_9mEZeIxy8Q,20
-csv_detective-0.7.5.dev1180.dist-info/RECORD,,
+csv_detective-0.7.5.dev1209.dist-info/METADATA,sha256=LwKAMVqoJjZfnrWAJV_nv_V3oprmbmmaNmX9e4Zvruc,1386
+csv_detective-0.7.5.dev1209.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+csv_detective-0.7.5.dev1209.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
+csv_detective-0.7.5.dev1209.dist-info/top_level.txt,sha256=M0Nv646VHo-49zWjPkwo2C48UmtfddV8_9mEZeIxy8Q,20
+csv_detective-0.7.5.dev1209.dist-info/RECORD,,

{csv_detective-0.7.5.dev1180.dist-info → csv_detective-0.7.5.dev1209.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.2)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

tests/test_fields.py

@@ -1,7 +1,8 @@
-import pandas as pd
+from datetime import date as _date, datetime as _datetime
+
 from numpy import random
+import pandas as pd
 import pytest
-from datetime import date as _date, datetime as _datetime
 
 from csv_detective.detect_fields.FR.geo import (
     adresse,
@@ -43,12 +44,12 @@ from csv_detective.detect_fields.other import (
     float as test_float,
 )
 from csv_detective.detect_fields.temp import date, datetime_iso, datetime_rfc822, year
-from csv_detective.detection import (
+from csv_detective.detection.variables import (
     detect_continuous_variable,
-    detetect_categorical_variable,
+    detect_categorical_variable,
 )
 from csv_detective.explore_csv import return_all_tests
-from csv_detective.utils import cast
+from csv_detective.output.dataframe import cast
 
 
 def test_all_tests_return_bool():
@@ -71,7 +72,7 @@ def test_detetect_categorical_variable():
     }
     df = pd.DataFrame(df_dict, dtype="unicode")
 
-    res, _ = detetect_categorical_variable(df)
+    res, _ = detect_categorical_variable(df)
     assert len(res.values) and all(k in res.values for k in ["cat", "cat2"])