csv-detective 0.9.2.dev1874__py3-none-any.whl → 0.9.2.dev1896__py3-none-any.whl

csv_detective/output/__init__.py

@@ -25,14 +25,7 @@ def generate_output(
     verbose: bool = False,
     sheet_name: Optional[Union[str, int]] = None,
 ) -> Union[dict, tuple[dict, pd.DataFrame]]:
-    if output_profile or output_df:
-        # to create the profile we have to cast columns, so using the dedicated function
-        table = cast_df(
-            df=table,
-            columns=analysis["columns"],
-            cast_json=cast_json,
-            verbose=verbose,
-        )
+    if output_profile:
         analysis["profile"] = create_profile(
             table=table,
             columns=analysis["columns"],
@@ -61,5 +54,10 @@ def generate_output(
         analysis["schema"] = generate_table_schema(analysis, save_file=False, verbose=verbose)
 
     if output_df:
-        return analysis, table
+        return analysis, cast_df(
+            df=table,
+            columns=analysis["columns"],
+            cast_json=cast_json,
+            verbose=verbose,
+        )
     return analysis

csv_detective/output/profile.py

@@ -4,7 +4,8 @@ from time import time
 
 import pandas as pd
 
-from csv_detective.utils import display_logs_depending_process_time, prevent_nan
+from csv_detective.detect_fields.other.float import float_casting
+from csv_detective.utils import cast_prevent_nan, display_logs_depending_process_time
 
 
 def create_profile(
@@ -18,11 +19,6 @@ def create_profile(
     if verbose:
         start = time()
         logging.info("Creating profile")
-    map_python_types = {
-        "string": str,
-        "int": float,
-        "float": float,
-    }
 
     if num_rows > 0:
         raise ValueError("To create profiles num_rows has to be set to -1")
@@ -35,12 +31,19 @@ def create_profile(
     for c in table.columns:
         # for numerical formats we want min, max, mean, std
         if columns[c]["python_type"] in ["float", "int"]:
+            # we locally cast the column to perform the operations, using the same method as in cast_df
+            cast_col = (
+                table[c].astype(pd.Int64Dtype())
+                if columns[c]["python_type"] == "int"
+                else table[c].apply(lambda x: float_casting(x) if isinstance(x, str) else pd.NA)
+            )
             profile[c].update(
-                min=prevent_nan(map_python_types[columns[c]["python_type"]](table[c].min())),
-                max=prevent_nan(map_python_types[columns[c]["python_type"]](table[c].max())),
-                mean=prevent_nan(map_python_types[columns[c]["python_type"]](table[c].mean())),
-                std=prevent_nan(map_python_types[columns[c]["python_type"]](table[c].std())),
+                min=cast_prevent_nan(cast_col.min(), columns[c]["python_type"]),
+                max=cast_prevent_nan(cast_col.max(), columns[c]["python_type"]),
+                mean=cast_prevent_nan(cast_col.mean(), columns[c]["python_type"]),
+                std=cast_prevent_nan(cast_col.std(), columns[c]["python_type"]),
             )
+            del cast_col
         # for all formats we want most frequent values, nb unique values and nb missing values
         tops_bruts = (
             table.loc[table[c].notna(), c]

csv_detective/utils.py

@@ -1,5 +1,5 @@
 import logging
-from typing import Optional
+from typing import Optional, Union
 
 import pandas as pd
 
@@ -31,5 +31,7 @@ def is_url(file_path: str) -> bool:
     return file_path.startswith("http")
 
 
-def prevent_nan(value: float) -> Optional[float]:
-    return None if pd.isna(value) else value
+def cast_prevent_nan(value: float, _type: str) -> Optional[Union[float, int]]:
+    if _type not in {"int", "float"}:
+        raise ValueError(f"Invalid type was passed: {_type}")
+    return None if pd.isna(value) else eval(_type)(value)

{csv_detective-0.9.2.dev1874.dist-info → csv_detective-0.9.2.dev1896.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: csv-detective
-Version: 0.9.2.dev1874
+Version: 0.9.2.dev1896
 Summary: Detect tabular files column content
 Author-email: Etalab <opendatateam@data.gouv.fr>
 License: MIT

{csv_detective-0.9.2.dev1874.dist-info → csv_detective-0.9.2.dev1896.dist-info}/RECORD

@@ -3,7 +3,7 @@ csv_detective/cli.py,sha256=mu5anmBmaDk52_uZGiA4T37wYZCuV43gZAepjs1Cqzc,1389
 csv_detective/explore_csv.py,sha256=sEMza4Z27ac88fGq7tUiK1zlfvuftztHhHVoa0c2EVU,9191
 csv_detective/load_tests.py,sha256=uVKweLq3cf-yB5ZZI-m9tBVs_SWNcOw8sDJa97TOJGo,2266
 csv_detective/s3_utils.py,sha256=z1KTVVkdurMv21o-rZu7_aluMJnSi-d5uxnQbqT2NoI,1407
-csv_detective/utils.py,sha256=u9I1tsyMfVr2eIYiGCD7Iu30d55H3za44-N3cV2nj8M,1013
+csv_detective/utils.py,sha256=xiIO7ZDqkTm9Rnhnq6RaDdnrPIfoG0JV9AsmaOG6plA,1162
 csv_detective/validate.py,sha256=RLHXLrRuynkdcvHUlSEbyglPvdbNYlT1Z4nQI-BdYdA,2898
 csv_detective/detect_fields/__init__.py,sha256=ZZ7u9zsMtCqPC2xxeLp57UTCbqpKFJi6D_LO1ew15BU,1980
 csv_detective/detect_fields/FR/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -137,10 +137,10 @@ csv_detective/detection/headers.py,sha256=y5iR4jWH5fUtAH_Zg0zxWSVG_INCHlXJFMbhPp
 csv_detective/detection/rows.py,sha256=quf3ZTTFPOo09H-faZ9cRKibb1QGHEKHlpivFRx2Va4,742
 csv_detective/detection/separator.py,sha256=XjeDBqhiBxVfkCPJKem9BAgJqs_hOgQltc_pxrH_-Tg,1547
 csv_detective/detection/variables.py,sha256=wfsA_MOk14TPMOY7gkvpTGpo9-USzMnFaAou3MPHqxc,3536
-csv_detective/output/__init__.py,sha256=02F5D5TODMiImyZzjnX-vIkMPkUC0ioIryqdBm6xT-w,2056
+csv_detective/output/__init__.py,sha256=bMsLp-XCVf4sNymIof_kdMdqFIY7GocOas-lPNekfQg,1930
 csv_detective/output/dataframe.py,sha256=pjxvpzIWVUW9_xvT3JjoPnOIVUUHnzL7kZo1xQdMDxQ,2139
 csv_detective/output/example.py,sha256=XrnPS_uC0cICn7tgnLWNctpUbnPzl7fIMzNTzJEWGJc,8655
-csv_detective/output/profile.py,sha256=k-t--uVHkrt3MRLnRAthiaF069jGc1jsQnfcOoBchrU,2524
+csv_detective/output/profile.py,sha256=thckCcfy9cES5yYNW6TDGV82gP1OFWJuLhInT1g7JpI,2814
 csv_detective/output/schema.py,sha256=5Duw5qnsJ-LaVC6JgF7p1zZAkehDzsbXA4iTSJUgLNM,13760
 csv_detective/output/utils.py,sha256=tbji3dEH7bDc6gLCeVSVquqU3xaHA1CQOMuaJT4Hub8,3297
 csv_detective/parsing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -150,19 +150,19 @@ csv_detective/parsing/csv.py,sha256=fJkjKvyk7InkNnYKtmivyi48mmcwvrha7gvZ5J4-86A,
 csv_detective/parsing/excel.py,sha256=sKD5PRN1TlzPPOKFnZ3VRb0r1yIjPLlpxVWmZQeLYFk,7027
 csv_detective/parsing/load.py,sha256=C3M8nvgWenOb8aDFi5dpDGCoAw9EBqr4EB63zbz2M14,3699
 csv_detective/parsing/text.py,sha256=uz8wfmNTQnOd_4fjrIZ_5rxmFmgrg343hJh2szB73Hc,1770
-csv_detective-0.9.2.dev1874.dist-info/licenses/LICENSE,sha256=A1dQrzxyxRHRih02KwibWj1khQyF7GeA6SqdOU87Gk4,1088
+csv_detective-0.9.2.dev1896.dist-info/licenses/LICENSE,sha256=A1dQrzxyxRHRih02KwibWj1khQyF7GeA6SqdOU87Gk4,1088
 tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/test_example.py,sha256=uTWswvUzBWEADGXZmMAdZvKhKvIjvT5zWOVVABgCDN4,1987
 tests/test_fields.py,sha256=5901OxKDReGMPQm3ZJ36oDjtJ8H3El5jPxf1YNu5wVg,12542
-tests/test_file.py,sha256=NBLwPCFN2skZHLkckPZ0M0ZvanEdL88KVK1Vi9GhSaU,8925
+tests/test_file.py,sha256=ZL0Jx499RUpmKFvcPQVnAeafSbyc23fqwt93ZrYg9GE,10258
 tests/test_labels.py,sha256=Y0XlOpztCyV65pk7iAS_nMMfdysoBujlBmz10vHul9A,469
 tests/test_structure.py,sha256=GRDYKy0UcdqlN4qglzsRC0puFj5cb-SVvONjvcPvtAA,1400
 tests/test_validation.py,sha256=ie-Xf0vk6-M6GQq-x7kY5yse1EmXfxQkbaV7fR3fvYo,3308
 venv/bin/activate_this.py,sha256=NRy3waFmwW1pOaNUp33wNN0vD1Kzkd-zXX-Sgl4EiVI,1286
 venv/bin/jp.py,sha256=7z7dvRg0M7HzpZG4ssQID7nScjvQx7bcYTxJWDOrS6E,1717
 venv/bin/runxlrd.py,sha256=YlZMuycM_V_hzNt2yt3FyXPuwouMCmMhvj1oZaBeeuw,16092
-csv_detective-0.9.2.dev1874.dist-info/METADATA,sha256=uQd1XKNz46xPglKQ-wEpbAjy0CAXOgPCYR-NCeBckS0,9767
-csv_detective-0.9.2.dev1874.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-csv_detective-0.9.2.dev1874.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
-csv_detective-0.9.2.dev1874.dist-info/top_level.txt,sha256=cYKb4Ok3XgYA7rMDOYtxysjSJp_iUA9lJjynhVzue8g,30
-csv_detective-0.9.2.dev1874.dist-info/RECORD,,
+csv_detective-0.9.2.dev1896.dist-info/METADATA,sha256=2ZrcsJkSf2uY3pxlmwvui5uFbicmYpa8nDnxmkp4-xM,9767
+csv_detective-0.9.2.dev1896.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+csv_detective-0.9.2.dev1896.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
+csv_detective-0.9.2.dev1896.dist-info/top_level.txt,sha256=cYKb4Ok3XgYA7rMDOYtxysjSJp_iUA9lJjynhVzue8g,30
+csv_detective-0.9.2.dev1896.dist-info/RECORD,,

tests/test_file.py

@@ -5,6 +5,7 @@ import pytest
 import responses
 
 from csv_detective import routine
+from csv_detective.output.profile import create_profile
 
 
 @pytest.mark.parametrize(
@@ -97,6 +98,55 @@ def test_profile_with_num_rows():
         )
 
 
+@pytest.mark.parametrize(
+    "params",
+    (
+        (
+            True,
+            {
+                "int_with_nan": {"format": "int", "python_type": "int"},
+                "date": {"format": "date", "python_type": "date"},
+            },
+        ),
+        (
+            False,
+            {
+                "int_with_nan": [{"format": "int", "python_type": "int"}],
+                "date": [{"format": "date", "python_type": "date"}],
+            },
+        ),
+    ),
+)
+def test_profile_specific_cases(params):
+    limited_output, columns = params
+    table = pd.DataFrame(
+        {
+            "int_with_nan": ["1", pd.NA, pd.NA],
+            "date": ["1996-01-02", "1996-01-02", "2024-11-12"],
+        }
+    )
+    profile = create_profile(
+        table=table,
+        columns=columns,
+        limited_output=limited_output,
+        num_rows=-1,
+    )
+    assert profile["int_with_nan"] == {
+        "min": 1,
+        "max": 1,
+        "mean": 1,
+        "std": None,
+        "tops": [{"count": 1, "value": "1"}],
+        "nb_distinct": 1,
+        "nb_missing_values": 2,
+    }
+    assert profile["date"] == {
+        "tops": [{"count": 2, "value": "1996-01-02"}, {"count": 1, "value": "2024-11-12"}],
+        "nb_distinct": 2,
+        "nb_missing_values": 0,
+    }
+
+
 def test_exception_different_number_of_columns():
     """
     A ValueError should be raised if the number of columns differs between the first rows