churnkit 0.75.1a2__py3-none-any.whl → 0.75.1a3__py3-none-any.whl

{churnkit-0.75.1a2.dist-info → churnkit-0.75.1a3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: churnkit
-Version: 0.75.1a2
+Version: 0.75.1a3
 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-0.75.1a2.dist-info → churnkit-0.75.1a3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-customer_retention/__init__.py,sha256=C6I88EHy9hhtRAg0eGgH0JkXYBBA2lzOc6qitHneXuw,1114
+customer_retention/__init__.py,sha256=9vKI748I497pRMAJl1x4_Th5hfFQRDfIHny7dk6gyQU,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
@@ -56,14 +56,14 @@ customer_retention/analysis/recommendations/transform/__init__.py,sha256=z5HPxPG
 customer_retention/analysis/recommendations/transform/power.py,sha256=4S-zZnLWrHVW4Q52xiyCPXJ8OweO28Tnld94kiFY5yw,3738
 customer_retention/analysis/recommendations/transform/scale.py,sha256=mKt6_UV0iQ1AiQwyHr3owhvkFWngecr6sTzgA4DX7Is,5081
 customer_retention/analysis/visualization/__init__.py,sha256=5dVikBgzwJuQZ-W0vN5uMB1lLjVmvJbEhROQw9_87PI,399
-customer_retention/analysis/visualization/chart_builder.py,sha256=xZgRjLDRbBYBPvLz0HOOUfyzydt4H6skv5d2Oe0pvPk,111788
+customer_retention/analysis/visualization/chart_builder.py,sha256=TmeTgMRChrsr4bFevToTBAsYqyy0e9Z5sNFQ37avC48,111799
 customer_retention/analysis/visualization/console.py,sha256=dl_nEo6rXXSRfSnYkkJ4CsvBcE-n3l4mH9MIIjtw8Yw,2853
 customer_retention/analysis/visualization/display.py,sha256=9px602M7GrllJYthHLthjpVYd0jiTTAyY5WK69dd4s0,6625
 customer_retention/analysis/visualization/number_formatter.py,sha256=I1gUB0tEmfTQuDfOGYBZ3KRbq1rUd7ltR0vhDxFNRv8,1171
 customer_retention/artifacts/__init__.py,sha256=zTROqiS6zlkkuCZgR6YOB0Cvlsyr0TpRBYsOEorpDYw,118
 customer_retention/artifacts/fit_artifact_registry.py,sha256=aNfZC0Dgbc6jEwRR5keDEop9jo_tuL82hKO3ouCh5eY,5750
 customer_retention/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-customer_retention/core/compat/__init__.py,sha256=tD0XOABGAVQwuUaII8v1EKVJ149n1anp2dUzQkFkl-M,5382
+customer_retention/core/compat/__init__.py,sha256=dwamNiYIDzHEHpcmaphvR7wAwHslIqz6FoYjmQiR8Gg,7245
 customer_retention/core/compat/detection.py,sha256=6W_1LefgQriBtRY2PnvSCUGDt0X63oIUEEVjFqG3qH0,2492
 customer_retention/core/compat/ops.py,sha256=L-tAh4A3UEfRvePS6rAbhqb0QtZ_bN-TV7ZWpTkMFLA,1809
 customer_retention/core/compat/pandas_backend.py,sha256=14JPoYTW6X-a3UwFaemhmPr8zi_GTdZnyitmqPQODR0,1839
@@ -107,7 +107,7 @@ customer_retention/generators/notebook_generator/stages/s01_ingestion.py,sha256=
 customer_retention/generators/notebook_generator/stages/s02_profiling.py,sha256=kpI-3FfTYpr29NBX24bYFXB03eq3cKSQBftCRr15qxY,3794
 customer_retention/generators/notebook_generator/stages/s03_cleaning.py,sha256=cNY9AEoZx2r1hNmz2cD4zy36bV855GKavcWSTjp1Hc4,8084
 customer_retention/generators/notebook_generator/stages/s04_transformation.py,sha256=pzZOnWUfGjtGKzaqGfkN-Dipef1KUfErbSejMJv8Eo0,7623
-customer_retention/generators/notebook_generator/stages/s05_feature_engineering.py,sha256=PVfVyA3Lc_DRXsxEf2eAeYtgfx9w8UJW0ImR8UjVpqA,5915
+customer_retention/generators/notebook_generator/stages/s05_feature_engineering.py,sha256=XksIe9u36SJyZzQxLv-v7rHEOp30PtwX-K-rpuk6iGc,5985
 customer_retention/generators/notebook_generator/stages/s06_feature_selection.py,sha256=FIPy6Dk6OI2LLo3vikq7i8EWkp_-kMbto1yN7Pgi7f4,4484
 customer_retention/generators/notebook_generator/stages/s07_model_training.py,sha256=yJ-FWSCamvAqjZrvxWaUAviWLPHHS4EQ2nrZMRbPey4,8076
 customer_retention/generators/notebook_generator/stages/s08_deployment.py,sha256=6IS1_9ZMvXBNMCTwGNZgSRU5Gh0kaats_CKJZ-z46wg,3556
@@ -124,11 +124,11 @@ customer_retention/generators/pipeline_generator/__init__.py,sha256=1SRNHmQGM-yY
 customer_retention/generators/pipeline_generator/findings_parser.py,sha256=YvlXmDPDXkNnCvScUDNycwkp1J2HXpbDUO43NiShAig,34527
 customer_retention/generators/pipeline_generator/generator.py,sha256=ZKLr34AM-XEswjoddJXciASUg2mL8jgsXjpQiaKy29M,6097
 customer_retention/generators/pipeline_generator/models.py,sha256=1vSUXzO1uZw194nPdDJ5vU3lZw35Am-UWQY0Ic9CvbE,4874
-customer_retention/generators/pipeline_generator/renderer.py,sha256=hHybbSplSQxhkt_5OcJ8NTXkQppO2VM7lylNOzz3ZAU,81770
+customer_retention/generators/pipeline_generator/renderer.py,sha256=bvGTU_AkRgFSa0_xiMJawuOg7EswP8GcErVBR661TYM,81872
 customer_retention/generators/spec_generator/__init__.py,sha256=vojlxKgLGnLHH9DNolB8mgL0_FsIfSSLmuHPXyr8bYY,782
 customer_retention/generators/spec_generator/databricks_generator.py,sha256=o_qAik7mXuwzC9c7xUTkno5GHUmfHz5F2dIWqTcaDzw,15416
 customer_retention/generators/spec_generator/generic_generator.py,sha256=I_glnOOsXDbL_v_ffxkeKwSYm5MCEB5qF9WAAZ8Woho,13962
-customer_retention/generators/spec_generator/mlflow_pipeline_generator.py,sha256=B6uE4YeSWQAMo-d08qsBkicrlTf-S6AIfL9SAKa87vY,27533
+customer_retention/generators/spec_generator/mlflow_pipeline_generator.py,sha256=8-iUBgGThRJM5EmfJUwEoy8hJGZb7dZfuO6eh_QRH7A,27614
 customer_retention/generators/spec_generator/pipeline_spec.py,sha256=c8v1SWgTdeGmNs96l1hOS0qx1B1ua0iwPhw1I5w9OIo,10705
 customer_retention/integrations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 customer_retention/integrations/adapters/__init__.py,sha256=Fgdp0ESROTUHnOb2RN9Ubo0A4BdfoenOGuUz61lHz8g,583
@@ -187,7 +187,7 @@ customer_retention/stages/features/feature_engineer.py,sha256=btVsdLHRKYk6E5xI-9
 customer_retention/stages/features/feature_manifest.py,sha256=EEBG7kdU_jWNcnDqdLHONIaJ-n2GcqLkjXjIxo3zn9w,9731
 customer_retention/stages/features/feature_selector.py,sha256=_CG3ZKVuZuqrwV9YvYvlTnXf0ahhsZNLmSRhf4nwNiQ,10089
 customer_retention/stages/features/interaction_features.py,sha256=P7aaHALbFcfEchJsesVPhVmOm-v2VmYkG90t8p2tNVA,4634
-customer_retention/stages/features/temporal_features.py,sha256=0RghOQwWte7cGULbKAtMggX9pQGwYGU1f4lkl-Y_5ao,9283
+customer_retention/stages/features/temporal_features.py,sha256=KyXehl56Bt2tW7uP5uG_EJIgWIy8ee5qkjRSKxuJlhQ,9183
 customer_retention/stages/ingestion/__init__.py,sha256=kYVOe8kq7S0I_tjY-BcdZ1IsNWrYYjzDmoAcV2lhijQ,308
 customer_retention/stages/ingestion/load_result.py,sha256=sambVq085Lj1rAfIrbDA2BgPU3HsVVJJpgkVWojkpyc,860
 customer_retention/stages/ingestion/loaders.py,sha256=I0cgJo1XU47y_y7RKk6oELGVu1062qNP2GU5jJfgXVk,7705
@@ -216,7 +216,7 @@ customer_retention/stages/profiling/column_profiler.py,sha256=WZKwPxpDmCQiBJBHB-
 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
-customer_retention/stages/profiling/pattern_analysis_config.py,sha256=RRxrZqTA_Xue1zbO6W6-gpVa7EC0ZdP5M0XOtuSg4lQ,22499
+customer_retention/stages/profiling/pattern_analysis_config.py,sha256=TivC8fY3xNQ561VgHgaSloDVl7zSDOi-no8BSr5Favg,22575
 customer_retention/stages/profiling/profile_result.py,sha256=NKKh1u2FmfBqnIbOEiqBh25IZDMm91h38RT7wzA8yQI,6350
 customer_retention/stages/profiling/quality_checks.py,sha256=ov8opsY4AoM9D6Yr_fGXsVwXfpmO0OeFfhdML-xfoIM,65678
 customer_retention/stages/profiling/relationship_detector.py,sha256=9WMM8YOIl-EWPY2P3PFuOENM9D1nm5lU5sDfZTE_chQ,9477
@@ -228,16 +228,16 @@ customer_retention/stages/profiling/segment_aware_outlier.py,sha256=PS5GXnf_g3D9
 customer_retention/stages/profiling/target_level_analyzer.py,sha256=XPhdHqTdK9zzBDqy-JyrTi6NFf07wRwIGsVEOAiR_dE,10491
 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_analyzer.py,sha256=Gl8GLxPlDIzh-shUYrePYnjzYQUwsBB-sB4Voqf69O8,32364
 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_pattern_analyzer.py,sha256=-DBNhBfyEGhl0-rIgbpEGDJikyINDG55FP15JURKm_A,26814
+customer_retention/stages/profiling/temporal_quality_checks.py,sha256=SosW3omX2c025UIdlXpLEBJCsAsIvoGXMbxw6tzBocA,13750
 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=AGX7BJiKwCtzyPL4cWy3EmqS6CnDwr8PZCWCl_5ivmA,10410
-customer_retention/stages/profiling/time_window_aggregator.py,sha256=NcxVAor8JhDnPLap_iS3z81flejd7uPeTQLwLmQn7MA,15868
+customer_retention/stages/profiling/time_series_profiler.py,sha256=RRpaHrd6CXzat6HTdowIFxoZQyzqC3LlO9y-q_tsv2g,10315
+customer_retention/stages/profiling/time_window_aggregator.py,sha256=SD53z3Itz2F3ptfYHRmlW4d7IbrXvJoJbsPw0VOoUWI,15909
 customer_retention/stages/profiling/type_detector.py,sha256=VgYHWcBGepyJKNdY1FKgb9scOaosN6fDY_-WiTjfoAg,14726
 customer_retention/stages/profiling/window_recommendation.py,sha256=Apd_PDFpo49HJJzldTcwzzgJjBzEfd8mbGboBwHhzGw,13354
 customer_retention/stages/temporal/__init__.py,sha256=f86XiSUMKQgeTLyOsu89IJcafOPjdBIR9bH_hhrY8b8,6135
@@ -254,7 +254,7 @@ customer_retention/stages/temporal/timestamp_manager.py,sha256=EisQM4_e14wsdqVxz
 customer_retention/stages/transformation/__init__.py,sha256=6XQGYKYNqdOuxlX6IujtVqRZ099pS8X_ATd6mLqwVtQ,783
 customer_retention/stages/transformation/binary_handler.py,sha256=ObwL90YP3ivwOJONBikzZouUoBz-YCTcxWybfwA5ddc,3201
 customer_retention/stages/transformation/categorical_encoder.py,sha256=T0mLgJ6cf2kLkha4HclAeeaxlz7cVJBWYEsEt8fs5KA,10145
-customer_retention/stages/transformation/datetime_transformer.py,sha256=iWzxb7gdpn1uEPo96_ir9hDcqCERnVPhBLTTQyxq1xk,3619
+customer_retention/stages/transformation/datetime_transformer.py,sha256=60qQUizDS_h-i6BNOAzDoOJxC1T1OEJE3ZguSA3mimI,3716
 customer_retention/stages/transformation/numeric_transformer.py,sha256=wqC2aUfXargeOph8d9F4P2wLet4lnFOKoI9x1mpJucw,6367
 customer_retention/stages/transformation/pipeline.py,sha256=qqbpisjN4uZ050eishlEj037u2mPKEwxGG0o7GruoQM,11278
 customer_retention/stages/validation/__init__.py,sha256=8Klgpez2ApVM1n1HUWcaGjaa21-aC-ReaZIVj7zHFh4,2380
@@ -276,27 +276,27 @@ customer_retention/transforms/artifact_store.py,sha256=FYLpDcv2N6-dUTX5RPEIK3aCW
 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-0.75.1a2.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,,
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/00_start_here.ipynb,sha256=zCyhftEd3v9fc0Ta6wvA6b-9LcoGzRi8bS1tMZ3iu9w,21911
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/01_data_discovery.ipynb,sha256=up0X3oDJ5sAo1-tbqMyZj_f1h6D542G2uAxjVmtYCOI,46430
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/01a_a_temporal_text_deep_dive.ipynb,sha256=uai8T3iJSqOrabBQnVi8Z0k8zZGVgs_VVQWRHyXN8QU,33690
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/01a_temporal_deep_dive.ipynb,sha256=fC1ASNtvI8X1lAe-Lzcw3oX2cptDC-ymPeEtKKWhg20,67326
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/01b_temporal_quality.ipynb,sha256=RU5hxgrTVMZs1ytChVv1t49WpTO0Oj6B_Fu8g0xS0To,23039
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/01c_temporal_patterns.ipynb,sha256=ZGYfztP6JhOEwPmTYdC0l7w579fKXcNEJXq-PnCLc2I,153167
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/01d_event_aggregation.ipynb,sha256=-FT3SoBU0fhaZxGeTo-_UQl6riCrtoJaFnUg31opk64,63244
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/02_column_deep_dive.ipynb,sha256=mbP2LQWsXDyTsWg0bhrCBHEfHsEer_XOXRYV9f8JxAk,60250
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/02a_text_columns_deep_dive.ipynb,sha256=M9YN8yAjjuC6ZaUlc-rVqVLEkWd7Rc_GNILHS9qO3PU,29704
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/03_quality_assessment.ipynb,sha256=H49LLmn1PHbcbAvSQfteESRGk125QwkPI5qbLk3yZgc,68595
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/04_relationship_analysis.ipynb,sha256=Rr-B4-xg0ILuAIgztlZkiGJdTzLuNjOqBFxO8W4o9iU,78624
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/05_multi_dataset.ipynb,sha256=bBxkuZyTl1yZg4kMXO87WRjgZMhj_6hwLGX6m3XC270,62664
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/06_feature_opportunities.ipynb,sha256=cBJF5o4z3Z-dustQ4CVklnfTcQ8saG97tlgswWK9uWE,67409
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/07_modeling_readiness.ipynb,sha256=IiA04fyb-l097Glp3MtR03vPjQsZlS1Icg-hjEHa_Dg,28376
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/08_baseline_experiments.ipynb,sha256=KmjhnDf1JdpEiIcdfQ-ZFo_at6t9JRC30B6NmmvMBmg,34226
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/09_business_alignment.ipynb,sha256=tMNfGM7AH50N1ONzHhGW2HZLpQwraIxVzOiVnI-10X8,17214
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/10_spec_generation.ipynb,sha256=KeUdfL9Mvdi6023XpnfZ6oLEDNZaWiIHUfsAWig24mE,42847
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/11_scoring_validation.ipynb,sha256=5fi3eHMm03ZKZgdFAXMgydtZ3qX2TtR3L9bZS2MpWPE,49937
+churnkit-0.75.1a3.data/data/share/churnkit/exploration_notebooks/12_view_documentation.ipynb,sha256=aQF7CG8HxckqUKOKqnmZgMkSvfVzyO2LlYPrymLYjBY,4405
+churnkit-0.75.1a3.dist-info/METADATA,sha256=hYbCUfYKPP5jeW_YjZRN8j4M6msQHdApmOx7-KEJDmU,12736
+churnkit-0.75.1a3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+churnkit-0.75.1a3.dist-info/entry_points.txt,sha256=swQFVe-jjgQSBJQNO2Ulkz2F5odaE-TsnlTor3HQBjw,70
+churnkit-0.75.1a3.dist-info/licenses/LICENSE,sha256=Bud8Oj25tnpoIuXCWW0xcSfmGPeEZAAHrDRoKdSYtZY,11344
+churnkit-0.75.1a3.dist-info/RECORD,,

customer_retention/__init__.py

@@ -17,7 +17,7 @@ Main module categories:
                 llm_context, iteration)
 """
 
-__version__ = "0.75.1a2"
+__version__ = "0.75.1a3"
 
 # Environment utilities (always available)
 from .core.compat import (

customer_retention/analysis/visualization/chart_builder.py

@@ -5,7 +5,7 @@ import numpy as np
 import plotly.express as px
 import plotly.graph_objects as go
 
-from customer_retention.core.compat import DataFrame, Series, ensure_pandas_series, to_pandas
+from customer_retention.core.compat import DataFrame, Series, ensure_pandas_series, safe_to_datetime, to_pandas
 
 from .number_formatter import NumberFormatter
 
@@ -532,9 +532,8 @@ class ChartBuilder:
         dates: Series,
         title: Optional[str] = None,
     ) -> go.Figure:
-        import pandas as pd
         dates = ensure_pandas_series(dates)
-        parsed = pd.to_datetime(dates, errors="coerce").dropna()
+        parsed = safe_to_datetime(dates, errors="coerce").dropna()
 
         if len(parsed) == 0:
             fig = go.Figure()
@@ -1029,7 +1028,7 @@ class ChartBuilder:
         """
         import pandas as pd
         dates = ensure_pandas_series(dates)
-        parsed = pd.to_datetime(dates, errors="coerce")
+        parsed = safe_to_datetime(dates, errors="coerce")
 
         if values is not None:
             values = ensure_pandas_series(values)
@@ -1078,7 +1077,7 @@ class ChartBuilder:
         """Create a month x day-of-week heatmap for pattern discovery."""
         import pandas as pd
         dates = ensure_pandas_series(dates)
-        parsed = pd.to_datetime(dates, errors="coerce").dropna()
+        parsed = safe_to_datetime(dates, errors="coerce").dropna()
 
         if values is not None:
             values = ensure_pandas_series(values)
@@ -1127,7 +1126,7 @@ class ChartBuilder:
         dates = ensure_pandas_series(dates)
         values = ensure_pandas_series(values)
 
-        df = pd.DataFrame({"date": pd.to_datetime(dates), "value": values}).dropna()
+        df = pd.DataFrame({"date": safe_to_datetime(dates), "value": values}).dropna()
         df = df.sort_values("date")
 
         df["rolling_mean"] = df["value"].rolling(window=window, center=True, min_periods=1).mean()
@@ -2222,7 +2221,7 @@ class ChartBuilder:
         import pandas as pd
         with warnings.catch_warnings():
             warnings.simplefilter("ignore")
-            dates = pd.to_datetime(series, errors='coerce').dropna()
+            dates = safe_to_datetime(pd.Series(series), errors='coerce').dropna()
         if len(dates) == 0:
             return
 

customer_retention/core/compat/__init__.py

@@ -147,6 +147,54 @@ def is_float_dtype(arr_or_dtype: Any) -> bool:
     return _pandas.api.types.is_float_dtype(arr_or_dtype)
 
 
+def _infer_epoch_unit(value: int) -> str:
+    """Infer the epoch unit from a representative integer timestamp value.
+
+    Spark LongType timestamps become int64 after ``to_pandas()``.  The bare
+    ``pd.to_datetime()`` call assumes nanoseconds for large integers, which
+    silently produces wrong dates when the source used seconds or milliseconds.
+    This helper picks the right ``unit`` based on magnitude.
+    """
+    abs_val = abs(int(value))
+    if abs_val > 1e17:
+        return "ns"
+    if abs_val > 1e14:
+        return "us"
+    if abs_val > 1e11:
+        return "ms"
+    return "s"
+
+
+def safe_to_datetime(series: Any, **kwargs: Any) -> _pandas.Series:
+    """Convert a Series to datetime, handling Spark LongType epoch integers.
+
+    Like ``pd.to_datetime`` but automatically detects integer epoch columns
+    and passes the correct ``unit`` parameter.  Any extra *kwargs* are
+    forwarded to ``pd.to_datetime``.
+    """
+    series = ensure_pandas_series(series)
+    if _pandas.api.types.is_datetime64_any_dtype(series):
+        return series
+    if _pandas.api.types.is_integer_dtype(series):
+        non_null = series.dropna()
+        if len(non_null) > 0:
+            unit = _infer_epoch_unit(non_null.iloc[0])
+            return _pandas.to_datetime(series, unit=unit, **kwargs)
+    return _pandas.to_datetime(series, **kwargs)
+
+
+def ensure_datetime_column(df: _pandas.DataFrame, column: str) -> _pandas.DataFrame:
+    """Ensure *column* in a **pandas** DataFrame is ``datetime64``.
+
+    Call this after ``to_pandas()`` to safely convert columns that may have
+    arrived as int64 epoch values from Spark.  Returns the DataFrame
+    (modified in-place).
+    """
+    if not _pandas.api.types.is_datetime64_any_dtype(df[column]):
+        df[column] = safe_to_datetime(df[column])
+    return df
+
+
 class PandasCompat:
     @staticmethod
     def value_counts_normalize(series: Any, normalize: bool = False) -> Any:
@@ -208,6 +256,8 @@ __all__ = [
     "is_notebook",
     "get_display_function",
     "get_dbutils",
+    "safe_to_datetime",
+    "ensure_datetime_column",
     "ops",
     "DataOps",
 ]

customer_retention/generators/notebook_generator/stages/s05_feature_engineering.py

@@ -55,7 +55,8 @@ else:
 else:
     print("Warning: No feature_timestamp column found. Using current date (may cause leakage).")
     if "signup_date" in df.columns:
-        df["tenure_days"] = (pd.Timestamp.now() - pd.to_datetime(df["signup_date"])).dt.days'''),
+        from customer_retention.core.compat import safe_to_datetime
+        df["tenure_days"] = (pd.Timestamp.now() - safe_to_datetime(df["signup_date"])).dt.days'''),
             self.cb.section("Validate Point-in-Time Correctness"),
             self.cb.code('''if "feature_timestamp" in df.columns:
     pit_report = PointInTimeJoiner.validate_temporal_integrity(df)

customer_retention/generators/pipeline_generator/renderer.py

@@ -290,6 +290,7 @@ from pathlib import Path
 {% if ops %}
 from customer_retention.transforms import {{ ops | sort | join(', ') }}
 {% endif %}
+from customer_retention.core.compat import ensure_datetime_column, safe_to_datetime
 from config import SOURCES, get_bronze_path{{ ', RAW_SOURCES' if config.lifecycle else '' }}
 
 SOURCE_NAME = "{{ source }}"
@@ -356,7 +357,7 @@ def _load_raw_events():
 {% if config.lifecycle.include_recency_bucket %}
 
 def add_recency_tenure(df: pd.DataFrame, raw_df: pd.DataFrame) -> pd.DataFrame:
-    raw_df[TIME_COLUMN] = pd.to_datetime(raw_df[TIME_COLUMN])
+    ensure_datetime_column(raw_df, TIME_COLUMN)
     reference_date = raw_df[TIME_COLUMN].max()
     entity_stats = raw_df.groupby(ENTITY_COLUMN)[TIME_COLUMN].agg(["min", "max"])
     entity_stats["days_since_last"] = (reference_date - entity_stats["max"]).dt.days
@@ -398,7 +399,7 @@ def add_lifecycle_quadrant(df: pd.DataFrame) -> pd.DataFrame:
 {% if config.lifecycle.include_cyclical_features %}
 
 def add_cyclical_features(df: pd.DataFrame, raw_df: pd.DataFrame) -> pd.DataFrame:
-    raw_df[TIME_COLUMN] = pd.to_datetime(raw_df[TIME_COLUMN])
+    ensure_datetime_column(raw_df, TIME_COLUMN)
     mean_dow = raw_df.groupby(ENTITY_COLUMN)[TIME_COLUMN].apply(lambda x: x.dt.dayofweek.mean())
     df = df.merge(mean_dow.rename("mean_dow"), left_on=ENTITY_COLUMN, right_index=True, how="left")
     df["dow_sin"] = np.sin(2 * np.pi * df["mean_dow"] / 7)
@@ -1447,6 +1448,7 @@ from pathlib import Path
 {% if ops %}
 from customer_retention.transforms import {{ ops | sort | join(', ') }}
 {% endif %}
+from customer_retention.core.compat import ensure_datetime_column, safe_to_datetime
 from config import PRODUCTION_DIR, RAW_SOURCES, TARGET_COLUMN
 
 SOURCE_NAME = "{{ source }}"
@@ -1502,7 +1504,7 @@ AGG_FUNCS = {{ config.aggregation.agg_funcs }}
 
 def apply_reshaping(df: pd.DataFrame) -> pd.DataFrame:
 {% if config.aggregation %}
-    df[TIME_COLUMN] = pd.to_datetime(df[TIME_COLUMN])
+    ensure_datetime_column(df, TIME_COLUMN)
     reference_date = df[TIME_COLUMN].max()
     result = df.groupby(ENTITY_COLUMN).agg("first")[[]]
     if TARGET_COLUMN in df.columns:
@@ -1535,7 +1537,7 @@ def _load_raw_events():
 {% if config.lifecycle.include_recency_bucket %}
 
 def add_recency_tenure(df: pd.DataFrame, raw_df: pd.DataFrame) -> pd.DataFrame:
-    raw_df[TIME_COLUMN] = pd.to_datetime(raw_df[TIME_COLUMN])
+    ensure_datetime_column(raw_df, TIME_COLUMN)
     reference_date = raw_df[TIME_COLUMN].max()
     entity_stats = raw_df.groupby(ENTITY_COLUMN)[TIME_COLUMN].agg(["min", "max"])
     entity_stats["days_since_last"] = (reference_date - entity_stats["max"]).dt.days
@@ -1577,7 +1579,7 @@ def add_lifecycle_quadrant(df: pd.DataFrame) -> pd.DataFrame:
 {% if config.lifecycle.include_cyclical_features %}
 
 def add_cyclical_features(df: pd.DataFrame, raw_df: pd.DataFrame) -> pd.DataFrame:
-    raw_df[TIME_COLUMN] = pd.to_datetime(raw_df[TIME_COLUMN])
+    ensure_datetime_column(raw_df, TIME_COLUMN)
     mean_dow = raw_df.groupby(ENTITY_COLUMN)[TIME_COLUMN].apply(lambda x: x.dt.dayofweek.mean())
     df = df.merge(mean_dow.rename("mean_dow"), left_on=ENTITY_COLUMN, right_index=True, how="left")
     df["dow_sin"] = np.sin(2 * np.pi * df["mean_dow"] / 7)

customer_retention/generators/spec_generator/mlflow_pipeline_generator.py

@@ -395,6 +395,7 @@ def log_data_quality_metrics(df: pd.DataFrame, prefix: str = "data"):
         code_lines = [
             "def engineer_features(df: pd.DataFrame) -> pd.DataFrame:",
             '    """Engineer features based on exploration findings."""',
+            "    from customer_retention.core.compat import safe_to_datetime",
             "    df = df.copy()",
             "    new_features = []",
             "",
@@ -411,7 +412,7 @@ def log_data_quality_metrics(df: pd.DataFrame, prefix: str = "data"):
             code_lines.extend([
                 f"    # Datetime features from {col_name}",
                 f"    if '{col_name}' in df.columns:",
-                f"        df['{col_name}'] = pd.to_datetime(df['{col_name}'], errors='coerce')",
+                f"        df['{col_name}'] = safe_to_datetime(df['{col_name}'], errors='coerce')",
                 "",
             ])
 

customer_retention/stages/features/temporal_features.py

@@ -10,7 +10,7 @@ from dataclasses import dataclass, field
 from enum import Enum
 from typing import List, Optional, Union
 
-from customer_retention.core.compat import DataFrame, Series, Timedelta, Timestamp, pd
+from customer_retention.core.compat import DataFrame, Series, Timedelta, Timestamp, pd, safe_to_datetime, to_pandas
 
 
 class ReferenceDateSource(Enum):
@@ -122,19 +122,19 @@ class TemporalFeatureGenerator:
         if not self._is_fitted:
             raise ValueError("Generator not fitted. Call fit() first.")
 
-        result = df.copy()
+        result = to_pandas(df).copy()
         self.generated_features = []
         warnings_list = []
 
         # Get reference date(s) for this transform
         if self.reference_date_source in [ReferenceDateSource.COLUMN, ReferenceDateSource.FEATURE_TIMESTAMP]:
-            ref_dates = pd.to_datetime(df[self.reference_date_column], format='mixed')
+            ref_dates = safe_to_datetime(df[self.reference_date_column])
         else:
             ref_dates = self.reference_date
 
         # Tenure features
         if self.created_column and self.created_column in df.columns:
-            created = pd.to_datetime(df[self.created_column], format='mixed')
+            created = safe_to_datetime(df[self.created_column])
             tenure_days = self._compute_days_diff(ref_dates, created)
             result["tenure_days"] = tenure_days
             self.generated_features.append("tenure_days")
@@ -154,7 +154,7 @@ class TemporalFeatureGenerator:
 
         # Recency features
         if self.last_order_column and self.last_order_column in df.columns:
-            last_order = pd.to_datetime(df[self.last_order_column], format='mixed')
+            last_order = safe_to_datetime(df[self.last_order_column])
             days_since_last = self._compute_days_diff(ref_dates, last_order)
             result["days_since_last_order"] = days_since_last
             self.generated_features.append("days_since_last_order")
@@ -162,8 +162,8 @@ class TemporalFeatureGenerator:
         # Activation features
         if (self.first_order_column and self.first_order_column in df.columns and
                 self.created_column and self.created_column in df.columns):
-            created = pd.to_datetime(df[self.created_column], format='mixed')
-            first_order = pd.to_datetime(df[self.first_order_column], format='mixed')
+            created = safe_to_datetime(df[self.created_column])
+            first_order = safe_to_datetime(df[self.first_order_column])
             days_to_first = self._compute_days_diff(first_order, created)
             result["days_to_first_order"] = days_to_first
             self.generated_features.append("days_to_first_order")
@@ -171,8 +171,8 @@ class TemporalFeatureGenerator:
         # Active period
         if (self.first_order_column and self.first_order_column in df.columns and
                 self.last_order_column and self.last_order_column in df.columns):
-            first_order = pd.to_datetime(df[self.first_order_column], format='mixed')
-            last_order = pd.to_datetime(df[self.last_order_column], format='mixed')
+            first_order = safe_to_datetime(df[self.first_order_column])
+            last_order = safe_to_datetime(df[self.last_order_column])
             active_period = self._compute_days_diff(last_order, first_order)
             result["active_period_days"] = active_period
             self.generated_features.append("active_period_days")
@@ -210,21 +210,21 @@ class TemporalFeatureGenerator:
                 raise ValueError(
                     "date_column must be provided when source is MAX_DATE"
                 )
-            self.reference_date = pd.to_datetime(df[self.date_column], format='mixed').max()
+            self.reference_date = safe_to_datetime(df[self.date_column]).max()
 
         elif self.reference_date_source == ReferenceDateSource.COLUMN:
             if self.reference_date_column is None:
                 raise ValueError(
                     "reference_date_column must be provided when source is COLUMN"
                 )
-            self.reference_date = pd.to_datetime(df[self.reference_date_column], format='mixed')
+            self.reference_date = safe_to_datetime(df[self.reference_date_column])
 
         elif self.reference_date_source == ReferenceDateSource.FEATURE_TIMESTAMP:
             if "feature_timestamp" not in df.columns:
                 raise ValueError(
                     "feature_timestamp column required when source is FEATURE_TIMESTAMP"
                 )
-            self.reference_date = pd.to_datetime(df["feature_timestamp"], format='mixed')
+            self.reference_date = safe_to_datetime(df["feature_timestamp"])
             self.reference_date_column = "feature_timestamp"
 
     def _compute_days_diff(

customer_retention/stages/profiling/pattern_analysis_config.py

@@ -4,7 +4,7 @@ from typing import Any, Dict, List, Optional, Tuple
 import numpy as np
 import pandas as pd
 
-from customer_retention.core.compat import DataFrame
+from customer_retention.core.compat import DataFrame, ensure_datetime_column, to_pandas
 
 
 @dataclass
@@ -216,12 +216,13 @@ class SparklineDataBuilder:
         self.freq = freq
 
     def build(self, df: DataFrame, columns: List[str]) -> Tuple[List[SparklineData], bool]:
-        import pandas as pd
+        df = to_pandas(df)
         has_target = self.target_column is not None and self.target_column in df.columns
         if has_target:
             validate_not_event_level(df, self.entity_column, self.target_column)
         df_work = self._prepare_working_df(df, has_target)
-        df_work['_period'] = pd.to_datetime(df_work[self.time_column]).dt.to_period(self.freq).dt.start_time
+        ensure_datetime_column(df_work, self.time_column)
+        df_work['_period'] = df_work[self.time_column].dt.to_period(self.freq).dt.start_time
         results = [self._build_sparkline_for_column(df_work, col, has_target)
                    for col in columns if col in df_work.columns]
         return results, has_target

customer_retention/stages/profiling/temporal_feature_analyzer.py

@@ -5,7 +5,7 @@ from typing import Any, Dict, List, Optional, Tuple
 import numpy as np
 from scipy import stats
 
-from customer_retention.core.compat import DataFrame, pd, qcut, to_datetime
+from customer_retention.core.compat import DataFrame, ensure_datetime_column, pd, qcut, to_pandas
 from customer_retention.core.utils import compute_effect_size
 
 
@@ -626,8 +626,8 @@ class TemporalFeatureAnalyzer:
         return next_priority
 
     def _prepare_dataframe(self, df: DataFrame) -> DataFrame:
-        df = df.copy()
-        df[self.time_column] = to_datetime(df[self.time_column])
+        df = to_pandas(df).copy()
+        ensure_datetime_column(df, self.time_column)
         return df
 
     def _validate_event_level_target_usage(self, df: DataFrame, target_column: Optional[str]) -> None:

customer_retention/stages/profiling/temporal_pattern_analyzer.py

@@ -5,7 +5,15 @@ 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, to_pandas
+from customer_retention.core.compat import (
+    DataFrame,
+    Timestamp,
+    cut,
+    ensure_datetime_column,
+    pd,
+    safe_to_datetime,
+    to_pandas,
+)
 from customer_retention.core.utils import compute_effect_size
 
 
@@ -177,6 +185,8 @@ def generate_trend_recommendations(trend: TrendResult, mean_value: float = 1.0)
 
 
 def analyze_cohort_distribution(first_events: DataFrame, time_column: str) -> CohortDistribution:
+    first_events = to_pandas(first_events)
+    ensure_datetime_column(first_events, time_column)
     years = first_events[time_column].dt.year
     year_counts = years.value_counts().sort_index().to_dict()
     total = len(first_events)
@@ -232,6 +242,7 @@ def compute_recency_buckets(
     reference_date: Timestamp, bucket_edges: Optional[List[float]] = None
 ) -> List[RecencyBucketStats]:
     df = to_pandas(df)
+    ensure_datetime_column(df, time_column)
     edges = bucket_edges or DEFAULT_BUCKET_EDGES
     labels = _generate_bucket_labels(edges)
     entity_last = df.groupby(entity_column)[time_column].max().reset_index()
@@ -298,6 +309,7 @@ def _diagnose_anomaly_pattern(
     df: DataFrame, entity_column: str, time_column: str, target_column: str
 ) -> AnomalyDiagnostics:
     df = to_pandas(df)
+    ensure_datetime_column(df, time_column)
     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
@@ -436,6 +448,7 @@ def compare_recency_by_target(
     df = to_pandas(df)
     if target_column not in df.columns:
         return None
+    ensure_datetime_column(df, time_column)
     ref_date = reference_date or df[time_column].max()
     entity_last = df.groupby(entity_column)[time_column].max().reset_index()
     entity_last["recency_days"] = (ref_date - entity_last[time_column]).dt.days
@@ -502,7 +515,7 @@ class TemporalPatternAnalyzer:
         if len(df_clean) < 3:
             return self._unknown_trend()
 
-        time_col = to_datetime(df_clean[self.time_column])
+        time_col = safe_to_datetime(df_clean[self.time_column])
         x = (time_col - time_col.min()).dt.total_seconds() / 86400
         y = df_clean[value_column].values
 
@@ -587,9 +600,10 @@ class TemporalPatternAnalyzer:
             return pd.DataFrame()
 
         df_copy = to_pandas(df).copy()
+        ensure_datetime_column(df_copy, cohort_column)
         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)
+        df_copy["_cohort"] = df_copy["_cohort"].dt.to_period(period)
 
         entity_cohorts = df_copy.groupby(entity_column)["_cohort"].first().reset_index()
         entity_cohorts.columns = [entity_column, "_cohort"]
@@ -615,11 +629,10 @@ class TemporalPatternAnalyzer:
             return RecencyResult(avg_recency_days=0, median_recency_days=0, min_recency_days=0, max_recency_days=0)
 
         df = to_pandas(df)
+        ensure_datetime_column(df, self.time_column)
         ref_date = reference_date or Timestamp.now()
-        to_datetime(df[self.time_column])
 
         entity_last = df.groupby(entity_column)[self.time_column].max()
-        entity_last = to_datetime(entity_last)
         recency_days = (ref_date - entity_last).dt.days
 
         target_correlation = None

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, to_pandas
+from customer_retention.core.compat import DataFrame, Timestamp, ensure_datetime_column, safe_to_datetime, to_pandas
 from customer_retention.core.components.enums import Severity
 
 
@@ -38,6 +38,7 @@ class DuplicateEventCheck(TemporalQualityCheck):
         self.time_column = time_column
 
     def run(self, df: DataFrame) -> TemporalQualityResult:
+        df = to_pandas(df)
         if len(df) == 0:
             return self._pass_result("No data to check")
 
@@ -70,11 +71,12 @@ class TemporalGapCheck(TemporalQualityCheck):
         self.max_gap_multiple = max_gap_multiple
 
     def run(self, df: DataFrame) -> TemporalQualityResult:
+        df = to_pandas(df)
         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])
+        ensure_datetime_column(df, self.time_column)
+        time_col = 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)
         threshold_days = expected_days * self.max_gap_multiple
@@ -108,10 +110,11 @@ class FutureDateCheck(TemporalQualityCheck):
         self.reference_date = reference_date or Timestamp.now()
 
     def run(self, df: DataFrame) -> TemporalQualityResult:
+        df = to_pandas(df)
         if len(df) == 0:
             return self._pass_result("No data to check")
 
-        time_col = to_datetime(df[self.time_column])
+        time_col = safe_to_datetime(df[self.time_column])
         future_mask = time_col > self.reference_date
         future_count = future_mask.sum()
 
@@ -138,10 +141,11 @@ class EventOrderCheck(TemporalQualityCheck):
         self.time_column = time_column
 
     def run(self, df: DataFrame) -> TemporalQualityResult:
+        df = to_pandas(df)
         if len(df) < 2:
             return self._pass_result("Insufficient data to check ordering")
 
-        df_check = df.assign(_parsed_time=to_datetime(df[self.time_column]))
+        df_check = df.assign(_parsed_time=safe_to_datetime(df[self.time_column]))
         collision_counts = df_check.groupby([self.entity_column, "_parsed_time"]).size()
         ambiguous = collision_counts[collision_counts > 1]
         ambiguous_count = ambiguous.sum() - len(ambiguous)

customer_retention/stages/profiling/time_series_profiler.py

@@ -6,9 +6,8 @@ import numpy as np
 from customer_retention.core.compat import (
     DataFrame,
     Timestamp,
-    is_datetime64_any_dtype,
+    ensure_datetime_column,
     pd,
-    to_datetime,
     to_pandas,
 )
 
@@ -196,11 +195,12 @@ 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()
@@ -231,8 +231,7 @@ 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:

customer_retention/stages/profiling/time_window_aggregator.py

@@ -10,9 +10,10 @@ from customer_retention.core.compat import (
     DataFrame,
     Timedelta,
     Timestamp,
+    ensure_datetime_column,
     is_numeric_dtype,
     pd,
-    to_datetime,
+    to_pandas,
 )
 
 
@@ -82,11 +83,12 @@ 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()
 
         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"])]
 

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')