Merge branch 'feature/polars' into polars_feature_rebase

dataprofiler/profilers/base_column_profilers.py

@@ -9,7 +9,7 @@
 from typing import Any, Callable, Generic, TypeVar
 
 import numpy as np
-import pandas as pd
+import polars as pl
 
 from . import profiler_utils
 from .profiler_options import BaseInspectorOptions, BaseOption
@@ -97,7 +97,7 @@ def _filter_properties_w_options(
     def _perform_property_calcs(
         self,
         calculations: dict,
-        df_series: pd.DataFrame,
+        df_series: pl.Series,
         prev_dependent_properties: dict,
         subset_properties: dict,
     ) -> None:
@@ -217,12 +217,12 @@ def __getitem__(self, item: str) -> Any:
         return getattr(self, item)
 
     @abc.abstractmethod
-    def _update_helper(self, df_series_clean: pd.DataFrame, profile: dict) -> None:
+    def _update_helper(self, df_series_clean: pl.Series, profile: dict) -> None:
         """Help update the profile."""
         raise NotImplementedError()
 
     @abc.abstractmethod
-    def update(self, df_series: pd.DataFrame) -> BaseColumnProfiler:
+    def update(self, df_series: pl.Series) -> BaseColumnProfiler:
         """
         Update the profile.
 

dataprofiler/profilers/categorical_column_profile.py

@@ -7,8 +7,9 @@
 from typing import cast
 
 import datasketches
+import pandas as pd
 import polars as pl
-from pandas import DataFrame, Series
+from polars import DataFrame, Series
 
 from .. import dp_logging
 from . import profiler_utils
@@ -681,6 +682,9 @@ def update(self, df_series: pl.Series | Series) -> CategoricalColumn:
         :return: updated CategoricalColumn
         :rtype: CategoricalColumn
         """
+        # TODO remove onces profiler builder is updated
+        if isinstance(df_series, pd.Series):
+            df_series = pl.from_pandas(df_series)  # type: ignore
         # If condition for limiting profile calculations
         if len(df_series) == 0 or self._stop_condition_is_met:
             return self