csv-detective 0.8.1.dev1703__py3-none-any.whl → 0.8.1.dev1729__py3-none-any.whl

tests/test_fields.py

@@ -1,8 +1,9 @@
-from datetime import date as _date, datetime as _datetime
+from datetime import date as _date
+from datetime import datetime as _datetime
 
-from numpy import random
 import pandas as pd
 import pytest
+from numpy import random
 
 from csv_detective.detect_fields.FR.geo import (
     adresse,
@@ -23,8 +24,8 @@ from csv_detective.detect_fields.FR.geo import (
 )
 from csv_detective.detect_fields.FR.other import (
     code_csp_insee,
-    code_rna,
     code_import,
+    code_rna,
     code_waldec,
     csp_insee,
     date_fr,
@@ -56,9 +57,13 @@ from csv_detective.detect_fields.other import (
     twitter,
     url,
     uuid,
-    int as test_int,
+)
+from csv_detective.detect_fields.other import (
     float as test_float,
 )
+from csv_detective.detect_fields.other import (
+    int as test_int,
+)
 from csv_detective.detect_fields.temp import (
     date,
     datetime_aware,
@@ -67,8 +72,8 @@ from csv_detective.detect_fields.temp import (
     year,
 )
 from csv_detective.detection.variables import (
-    detect_continuous_variable,
     detect_categorical_variable,
+    detect_continuous_variable,
 )
 from csv_detective.load_tests import return_all_tests
 from csv_detective.output.dataframe import cast
@@ -225,10 +230,7 @@ fields = {
         True: ["13 fevrier 1996"],
         False: ["44 march 2025"],
     },
-    insee_ape700: {
-        True: ["0116Z"],
-        False: ["0116A"]
-    },
+    insee_ape700: {True: ["0116Z"], False: ["0116A"]},
     tel_fr: {
         True: ["0134643467"],
         False: ["6625388263", "01288398"],
@@ -360,7 +362,11 @@ fields = {
     },
     datetime_naive: {
         True: ["2021-06-22 10:20:10", "2030/06/22 00:00:00.0028"],
-        False: ["2021-06-22T30:20:10", "Sun, 06 Nov 1994 08:49:37 GMT", "2021-06-44 10:20:10+02:00"],
+        False: [
+            "2021-06-22T30:20:10",
+            "Sun, 06 Nov 1994 08:49:37 GMT",
+            "2021-06-44 10:20:10+02:00",
+        ],
     },
     datetime_rfc822: {
         True: ["Sun, 06 Nov 1994 08:49:37 GMT"],

tests/test_file.py

@@ -1,7 +1,8 @@
+from unittest.mock import patch
+
 import pandas as pd
 import pytest
 import responses
-from unittest.mock import patch
 
 from csv_detective import routine
 
@@ -70,10 +71,10 @@ def test_profile_output_on_file():
         [
             c in list(output["profile"]["NUMCOM"].keys())
             for c in [
-                    "min",
-                    "max",
-                    "mean",
-                    "std",
+                "min",
+                "max",
+                "mean",
+                "std",
             ]
         ]
     )
@@ -191,7 +192,7 @@ def mocked_responses():
     "params",
     # ideally we'd like to do the same with params_others but pandas.read_excel uses urllib
     # which doesn't support the way we mock the response, TBC
-    params_csv + [("a_test_file.csv", {"separator": ";", "header_row_idx": 2, "total_lines": 404})]
+    params_csv + [("a_test_file.csv", {"separator": ";", "header_row_idx": 2, "total_lines": 404})],
 )
 def test_urls(mocked_responses, params):
     file_name, checks = params
@@ -261,17 +262,17 @@ def test_cast_json(mocked_responses, cast_json):
     cast_json, expected_type = cast_json
     expected_content = 'id,a_simple_dict\n1,{"a": 1}\n2,{"b": 2}\n3,{"c": 3}\n'
     mocked_responses.get(
-        'http://example.com/test.csv',
+        "http://example.com/test.csv",
         body=expected_content,
         status=200,
     )
     analysis, df = routine(
-        file_path='http://example.com/test.csv',
+        file_path="http://example.com/test.csv",
         num_rows=-1,
         output_profile=False,
         save_results=False,
         output_df=True,
         cast_json=cast_json,
     )
-    assert analysis['columns']["a_simple_dict"]["python_type"] == "json"
+    assert analysis["columns"]["a_simple_dict"]["python_type"] == "json"
     assert isinstance(df["a_simple_dict"][0], expected_type)

tests/test_labels.py

@@ -10,13 +10,14 @@ def test_money_labels():
 
 
 @pytest.mark.parametrize(
-    "params", [
+    "params",
+    [
         ("latitude", 1.0),
         ("lat", 1.0),
         ("coord_lat", 0.5),
         ("y", 1.0),
         ("nb_cycles", 0.0),
-    ]
+    ],
 )
 def test_latitude(params):
     header, expected = params

tests/test_structure.py

@@ -1,6 +1,6 @@
 import os
-# flake8: noqa
-from csv_detective import detect_fields, detect_labels
+
+from csv_detective import detect_fields, detect_labels  # noqa
 from csv_detective.load_tests import return_all_tests
 
 
@@ -18,7 +18,8 @@ def tests_conformity():
                 if "__pycache__" not in dirname:
                     subfolders.append(os.path.join(dirpath, dirname))
         final_subfolders = [
-            sf for sf in subfolders
+            sf
+            for sf in subfolders
             if not any(other_sf.startswith(sf) for other_sf in subfolders if sf != other_sf)
         ]
         for f_sf in final_subfolders:

tests/test_validation.py

@@ -30,13 +30,16 @@ def get_nested_value(source_dict: dict, key_chain: list[str]):
         ((False, None, None), {"separator": "|"}),
         ((False, None, None), {"encoding": "unknown"}),
         ((False, None, None), {"header": ["a", "b"]}),
-        ((False, pd.DataFrame, dict), {
-            "columns.NUMCOM": {
-                "python_type": "int",
-                "format": "int",
-                "score": 1.0,
+        (
+            (False, pd.DataFrame, dict),
+            {
+                "columns.NUMCOM": {
+                    "python_type": "int",
+                    "format": "int",
+                    "score": 1.0,
+                },
             },
-        }),
+        ),
     ),
 )
 def test_validation(_params):