churnkit 0.75.1a2__py3-none-any.whl → 0.76.0a1__py3-none-any.whl

customer_retention/stages/profiling/time_series_profiler.py

@@ -6,9 +6,9 @@ import numpy as np
 from customer_retention.core.compat import (
     DataFrame,
     Timestamp,
-    is_datetime64_any_dtype,
+    ensure_datetime_column,
+    native_pd,
     pd,
-    to_datetime,
     to_pandas,
 )
 
@@ -96,7 +96,7 @@ def classify_lifecycle_quadrants(entity_lifecycles: DataFrame) -> LifecycleQuadr
         lifecycles=lc,
         tenure_threshold=tenure_threshold,
         intensity_threshold=intensity_threshold,
-        recommendations=pd.DataFrame(rows),
+        recommendations=native_pd.DataFrame(rows),
     )
 
 
@@ -161,7 +161,7 @@ def classify_activity_segments(entity_lifecycles: DataFrame) -> ActivitySegmentR
         lifecycles=lc,
         q25_threshold=q25,
         q75_threshold=q75,
-        recommendations=pd.DataFrame(rows),
+        recommendations=native_pd.DataFrame(rows),
     )
 
 
@@ -196,11 +196,12 @@ class TimeSeriesProfiler:
         self.time_column = time_column
 
     def profile(self, df: DataFrame) -> TimeSeriesProfile:
+        df = self._prepare_dataframe(df)
+
         if len(df) == 0:
             return self._empty_profile()
 
         self._validate_columns(df)
-        df = self._prepare_dataframe(df)
 
         total_events = len(df)
         unique_entities = df[self.entity_column].nunique()
@@ -231,14 +232,13 @@ class TimeSeriesProfiler:
 
     def _prepare_dataframe(self, df: DataFrame) -> DataFrame:
         df = to_pandas(df).copy()
-        if not is_datetime64_any_dtype(df[self.time_column]):
-            df[self.time_column] = to_datetime(df[self.time_column])
+        ensure_datetime_column(df, self.time_column)
         return df
 
     def _compute_entity_lifecycles(self, df: DataFrame) -> DataFrame:
         grouped = df.groupby(self.entity_column)[self.time_column]
 
-        lifecycles = pd.DataFrame({
+        lifecycles = native_pd.DataFrame({
             "entity": grouped.first().index.tolist(),
             "first_event": grouped.min().values,
             "last_event": grouped.max().values,
@@ -303,7 +303,7 @@ class TimeSeriesProfiler:
             events_per_entity=DistributionStats(
                 min=0, max=0, mean=0, median=0, std=0, q25=0, q75=0
             ),
-            entity_lifecycles=pd.DataFrame(columns=[
+            entity_lifecycles=native_pd.DataFrame(columns=[
                 "entity", "first_event", "last_event", "duration_days", "event_count"
             ]),
             avg_inter_event_days=None,

customer_retention/stages/profiling/time_window_aggregator.py

@@ -10,9 +10,11 @@ from customer_retention.core.compat import (
     DataFrame,
     Timedelta,
     Timestamp,
+    ensure_datetime_column,
     is_numeric_dtype,
+    native_pd,
     pd,
-    to_datetime,
+    to_pandas,
 )
 
 
@@ -82,11 +84,12 @@ class TimeWindowAggregator:
         include_recency: bool = False, include_tenure: bool = False,
         exclude_columns: Optional[List[str]] = None,
     ) -> DataFrame:
+        df = to_pandas(df)
         if len(df) == 0:
-            return pd.DataFrame()
+            return native_pd.DataFrame()
 
         df = df.copy()
-        df[self.time_column] = to_datetime(df[self.time_column])
+        ensure_datetime_column(df, self.time_column)
         reference_date = self._validate_reference_date(df, reference_date)
         parsed_windows = [TimeWindow.from_string(w) for w in (windows or ["30d"])]
 
@@ -111,7 +114,7 @@ class TimeWindowAggregator:
         if include_tenure:
             result_data["days_since_first_event"] = self._compute_tenure(df, entities, reference_date)
 
-        result = pd.DataFrame(result_data)
+        result = native_pd.DataFrame(result_data)
         result.attrs["aggregation_reference_date"] = (
             reference_date.isoformat() if hasattr(reference_date, "isoformat") else str(reference_date))
         result.attrs["aggregation_timestamp"] = Timestamp.now().isoformat()

customer_retention/stages/transformation/datetime_transformer.py

@@ -3,7 +3,14 @@ from typing import Optional, Union
 
 import numpy as np
 
-from customer_retention.core.compat import DataFrame, Series, Timestamp, is_datetime64_any_dtype, pd
+from customer_retention.core.compat import (
+    DataFrame,
+    Series,
+    Timestamp,
+    ensure_pandas_series,
+    is_datetime64_any_dtype,
+    safe_to_datetime,
+)
 
 
 @dataclass
@@ -92,6 +99,7 @@ class DatetimeTransformer:
         )
 
     def _ensure_datetime(self, series: Series) -> Series:
+        series = ensure_pandas_series(series)
         if is_datetime64_any_dtype(series):
             return series
-        return pd.to_datetime(series, errors='coerce', format='mixed')
+        return safe_to_datetime(series, errors='coerce')