csv-detective 0.9.1.dev1847__py3-none-any.whl → 0.9.1.dev1869__py3-none-any.whl

csv_detective/detection/formats.py

@@ -14,6 +14,9 @@ from csv_detective.output.utils import prepare_output_dict
 from csv_detective.parsing.columns import MAX_ROWS_ANALYSIS, test_col, test_label
 from csv_detective.validate import validate
 
+# above this threshold, a column is not considered categorical
+MAX_NUMBER_CATEGORICAL_VALUES = 25
+
 
 def detect_formats(
     table: pd.DataFrame,
@@ -28,14 +31,18 @@ def detect_formats(
     if on_sample:
         if verbose:
             logging.warning(f"File is too long, analysing the {MAX_ROWS_ANALYSIS} first rows")
-        table = table.sample(n=MAX_ROWS_ANALYSIS, random_state=1)
+        table = build_sample(table)
 
     if table.empty:
         res_categorical = []
         # res_continuous = []
     else:
         # Detects columns that are categorical
-        res_categorical, categorical_mask = detect_categorical_variable(table, verbose=verbose)
+        res_categorical, categorical_mask = detect_categorical_variable(
+            table,
+            max_number_categorical_values=MAX_NUMBER_CATEGORICAL_VALUES,
+            verbose=verbose,
+        )
         res_categorical = list(res_categorical)
         # Detect columns that are continuous (we already know the categorical) :
         # we don't need this for now, cuts processing time
@@ -166,3 +173,33 @@ def detect_formats(
             raise ValueError("Could not infer detected formats on the whole file")
 
     return analysis
+
+
+def build_sample(table: pd.DataFrame) -> pd.DataFrame:
+    """
+    building a sample of MAX_ROWS_ANALYSIS rows that contains at least one representative of
+    the min and max values of each column, and one case of NaN if the column contains any.
+    """
+    samples = pd.concat(
+        [
+            # one row with the minimum of the column
+            table.loc[table[col] == table[col].dropna().min()].iloc[[0]]
+            for col in table.columns
+        ]
+        + [
+            # one row with the maximum of the column
+            table.loc[table[col] == table[col].dropna().max()].iloc[[0]]
+            for col in table.columns
+        ]
+        + [
+            # one row with a NaN value if the column has any
+            table.loc[table[col].isna()].iloc[[0]]
+            for col in table.columns
+            if table[col].isna().any()
+        ],
+        ignore_index=True,
+    )
+    return pd.concat(
+        [samples, table.sample(n=MAX_ROWS_ANALYSIS - len(samples), random_state=1)],
+        ignore_index=True,
+    )

csv_detective/output/__init__.py

@@ -25,12 +25,20 @@ def generate_output(
     verbose: bool = False,
     sheet_name: Optional[Union[str, int]] = None,
 ) -> Union[dict, tuple[dict, pd.DataFrame]]:
-    if output_profile:
+    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,
+        )
         analysis["profile"] = create_profile(
             table=table,
-            dict_cols_fields=analysis["columns"],
+            columns=analysis["columns"],
             num_rows=num_rows,
             limited_output=limited_output,
+            cast_json=cast_json,
             verbose=verbose,
         )
 
@@ -45,16 +53,13 @@ def generate_output(
                 output_path += "_sheet-" + str(sheet_name)
             output_path += ".json"
         with open(output_path, "w", encoding="utf8") as fp:
-            json.dump(analysis, fp, indent=4, separators=(",", ": "), ensure_ascii=False)
+            json.dump(
+                analysis, fp, indent=4, separators=(",", ": "), ensure_ascii=False, default=str
+            )
 
     if output_schema:
         analysis["schema"] = generate_table_schema(analysis, save_file=False, verbose=verbose)
 
     if output_df:
-        return analysis, cast_df(
-            df=table,
-            columns=analysis["columns"],
-            cast_json=cast_json,
-            verbose=verbose,
-        )
+        return analysis, table
     return analysis

csv_detective/output/profile.py

@@ -4,15 +4,15 @@ from time import time
 
 import pandas as pd
 
-from csv_detective.detect_fields.other.float import float_casting
 from csv_detective.utils import display_logs_depending_process_time, prevent_nan
 
 
 def create_profile(
     table: pd.DataFrame,
-    dict_cols_fields: dict,
+    columns: dict,
     num_rows: int,
     limited_output: bool = True,
+    cast_json: bool = True,
     verbose: bool = False,
 ) -> dict:
     if verbose:
@@ -26,65 +26,44 @@ def create_profile(
 
     if num_rows > 0:
         raise ValueError("To create profiles num_rows has to be set to -1")
-    safe_table = table.copy()
     if not limited_output:
-        dict_cols_fields = {
+        columns = {
             k: v[0] if v else {"python_type": "string", "format": "string", "score": 1.0}
-            for k, v in dict_cols_fields.items()
+            for k, v in columns.items()
         }
-    dtypes = {k: map_python_types.get(v["python_type"], str) for k, v in dict_cols_fields.items()}
-    for c in safe_table.columns:
-        if dtypes[c] is float:
-            safe_table[c] = safe_table[c].apply(
-                lambda s: float_casting(s) if isinstance(s, str) else s
-            )
     profile = defaultdict(dict)
-    for c in safe_table.columns:
-        if map_python_types.get(dict_cols_fields[c]["python_type"], str) in [
-            float,
-            int,
-        ]:
+    for c in table.columns:
+        # for numerical formats we want min, max, mean, std
+        if columns[c]["python_type"] in ["float", "int"]:
             profile[c].update(
-                min=prevent_nan(
-                    map_python_types.get(dict_cols_fields[c]["python_type"], str)(
-                        safe_table[c].min()
-                    )
-                ),
-                max=prevent_nan(
-                    map_python_types.get(dict_cols_fields[c]["python_type"], str)(
-                        safe_table[c].max()
-                    )
-                ),
-                mean=prevent_nan(
-                    map_python_types.get(dict_cols_fields[c]["python_type"], str)(
-                        safe_table[c].mean()
-                    )
-                ),
-                std=prevent_nan(
-                    map_python_types.get(dict_cols_fields[c]["python_type"], str)(
-                        safe_table[c].std()
-                    )
-                ),
+                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())),
             )
+        # for all formats we want most frequent values, nb unique values and nb missing values
         tops_bruts = (
-            safe_table[safe_table[c].notna()][c]
-            .value_counts(dropna=True)
+            table.loc[table[c].notna(), c]
+            .value_counts()
             .reset_index()
             .iloc[:10]
             .to_dict(orient="records")
         )
-        tops = []
-        for tb in tops_bruts:
-            tops.append(
+        profile[c].update(
+            tops=[
                 {
                     "count": tb["count"],
                     "value": tb[c],
                 }
-            )
-        profile[c].update(
-            tops=tops,
-            nb_distinct=safe_table[c].nunique(),
-            nb_missing_values=len(safe_table[c].loc[safe_table[c].isna()]),
+                for tb in tops_bruts
+            ],
+            nb_distinct=(
+                table[c].nunique()
+                if columns[c]["python_type"] != "json" or not cast_json
+                # a column containing cast json is not serializable
+                else table[c].astype(str).nunique()
+            ),
+            nb_missing_values=len(table[c].loc[table[c].isna()]),
         )
     if verbose:
         display_logs_depending_process_time(

csv_detective/parsing/columns.py

@@ -6,7 +6,7 @@ import pandas as pd
 
 from csv_detective.utils import display_logs_depending_process_time
 
-MAX_ROWS_ANALYSIS = int(1e5)
+MAX_ROWS_ANALYSIS = int(1e4)
 
 
 def test_col_val(

{csv_detective-0.9.1.dev1847.dist-info → csv_detective-0.9.1.dev1869.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: csv-detective
-Version: 0.9.1.dev1847
+Version: 0.9.1.dev1869
 Summary: Detect tabular files column content
 Author-email: Etalab <opendatateam@data.gouv.fr>
 License: MIT

{csv_detective-0.9.1.dev1847.dist-info → csv_detective-0.9.1.dev1869.dist-info}/RECORD

@@ -132,37 +132,37 @@ csv_detective/detection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG
 csv_detective/detection/columns.py,sha256=_JtZHBr3aoEmSWh2xVe2ISnt-G7hpnA9vqlvcaGd0Go,2887
 csv_detective/detection/encoding.py,sha256=KZ8W8BPfZAq9UiP5wgaeupYa5INU8KPz98E2L3XpX2Y,999
 csv_detective/detection/engine.py,sha256=1Z4vzjxwPRZ9-vv8nw-zU2sgBZtOsEz0UoKjGaSwVJU,1543
-csv_detective/detection/formats.py,sha256=dzJPdi2rP2jTHZBk9UHpJL3c5N-PSohCymHs-OZt45c,6211
+csv_detective/detection/formats.py,sha256=YFFEJHhlMw7IMtbotpam1qYt07djnYMHd8j6AvOA3XA,7459
 csv_detective/detection/headers.py,sha256=y5iR4jWH5fUtAH_Zg0zxWSVG_INCHlXJFMbhPpI2YMo,1148
 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=f-UFv_iULpVF_Fy39H4sfACEnrthjK4N3mCAVPkjnKw,1860
+csv_detective/output/__init__.py,sha256=02F5D5TODMiImyZzjnX-vIkMPkUC0ioIryqdBm6xT-w,2056
 csv_detective/output/dataframe.py,sha256=pjxvpzIWVUW9_xvT3JjoPnOIVUUHnzL7kZo1xQdMDxQ,2139
 csv_detective/output/example.py,sha256=XrnPS_uC0cICn7tgnLWNctpUbnPzl7fIMzNTzJEWGJc,8655
-csv_detective/output/profile.py,sha256=Jeh0mrfH_hAVxV2E5I4XzdCm7ZAGAV_Xj3AXOi77lcA,3130
+csv_detective/output/profile.py,sha256=k-t--uVHkrt3MRLnRAthiaF069jGc1jsQnfcOoBchrU,2524
 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
-csv_detective/parsing/columns.py,sha256=fbvQMu12gAmz4TnNCL7pLnMFB-mWN_O-zEoj8jEGj0A,5696
+csv_detective/parsing/columns.py,sha256=HRHJBJ1gftuheegJHzhQmg-u83pVAXXuQ9GKR34mKgk,5696
 csv_detective/parsing/compression.py,sha256=Fnw5tj-PpBNI8NYsWj5gD-DUoWcVLnsVpiKm9MpxmIA,350
 csv_detective/parsing/csv.py,sha256=fJkjKvyk7InkNnYKtmivyi48mmcwvrha7gvZ5J4-86A,1588
 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-0.9.1.dev1847.dist-info/licenses/LICENSE,sha256=A1dQrzxyxRHRih02KwibWj1khQyF7GeA6SqdOU87Gk4,1088
+csv_detective-0.9.1.dev1869.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=YuVbSfeo_ASPiLT8CyxXqJENcDpj4wAFXzLwu_GzsOA,8437
+tests/test_file.py,sha256=NBLwPCFN2skZHLkckPZ0M0ZvanEdL88KVK1Vi9GhSaU,8925
 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-0.9.1.dev1847.dist-info/METADATA,sha256=4GPrJUwsDAkxwVV9fnFv4pVHmelYX1C1H4QCh_zG8wc,9767
-csv_detective-0.9.1.dev1847.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-csv_detective-0.9.1.dev1847.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
-csv_detective-0.9.1.dev1847.dist-info/top_level.txt,sha256=cYKb4Ok3XgYA7rMDOYtxysjSJp_iUA9lJjynhVzue8g,30
-csv_detective-0.9.1.dev1847.dist-info/RECORD,,
+csv_detective-0.9.1.dev1869.dist-info/METADATA,sha256=3gGiQT_yLk3thJkrLt5l90W8ylzk_MVYN0_F3wGv5qE,9767
+csv_detective-0.9.1.dev1869.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+csv_detective-0.9.1.dev1869.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
+csv_detective-0.9.1.dev1869.dist-info/top_level.txt,sha256=cYKb4Ok3XgYA7rMDOYtxysjSJp_iUA9lJjynhVzue8g,30
+csv_detective-0.9.1.dev1869.dist-info/RECORD,,

tests/test_file.py

@@ -276,3 +276,20 @@ def test_cast_json(mocked_responses, cast_json):
     )
     assert analysis["columns"]["a_simple_dict"]["python_type"] == "json"
     assert isinstance(df["a_simple_dict"][0], expected_type)
+
+
+def test_almost_uniform_column(mocked_responses):
+    col_name = "int_not_bool"
+    expected_content = f"{col_name}\n" + "9\n" + "1\n" * int(1e7)
+    mocked_responses.get(
+        "http://example.com/test.csv",
+        body=expected_content,
+        status=200,
+    )
+    analysis = routine(
+        file_path="http://example.com/test.csv",
+        num_rows=-1,
+        output_profile=False,
+        save_results=False,
+    )
+    assert analysis["columns"][col_name]["format"] == "int"