chore: fix linting errors

Author: portellaa

.pre-commit-config.yaml

@@ -1,4 +1,4 @@
-default_stages: [commit, push, manual]
+default_stages: [pre-commit, pre-push, manual]
 
 repos:
 -   repo: https://github.com/commitizen-tools/commitizen

src/ydata_profiling/model/correlations.py

@@ -1,6 +1,6 @@
 """Correlations between variables."""
 import warnings
-from typing import Dict, List, Optional, Sized
+from typing import Dict, List, Optional, Sized, no_type_check
 
 import numpy as np
 import pandas as pd
@@ -16,20 +16,21 @@
 class CorrelationBackend:
     """Helper class to select and cache the appropriate correlation backend (Pandas or Spark)."""
 
+    @no_type_check
     def __init__(self, df: Sized):
         """Determine backend once and store it for all correlation computations."""
         if isinstance(df, pd.DataFrame):
             from ydata_profiling.model.pandas import (
-                correlations_pandas as correlation_backend, #type: ignore
+                correlations_pandas as correlation_backend,
             )
         else:
             from ydata_profiling.model.spark import (
-                correlations_spark as correlation_backend, # type: ignore
+                correlations_spark as correlation_backend,
             )
 
         self.backend = correlation_backend
 
-    def get_method(self, method_name: str):
+    def get_method(self, method_name: str):  # noqa: ANN201
         """Retrieve the appropriate correlation method class from the backend."""
         if hasattr(self.backend, method_name):
             return getattr(self.backend, method_name)

src/ydata_profiling/model/dataframe.py

@@ -12,8 +12,10 @@
     from pyspark.sql import DataFrame as sparkDataFrame  # type: ignore
     from ydata_profiling.model.spark.dataframe_spark import spark_preprocess
 
-from ydata_profiling.config import Settings
-from ydata_profiling.model.pandas.dataframe_pandas import pandas_preprocess
+from ydata_profiling.config import Settings  # noqa: E402
+from ydata_profiling.model.pandas.dataframe_pandas import (  # noqa: E402
+    pandas_preprocess,
+)
 
 
 def preprocess(config: Settings, df: Any) -> Any:

src/ydata_profiling/model/describe.py

@@ -1,6 +1,6 @@
 """Organize the calculation of statistics for each series in this DataFrame."""
 from datetime import datetime
-from typing import Any, Dict, Optional, Union
+from typing import Any, Dict, Optional, Union, no_type_check
 
 import pandas as pd
 from tqdm.auto import tqdm
@@ -27,9 +27,10 @@
 from ydata_profiling.version import __version__
 
 
+@no_type_check
 def describe(
     config: Settings,
-    df: Union[pd.DataFrame, "pyspark.sql.DataFrame"],  # type: ignore
+    df: Union[pd.DataFrame, "pyspark.sql.DataFrame"],  # noqa
     summarizer: BaseSummarizer,
     typeset: VisionsTypeset,
     sample: Optional[dict] = None,

src/ydata_profiling/model/handler.py

@@ -1,7 +1,7 @@
 """
     Auxiliary handler methods for data summary extraction
 """
-from typing import Any, Callable, Dict, List, Sequence
+from typing import Callable, Dict, List, Sequence
 
 import networkx as nx
 from visions import VisionsTypeset
@@ -15,7 +15,7 @@ def compose(functions: Sequence[Callable]) -> Callable:
     :return: combined function applying all functions in order.
     """
 
-    def composed_function(*args):
+    def composed_function(*args):  # noqa: ANN201
         result = args  # Start with the input arguments
         for func in functions:
             result = func(*result) if isinstance(result, tuple) else func(result)

src/ydata_profiling/model/pandas/dataframe_pandas.py

@@ -1,5 +1,3 @@
-import warnings
-
 import pandas as pd
 
 from ydata_profiling.config import Settings

src/ydata_profiling/model/pandas/summary_pandas.py

@@ -9,6 +9,7 @@
 from visions import VisionsTypeset
 
 from ydata_profiling.config import Settings
+from ydata_profiling.model.summarizer import BaseSummarizer
 from ydata_profiling.model.typeset import ProfilingTypeSet
 from ydata_profiling.utils.dataframe import sort_column_names
 
@@ -20,7 +21,7 @@ def _is_cast_type_defined(typeset: VisionsTypeset, series: str) -> bool:
 def pandas_describe_1d(
     config: Settings,
     series: pd.Series,
-    summarizer: "BaseSummarizer",  # type:ignore
+    summarizer: BaseSummarizer,
     typeset: VisionsTypeset,
 ) -> dict:
     """Describe a series (infer the variable type, then calculate type-specific values).

src/ydata_profiling/model/spark/__init__.py

@@ -29,7 +29,7 @@
             for name in dir(module)
             if not name.startswith("_")
         }
-    ) # type: ignore
+    )  # type: ignore
 
 # Explicitly list all available functions
 __all__ = [

src/ydata_profiling/model/spark/describe_counts_spark.py

@@ -2,13 +2,15 @@
     Pyspark counts
 """
 from typing import Tuple
+
 import pandas as pd
+from pyspark.sql import DataFrame
+from pyspark.sql import functions as F
 
 from ydata_profiling.config import Settings
-
-from pyspark.sql import DataFrame, functions as F
 from ydata_profiling.model.summary_algorithms import describe_counts
 
+
 @describe_counts.register
 def describe_counts_spark(
     config: Settings, series: DataFrame, summary: dict
@@ -34,7 +36,9 @@ def describe_counts_spark(
     value_counts_index_sorted = value_counts.orderBy(F.asc(series.columns[0]))
 
     # Count missing values
-    n_missing = value_counts.filter(F.col(series.columns[0]).isNull()).select("count").first()
+    n_missing = (
+        value_counts.filter(F.col(series.columns[0]).isNull()).select("count").first()
+    )
     n_missing = n_missing["count"] if n_missing else 0
 
     # Convert top 200 values to Pandas for frequency table display
@@ -51,11 +55,9 @@ def describe_counts_spark(
 
     column = series.columns[0]
 
-
-    if series.dtypes[0][1] in ('int', 'float', 'bigint', 'double'):
+    if series.dtypes[0][1] in ("int", "float", "bigint", "double"):
         value_counts_no_nan = (
-            value_counts
-            .filter(F.col(column).isNotNull())  # Exclude NaNs
+            value_counts.filter(F.col(column).isNotNull())  # Exclude NaNs
             .filter(~F.isnan(F.col(column)))  # Remove implicit NaNs (if numeric column)
             .groupBy(column)  # Group by unique values
             .count()  # Count occurrences
@@ -64,8 +66,7 @@ def describe_counts_spark(
         )
     else:
         value_counts_no_nan = (
-            value_counts
-            .filter(F.col(column).isNotNull())  # Exclude NULLs
+            value_counts.filter(F.col(column).isNotNull())  # Exclude NULLs
             .groupBy(column)  # Group by unique timestamp values
             .count()  # Count occurrences
             .orderBy(F.desc("count"))  # Sort by most frequent timestamps
@@ -75,8 +76,12 @@ def describe_counts_spark(
     # Convert to Pandas Series, forcing proper structure
     if value_counts_no_nan.count() > 0:
         pdf = value_counts_no_nan.toPandas().set_index(column)["count"]
-        summary["value_counts_without_nan"] = pd.Series(pdf)  # Ensures it's always a Series
+        summary["value_counts_without_nan"] = pd.Series(
+            pdf
+        )  # Ensures it's always a Series
     else:
-        summary["value_counts_without_nan"] = pd.Series(dtype=int)  # Ensures an empty Series
+        summary["value_counts_without_nan"] = pd.Series(
+            dtype=int
+        )  # Ensures an empty Series
 
-    return config, series, summary
+    return config, series, summary

src/ydata_profiling/model/spark/duplicates_spark.py

@@ -6,6 +6,7 @@
 from ydata_profiling.config import Settings
 from ydata_profiling.model.duplicates import get_duplicates
 
+
 @get_duplicates.register
 def get_duplicates_spark(
     config: Settings, df: DataFrame, supported_columns: Sequence