fully finished

capitalone · Mar 3, 2024 · 7d9e655 · 7d9e655
1 parent a06a2a0
commit 7d9e655
Show file tree

Hide file tree

Showing 5 changed files with 95 additions and 111 deletions.
diff --git a/dataprofiler/profilers/float_column_profile.py b/dataprofiler/profilers/float_column_profile.py
@@ -280,7 +280,7 @@ def _get_float_precision(
 
         :param df_series_clean: df series with nulls removed, assumes all values
             are floats as well
-        :type df_series_clean: pandas.core.series.Series
+        :type df_series_clean: polars.series.series.Series
         :param sample_ratio: Ratio of samples used for float precision
         :type sample_ratio: float (between 0 and 1)
         :return: string representing its precision print format
@@ -332,9 +332,9 @@ def _is_each_row_float(cls, df_series: pl.Series) -> pl.Series:
         For column [1.0, np.NaN, 1.0] returns [True, True, True]
         For column [1.0, "a", "b"] returns [True, False, False]
         :param df_series: series of values to evaluate
-        :type df_series: pandas.core.series.Series
+        :type df_series: polars.series.series.Series
         :return: is_float_col
-        :rtype: Union[List[bool], pandas.Series[bool]]
+        :rtype: pl.Series
         """
         if len(df_series) == 0:
             return pl.Series()
@@ -361,7 +361,7 @@ def _update_precision(
         subset before they are merged into the main data profile.
         :type subset_properties: dict
         :param df_series: Data to be profiled
-        :type df_series: pandas.DataFrame
+        :type df_series: polars.DataFrame
         :return: None
         """
         sample_ratio = None
@@ -403,19 +403,18 @@ def _update_helper(self, df_series_clean: pl.Series, profile: dict) -> None:
         Update column profile properties with cleaned dataset and its known profile.
 
         :param df_series_clean: df series with nulls removed
-        :type df_series_clean: pandas.core.series.Series
+        :type df_series_clean: polars.series.series.Series
         :param profile: float profile dictionary
         :type profile: dict
         :return: None
         """
-        df_series_clean = df_series_clean.to_pandas()
         if self._NumericStatsMixin__calculations:
             NumericStatsMixin._update_helper(self, df_series_clean, profile)
         self._update_column_base_properties(profile)
 
     def _update_numeric_stats(
         self,
-        df_series: pl.DataFrame,
+        df_series: pl.Series,
         prev_dependent_properties: dict,
         subset_properties: dict,
     ) -> None:
@@ -430,7 +429,7 @@ def _update_numeric_stats(
         subset before they are merged into the main data profile.
         :type subset_properties: Dict
         :param df_series: Data to be profiled
-        :type df_series: Pandas Dataframe
+        :type df_series: Polars Dataframe
         :return: None
         """
         super()._update_helper(df_series, subset_properties)
@@ -440,7 +439,7 @@ def update(self, df_series: pl.Series) -> FloatColumn:
         Update the column profile.
 
         :param df_series: df series
-        :type df_series: pandas.core.series.Series
+        :type df_series: polars.series.series.Series
         :return: updated FloatColumn
         :rtype: FloatColumn
         """

diff --git a/dataprofiler/profilers/int_column_profile.py b/dataprofiler/profilers/int_column_profile.py
@@ -2,7 +2,6 @@
 from __future__ import annotations
 
 import numpy as np
-import pandas as pd
 import polars as pl
 
 from .base_column_profilers import BaseColumnPrimitiveTypeProfiler, BaseColumnProfiler
@@ -125,7 +124,7 @@ def _is_each_row_int(cls, df_series: pl.Series) -> list[bool]:
         For column [1.1 1.1 1.1] returns False
 
         :param df_series: series of values to evaluate
-        :type df_series: pandas.core.series.Series
+        :type df_series: polars.series.series.Series
         :return: is_int_col
         :rtype: list
         """
@@ -140,12 +139,11 @@ def _update_helper(self, df_series_clean: pl.Series, profile: dict) -> None:
         Update col profile properties with clean dataset and its known null params.
 
         :param df_series_clean: df series with nulls removed
-        :type df_series_clean: pandas.core.series.Series
+        :type df_series_clean: polars.series.series.Series
         :param profile: int profile dictionary
         :type profile: dict
         :return: None
         """
-        df_series_clean = pd.Series(df_series_clean.to_numpy())
         if self._NumericStatsMixin__calculations:
             NumericStatsMixin._update_helper(self, df_series_clean, profile)
         self._update_column_base_properties(profile)
@@ -155,7 +153,7 @@ def update(self, df_series: pl.Series) -> IntColumn:
         Update the column profile.
 
         :param df_series: df series
-        :type df_series: pandas.core.series.Series
+        :type df_series: polars.series.series.Series
         :return: updated IntColumn
         :rtype: IntColumn
         """