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

{churnkit-0.75.1a1.dist-info → churnkit-0.75.1a2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: churnkit
-Version: 0.75.1a1
+Version: 0.75.1a2
 Summary: Structured ML framework for customer churn prediction -- from exploration notebooks to production pipelines, locally or on Databricks.
 Project-URL: Homepage, https://github.com/aladjov/CR
 Project-URL: Documentation, https://github.com/aladjov/CR/wiki

{churnkit-0.75.1a1.dist-info → churnkit-0.75.1a2.dist-info}/RECORD

@@ -1,9 +1,9 @@
-customer_retention/__init__.py,sha256=eWE6DURL9I4j4mhLjGhGbuT_Ab6c_yj0tp77DF7X6yk,1114
+customer_retention/__init__.py,sha256=C6I88EHy9hhtRAg0eGgH0JkXYBBA2lzOc6qitHneXuw,1114
 customer_retention/cli.py,sha256=Wdl540cZgu_9mV-hWmTV9jD3S8QTDR8Ik-5hQXYCvmg,2466
 customer_retention/analysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 customer_retention/analysis/jupyter_save_hook.py,sha256=iiNFIL83yOPX8BGUjCE6Pt5Kc8X-2adtE1_NZTMUaZQ,947
 customer_retention/analysis/notebook_html_exporter.py,sha256=AMOTcD6nZncM4MPdVS1Kn4WF2YoaOoODMI2X48oEZ24,4491
-customer_retention/analysis/notebook_progress.py,sha256=EUJTvGIIdZF_wCi4NtuL7pHx3vX--HSLdwlT09-0ulk,2212
+customer_retention/analysis/notebook_progress.py,sha256=aauU-0AXHraFf0M_91aSmZwI-HmZslaGnmu-Msw4xPM,2298
 customer_retention/analysis/plotly_preprocessor.py,sha256=Bdd_9-AmfmJdrmm030wzgpLflbiszp9KhXPbw_F5Id0,5300
 customer_retention/analysis/auto_explorer/__init__.py,sha256=0isViyt62QvDkYc2oxOhsDQ9RNMqBq1ihvwEZgoLb_s,1572
 customer_retention/analysis/auto_explorer/exploration_manager.py,sha256=60ObVRhYwAWqHnLrkeJ6_oQjPvXOl4gkLutE66_k8uc,18028
@@ -212,7 +212,7 @@ customer_retention/stages/preprocessing/transformer_manager.py,sha256=-yDfUA5_No
 customer_retention/stages/profiling/__init__.py,sha256=9t4OJvV7DyI11zzN0ZkOi_pzCj_Qjp6BPpdpCA6-MKo,9884
 customer_retention/stages/profiling/categorical_distribution.py,sha256=kcbhpcIbdCcNJ9Cu_YiTz8cgUBTugrY5avMrL0Ymmd0,10704
 customer_retention/stages/profiling/categorical_target_analyzer.py,sha256=T-QvI0qW2R8aeamhuvSqglluMFUuJxdO9_lMLdU3Kr4,12077
-customer_retention/stages/profiling/column_profiler.py,sha256=kCoh4czphLd9-4FPCKWkV6q6YB0iZEf998yPwV4XR9A,20372
+customer_retention/stages/profiling/column_profiler.py,sha256=WZKwPxpDmCQiBJBHB-y50Nwfd-m78XEDmhV0YtCDSok,20382
 customer_retention/stages/profiling/distribution_analysis.py,sha256=9v-QY41cuQI_Fuvjkqx1Q3QAcsSK8ThU43t8PRgD0uo,17052
 customer_retention/stages/profiling/drift_detector.py,sha256=I1OYr37ew-XB7sVp6VARqjH0eKZA1Rx0eOQNRJZTOMs,12681
 customer_retention/stages/profiling/feature_capacity.py,sha256=fP_sK2KxU6zpdfnIcAW313N451SXqHT1wv9psd5WhSk,19598
@@ -229,14 +229,14 @@ customer_retention/stages/profiling/target_level_analyzer.py,sha256=XPhdHqTdK9zz
 customer_retention/stages/profiling/temporal_analyzer.py,sha256=PXf4pYNcszp7N8_14MKFKXDku-fw2M_NLWN7jUsHd1Q,16102
 customer_retention/stages/profiling/temporal_coverage.py,sha256=r23s1qyB7o11ab_TTLOgb4q29OPA_crRshFpMLt4t_w,18561
 customer_retention/stages/profiling/temporal_feature_analyzer.py,sha256=iWcT84ly5iPqNRnxDxe458R4Iha5u72_g-2-ZNAk4Gs,32343
-customer_retention/stages/profiling/temporal_feature_engineer.py,sha256=Eovymy6qoFIOYy3-sQZyqVTYfIXOAf11aomBcjLjMSE,27096
-customer_retention/stages/profiling/temporal_pattern_analyzer.py,sha256=VXjKr21CEaHQY7PYrasGeDWESlLeQdam64JdNB46-_Y,26383
-customer_retention/stages/profiling/temporal_quality_checks.py,sha256=02teyAdAsASWsJZD7SElfutBYwK23DaNSRO4rgW1Fxs,13552
+customer_retention/stages/profiling/temporal_feature_engineer.py,sha256=kTp5avXNsGGCYF_TBUg4KpbzfL79zz50zQ7ywVOxPkg,27141
+customer_retention/stages/profiling/temporal_pattern_analyzer.py,sha256=EyV5905sjclCv4AOblXn6P8bDHvQpJsv7yuIotlpZLA,26512
+customer_retention/stages/profiling/temporal_quality_checks.py,sha256=bxZEqpADOFoYWb-rXBZrFyUdRHqQ9k4fCrQXzL4uVCk,13590
 customer_retention/stages/profiling/temporal_target_analyzer.py,sha256=eeZlUhTWZfCftwgm_dySi1feRLuoU9SRLL_r_4jgN5g,8785
 customer_retention/stages/profiling/text_embedder.py,sha256=ck7WIq7pGC7xgEzMQr7fYdHcJegYR6wfdh3z32WUiK8,3038
 customer_retention/stages/profiling/text_processor.py,sha256=spdfwVSEU07aYbl2bIsg_INOBt3Js-IA15WVkjf1ask,4474
 customer_retention/stages/profiling/text_reducer.py,sha256=ilSuUAu0dHUyRGTNg8TzoCEd-EAyXKvoAm4uGqwlSQs,2409
-customer_retention/stages/profiling/time_series_profiler.py,sha256=9EaCRHMIrSVGFW_IWnU8BU4v44WZKMb8Tbbdw13y41Y,10384
+customer_retention/stages/profiling/time_series_profiler.py,sha256=AGX7BJiKwCtzyPL4cWy3EmqS6CnDwr8PZCWCl_5ivmA,10410
 customer_retention/stages/profiling/time_window_aggregator.py,sha256=NcxVAor8JhDnPLap_iS3z81flejd7uPeTQLwLmQn7MA,15868
 customer_retention/stages/profiling/type_detector.py,sha256=VgYHWcBGepyJKNdY1FKgb9scOaosN6fDY_-WiTjfoAg,14726
 customer_retention/stages/profiling/window_recommendation.py,sha256=Apd_PDFpo49HJJzldTcwzzgJjBzEfd8mbGboBwHhzGw,13354
@@ -270,33 +270,33 @@ customer_retention/stages/validation/pipeline_validation_runner.py,sha256=uuBvGx
 customer_retention/stages/validation/quality_scorer.py,sha256=VuhSEZj3rL5URvxSjdIryOS1W0x7y_BNlX5yog4ExNk,19017
 customer_retention/stages/validation/rule_generator.py,sha256=E6jeWMeCiMRq9lhoryGB8Tvdo65poJi5dj3oNRtC19k,2139
 customer_retention/stages/validation/scoring_pipeline_validator.py,sha256=FvM7AsNpiOO0nLr6NGkJGzJfUhxvPNZ7ccDrp44zFiI,21537
-customer_retention/stages/validation/timeseries_detector.py,sha256=3IJ6H9bdu3nvxJZcrbhRJpl0nY7wLo2SAukM3AlgIe4,27619
+customer_retention/stages/validation/timeseries_detector.py,sha256=OODBr-NZ9JvtiT80JTynXQe6YaA8A2TOoQRLcJ_JNpw,27685
 customer_retention/transforms/__init__.py,sha256=W9owOGVCFSoCQfcRAQciNASYqbPpDE9gGjvnLcXawrE,1320
 customer_retention/transforms/artifact_store.py,sha256=FYLpDcv2N6-dUTX5RPEIK3aCWKhYK3hRpPROidLpRik,1641
 customer_retention/transforms/executor.py,sha256=oML5dCidxbW_q6YUkAwWcutYP6bIFB6IdD3BvemK45A,6304
 customer_retention/transforms/fitted.py,sha256=3pNvnae-P3t3bKMeZz1Bl0xww-feapIYdoeTY6aUtI8,3278
 customer_retention/transforms/ops.py,sha256=Xg2g9UOOudq_y9Hf3oWsjpqw3dEoykQR5pDSoyW8GX0,4294
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/00_start_here.ipynb,sha256=zCyhftEd3v9fc0Ta6wvA6b-9LcoGzRi8bS1tMZ3iu9w,21911
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/01_data_discovery.ipynb,sha256=up0X3oDJ5sAo1-tbqMyZj_f1h6D542G2uAxjVmtYCOI,46430
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/01a_a_temporal_text_deep_dive.ipynb,sha256=uai8T3iJSqOrabBQnVi8Z0k8zZGVgs_VVQWRHyXN8QU,33690
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/01a_temporal_deep_dive.ipynb,sha256=fC1ASNtvI8X1lAe-Lzcw3oX2cptDC-ymPeEtKKWhg20,67326
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/01b_temporal_quality.ipynb,sha256=RU5hxgrTVMZs1ytChVv1t49WpTO0Oj6B_Fu8g0xS0To,23039
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/01c_temporal_patterns.ipynb,sha256=ZGYfztP6JhOEwPmTYdC0l7w579fKXcNEJXq-PnCLc2I,153167
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/01d_event_aggregation.ipynb,sha256=-FT3SoBU0fhaZxGeTo-_UQl6riCrtoJaFnUg31opk64,63244
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/02_column_deep_dive.ipynb,sha256=mbP2LQWsXDyTsWg0bhrCBHEfHsEer_XOXRYV9f8JxAk,60250
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/02a_text_columns_deep_dive.ipynb,sha256=M9YN8yAjjuC6ZaUlc-rVqVLEkWd7Rc_GNILHS9qO3PU,29704
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/03_quality_assessment.ipynb,sha256=H49LLmn1PHbcbAvSQfteESRGk125QwkPI5qbLk3yZgc,68595
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/04_relationship_analysis.ipynb,sha256=Rr-B4-xg0ILuAIgztlZkiGJdTzLuNjOqBFxO8W4o9iU,78624
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/05_multi_dataset.ipynb,sha256=bBxkuZyTl1yZg4kMXO87WRjgZMhj_6hwLGX6m3XC270,62664
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/06_feature_opportunities.ipynb,sha256=cBJF5o4z3Z-dustQ4CVklnfTcQ8saG97tlgswWK9uWE,67409
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/07_modeling_readiness.ipynb,sha256=IiA04fyb-l097Glp3MtR03vPjQsZlS1Icg-hjEHa_Dg,28376
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/08_baseline_experiments.ipynb,sha256=KmjhnDf1JdpEiIcdfQ-ZFo_at6t9JRC30B6NmmvMBmg,34226
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/09_business_alignment.ipynb,sha256=tMNfGM7AH50N1ONzHhGW2HZLpQwraIxVzOiVnI-10X8,17214
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/10_spec_generation.ipynb,sha256=KeUdfL9Mvdi6023XpnfZ6oLEDNZaWiIHUfsAWig24mE,42847
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/11_scoring_validation.ipynb,sha256=5fi3eHMm03ZKZgdFAXMgydtZ3qX2TtR3L9bZS2MpWPE,49937
-churnkit-0.75.1a1.data/data/share/churnkit/exploration_notebooks/12_view_documentation.ipynb,sha256=aQF7CG8HxckqUKOKqnmZgMkSvfVzyO2LlYPrymLYjBY,4405
-churnkit-0.75.1a1.dist-info/METADATA,sha256=7IQb94O6dIEFTy7hejcQJU8eXJ6QKnnmxpyZqUKSrhY,12736
-churnkit-0.75.1a1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-churnkit-0.75.1a1.dist-info/entry_points.txt,sha256=swQFVe-jjgQSBJQNO2Ulkz2F5odaE-TsnlTor3HQBjw,70
-churnkit-0.75.1a1.dist-info/licenses/LICENSE,sha256=Bud8Oj25tnpoIuXCWW0xcSfmGPeEZAAHrDRoKdSYtZY,11344
-churnkit-0.75.1a1.dist-info/RECORD,,
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/00_start_here.ipynb,sha256=zCyhftEd3v9fc0Ta6wvA6b-9LcoGzRi8bS1tMZ3iu9w,21911
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/01_data_discovery.ipynb,sha256=up0X3oDJ5sAo1-tbqMyZj_f1h6D542G2uAxjVmtYCOI,46430
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/01a_a_temporal_text_deep_dive.ipynb,sha256=uai8T3iJSqOrabBQnVi8Z0k8zZGVgs_VVQWRHyXN8QU,33690
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/01a_temporal_deep_dive.ipynb,sha256=fC1ASNtvI8X1lAe-Lzcw3oX2cptDC-ymPeEtKKWhg20,67326
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/01b_temporal_quality.ipynb,sha256=RU5hxgrTVMZs1ytChVv1t49WpTO0Oj6B_Fu8g0xS0To,23039
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/01c_temporal_patterns.ipynb,sha256=ZGYfztP6JhOEwPmTYdC0l7w579fKXcNEJXq-PnCLc2I,153167
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/01d_event_aggregation.ipynb,sha256=-FT3SoBU0fhaZxGeTo-_UQl6riCrtoJaFnUg31opk64,63244
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/02_column_deep_dive.ipynb,sha256=mbP2LQWsXDyTsWg0bhrCBHEfHsEer_XOXRYV9f8JxAk,60250
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/02a_text_columns_deep_dive.ipynb,sha256=M9YN8yAjjuC6ZaUlc-rVqVLEkWd7Rc_GNILHS9qO3PU,29704
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/03_quality_assessment.ipynb,sha256=H49LLmn1PHbcbAvSQfteESRGk125QwkPI5qbLk3yZgc,68595
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/04_relationship_analysis.ipynb,sha256=Rr-B4-xg0ILuAIgztlZkiGJdTzLuNjOqBFxO8W4o9iU,78624
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/05_multi_dataset.ipynb,sha256=bBxkuZyTl1yZg4kMXO87WRjgZMhj_6hwLGX6m3XC270,62664
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/06_feature_opportunities.ipynb,sha256=cBJF5o4z3Z-dustQ4CVklnfTcQ8saG97tlgswWK9uWE,67409
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/07_modeling_readiness.ipynb,sha256=IiA04fyb-l097Glp3MtR03vPjQsZlS1Icg-hjEHa_Dg,28376
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/08_baseline_experiments.ipynb,sha256=KmjhnDf1JdpEiIcdfQ-ZFo_at6t9JRC30B6NmmvMBmg,34226
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/09_business_alignment.ipynb,sha256=tMNfGM7AH50N1ONzHhGW2HZLpQwraIxVzOiVnI-10X8,17214
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/10_spec_generation.ipynb,sha256=KeUdfL9Mvdi6023XpnfZ6oLEDNZaWiIHUfsAWig24mE,42847
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/11_scoring_validation.ipynb,sha256=5fi3eHMm03ZKZgdFAXMgydtZ3qX2TtR3L9bZS2MpWPE,49937
+churnkit-0.75.1a2.data/data/share/churnkit/exploration_notebooks/12_view_documentation.ipynb,sha256=aQF7CG8HxckqUKOKqnmZgMkSvfVzyO2LlYPrymLYjBY,4405
+churnkit-0.75.1a2.dist-info/METADATA,sha256=_YubBia8HFc-pJjr1z979oFMzQ6kH61DYhHalVn-y40,12736
+churnkit-0.75.1a2.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+churnkit-0.75.1a2.dist-info/entry_points.txt,sha256=swQFVe-jjgQSBJQNO2Ulkz2F5odaE-TsnlTor3HQBjw,70
+churnkit-0.75.1a2.dist-info/licenses/LICENSE,sha256=Bud8Oj25tnpoIuXCWW0xcSfmGPeEZAAHrDRoKdSYtZY,11344
+churnkit-0.75.1a2.dist-info/RECORD,,

customer_retention/__init__.py

@@ -17,7 +17,7 @@ Main module categories:
                 llm_context, iteration)
 """
 
-__version__ = "0.75.1a1"
+__version__ = "0.75.1a2"
 
 # Environment utilities (always available)
 from .core.compat import (

customer_retention/analysis/notebook_progress.py

@@ -4,7 +4,7 @@ import threading
 from pathlib import Path
 from typing import Optional
 
-from customer_retention.analysis.notebook_html_exporter import export_notebook_html
+from customer_retention.core.compat import is_databricks
 from customer_retention.core.config.experiments import get_notebook_experiments_dir
 
 
@@ -25,7 +25,7 @@ def track_and_export_previous(current_notebook: str) -> None:
     previous = _read_last_notebook(progress_file)
     _write_current_notebook(progress_file, current_notebook)
 
-    if previous:
+    if previous and not is_databricks():
         _export_in_background(previous, docs_dir)
 
 
@@ -40,6 +40,8 @@ def _read_last_notebook(progress_file: Path) -> Optional[str]:
 
 def _export_notebook(notebook_name: str, docs_dir: Path) -> Optional[Path]:
     """Export *notebook_name* to HTML in *docs_dir*."""
+    from customer_retention.analysis.notebook_html_exporter import export_notebook_html
+
     return export_notebook_html(Path(notebook_name), docs_dir)
 
 

customer_retention/stages/profiling/column_profiler.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 import numpy as np
 
-from customer_retention.core.compat import Timestamp, is_bool_dtype, is_datetime64_any_dtype, pd
+from customer_retention.core.compat import Timestamp, is_bool_dtype, is_datetime64_any_dtype, pd, to_datetime
 from customer_retention.core.config.column_config import ColumnType
 
 from .profile_result import (
@@ -304,7 +304,7 @@ class DatetimeProfiler(ColumnProfiler):
                 pass
             else:
                 try:
-                    clean_series = pd.to_datetime(clean_series, errors='coerce', format='mixed')
+                    clean_series = to_datetime(clean_series, errors='coerce', format='mixed')
                 except Exception:
                     return {"datetime_metrics": None}
 

customer_retention/stages/profiling/temporal_feature_engineer.py

@@ -25,7 +25,7 @@ from typing import Any, Dict, List, Optional
 
 import numpy as np
 
-from customer_retention.core.compat import pd
+from customer_retention.core.compat import Timedelta, pd, to_datetime, to_pandas
 
 
 class ReferenceMode(Enum):
@@ -179,8 +179,8 @@ class TemporalFeatureEngineer:
         Returns:
             TemporalFeatureResult with features DataFrame and metadata
         """
-        events_df = events_df.copy()
-        events_df[time_col] = pd.to_datetime(events_df[time_col])
+        events_df = to_pandas(events_df).copy()
+        events_df[time_col] = to_datetime(events_df[time_col])
 
         # Determine reference dates per entity
         ref_dates = self._get_reference_dates(
@@ -313,9 +313,9 @@ class TemporalFeatureEngineer:
             })
 
         if reference_dates is not None and reference_col is not None:
-            ref_df = reference_dates[[entity_col, reference_col]].copy()
+            ref_df = to_pandas(reference_dates)[[entity_col, reference_col]].copy()
             ref_df.columns = [entity_col, "reference_date"]
-            ref_df["reference_date"] = pd.to_datetime(ref_df["reference_date"])
+            ref_df["reference_date"] = to_datetime(ref_df["reference_date"])
             return ref_df
 
         # Default: Use last event date per entity
@@ -511,8 +511,8 @@ class TemporalFeatureEngineer:
             entity_df["last_event"].iloc[0]
 
             # Calculate split boundaries
-            split1 = first_event + pd.Timedelta(days=history_days * splits[0])
-            split2 = first_event + pd.Timedelta(days=history_days * (splits[0] + splits[1]))
+            split1 = first_event + Timedelta(days=history_days * splits[0])
+            split2 = first_event + Timedelta(days=history_days * (splits[0] + splits[1]))
 
             for col in value_cols:
                 beginning_val = entity_df[entity_df[time_col] < split1][col].sum()

customer_retention/stages/profiling/temporal_pattern_analyzer.py

@@ -5,7 +5,7 @@ from typing import Dict, List, Optional, Tuple
 import numpy as np
 from scipy import stats
 
-from customer_retention.core.compat import DataFrame, Timestamp, cut, pd, to_datetime
+from customer_retention.core.compat import DataFrame, Timestamp, cut, pd, to_datetime, to_pandas
 from customer_retention.core.utils import compute_effect_size
 
 
@@ -231,6 +231,7 @@ def compute_recency_buckets(
     df: DataFrame, entity_column: str, time_column: str, target_column: str,
     reference_date: Timestamp, bucket_edges: Optional[List[float]] = None
 ) -> List[RecencyBucketStats]:
+    df = to_pandas(df)
     edges = bucket_edges or DEFAULT_BUCKET_EDGES
     labels = _generate_bucket_labels(edges)
     entity_last = df.groupby(entity_column)[time_column].max().reset_index()
@@ -296,6 +297,7 @@ def classify_distribution_pattern(buckets: List[RecencyBucketStats]) -> str:
 def _diagnose_anomaly_pattern(
     df: DataFrame, entity_column: str, time_column: str, target_column: str
 ) -> AnomalyDiagnostics:
+    df = to_pandas(df)
     entity_target = df.groupby(entity_column)[target_column].first()
     target_1_pct = float(entity_target.mean() * 100)
     target_1_is_minority = target_1_pct < 50
@@ -431,6 +433,7 @@ def compare_recency_by_target(
     df: DataFrame, entity_column: str, time_column: str, target_column: str,
     reference_date: Optional[Timestamp] = None, cap_percentile: float = 0.99
 ) -> Optional[RecencyComparisonResult]:
+    df = to_pandas(df)
     if target_column not in df.columns:
         return None
     ref_date = reference_date or df[time_column].max()
@@ -495,7 +498,7 @@ class TemporalPatternAnalyzer:
         if len(df) < 3:
             return self._unknown_trend()
 
-        df_clean = df[[self.time_column, value_column]].dropna()
+        df_clean = to_pandas(df)[[self.time_column, value_column]].dropna()
         if len(df_clean) < 3:
             return self._unknown_trend()
 
@@ -583,7 +586,7 @@ class TemporalPatternAnalyzer:
         if len(df) == 0:
             return pd.DataFrame()
 
-        df_copy = df.copy()
+        df_copy = to_pandas(df).copy()
         entity_first_event = df_copy.groupby(entity_column)[cohort_column].min()
         df_copy["_cohort"] = df_copy[entity_column].map(entity_first_event)
         df_copy["_cohort"] = to_datetime(df_copy["_cohort"]).dt.to_period(period)
@@ -611,6 +614,7 @@ class TemporalPatternAnalyzer:
         if len(df) == 0:
             return RecencyResult(avg_recency_days=0, median_recency_days=0, min_recency_days=0, max_recency_days=0)
 
+        df = to_pandas(df)
         ref_date = reference_date or Timestamp.now()
         to_datetime(df[self.time_column])
 

customer_retention/stages/profiling/temporal_quality_checks.py

@@ -1,7 +1,7 @@
 from dataclasses import dataclass, field
 from typing import Optional
 
-from customer_retention.core.compat import DataFrame, Timestamp, to_datetime
+from customer_retention.core.compat import DataFrame, Timestamp, to_datetime, to_pandas
 from customer_retention.core.components.enums import Severity
 
 
@@ -73,6 +73,7 @@ class TemporalGapCheck(TemporalQualityCheck):
         if len(df) < 2:
             return self._pass_result("Insufficient data to check gaps")
 
+        df = to_pandas(df)
         time_col = to_datetime(df.sort_values(self.time_column)[self.time_column])
         diffs_days = time_col.diff().dropna().dt.total_seconds() / 86400
         expected_days = self.FREQ_TO_DAYS.get(self.expected_frequency, 1)

customer_retention/stages/profiling/time_series_profiler.py

@@ -9,6 +9,7 @@ from customer_retention.core.compat import (
     is_datetime64_any_dtype,
     pd,
     to_datetime,
+    to_pandas,
 )
 
 
@@ -229,7 +230,7 @@ class TimeSeriesProfiler:
             raise KeyError(f"Time column '{self.time_column}' not found")
 
     def _prepare_dataframe(self, df: DataFrame) -> DataFrame:
-        df = df.copy()
+        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])
         return df

customer_retention/stages/validation/timeseries_detector.py

@@ -11,7 +11,7 @@ from datetime import timedelta
 from enum import Enum
 from typing import Any, Dict, List, Optional, Tuple
 
-from customer_retention.core.compat import DataFrame, is_datetime64_any_dtype, pd, to_datetime
+from customer_retention.core.compat import DataFrame, is_datetime64_any_dtype, pd, to_datetime, to_pandas
 
 
 class DatasetType(Enum):
@@ -181,6 +181,7 @@ class TimeSeriesDetector:
         TimeSeriesCharacteristics
             Detected characteristics of the dataset
         """
+        df = to_pandas(df)
         evidence = []
 
         # Auto-detect entity column if not provided
@@ -510,6 +511,8 @@ class TimeSeriesValidator:
         """
         issues = []
 
+        df = to_pandas(df)
+
         # Validate inputs
         if entity_column not in df.columns:
             return TimeSeriesValidationResult(