churnkit 0.76.1a1__py3-none-any.whl → 0.76.1a2__py3-none-any.whl

{churnkit-0.76.1a1.dist-info → churnkit-0.76.1a2.dist-info}/RECORD

@@ -1,13 +1,13 @@
-customer_retention/__init__.py,sha256=fNqb1iL6Q95kXsIVQBbVJtV_NmNSWBtgbGZxRy7vuYM,1406
+customer_retention/__init__.py,sha256=WoYIyGA62vbXjZNwi_JHtf4CH4bwc7jFm8fTryQFLzE,1406
 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=Tm98ihaFQMXRAlEHTH89T23gLNZardzrCMC4svcoAUw,2463
+customer_retention/analysis/notebook_progress.py,sha256=ojzkeL0m8JmB0_xfIhfijbrKG_SKRRc2Kk69vqxLehQ,2511
 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
-customer_retention/analysis/auto_explorer/explorer.py,sha256=IFJ3K2TtTukB8ppn-wJ6JFMq8V3ZTLu9au5AZqjvtFM,13286
+customer_retention/analysis/auto_explorer/explorer.py,sha256=bPz8iUZDZl3Bb6-RDpGIEqxWIMvZqwx-VV1tvugNaWY,13306
 customer_retention/analysis/auto_explorer/findings.py,sha256=frry7huqfDuP0VwE0AOn4zPr0TPiUYN8ESqanUYxRA4,11420
 customer_retention/analysis/auto_explorer/layered_recommendations.py,sha256=NcCzh92uI27ATze1_XAEcS1vzP8uu2bld8N6RYBWRTM,24392
 customer_retention/analysis/auto_explorer/recommendation_builder.py,sha256=7edPcLjpeOw1BiRO0J7M1DpdEdfAJrjVEfAe-v2IpYw,6225
@@ -63,7 +63,7 @@ customer_retention/analysis/visualization/number_formatter.py,sha256=I1gUB0tEmfT
 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=mriOzKG3GTe_fNvnES39BuEzgBcYO2Qa0RcqgcTVpec,7283
+customer_retention/core/compat/__init__.py,sha256=H1unnElzwg9TMdJycKFHsOTc2CQr9SZTdbxVLUfjCcc,7612
 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
@@ -131,7 +131,7 @@ customer_retention/generators/spec_generator/generic_generator.py,sha256=I_glnOO
 customer_retention/generators/spec_generator/mlflow_pipeline_generator.py,sha256=LME87sjzP_MjOMA3NTxqRfOhCroUJAb40BAnSH4-I74,29866
 customer_retention/generators/spec_generator/pipeline_spec.py,sha256=c8v1SWgTdeGmNs96l1hOS0qx1B1ua0iwPhw1I5w9OIo,10705
 customer_retention/integrations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-customer_retention/integrations/databricks_init.py,sha256=xQgCBhzx0DoGGGeocYX9Iu3H2dEl--bvA36T7_uF6TM,6526
+customer_retention/integrations/databricks_init.py,sha256=kHlj1mTo5hB95zrwQdBFM6yktlKUFsK-AUjqSHec4n4,6923
 customer_retention/integrations/adapters/__init__.py,sha256=Fgdp0ESROTUHnOb2RN9Ubo0A4BdfoenOGuUz61lHz8g,583
 customer_retention/integrations/adapters/base.py,sha256=z6dVAowDKGogKsYGR7VMcLkS6VhcB9h4zgN1tilNYRg,254
 customer_retention/integrations/adapters/factory.py,sha256=CMsqOeDozADbWnk8fzktZvAyL1FEmUjDMvfDCpLDVaU,1202
@@ -213,7 +213,7 @@ 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=WZKwPxpDmCQiBJBHB-y50Nwfd-m78XEDmhV0YtCDSok,20382
+customer_retention/stages/profiling/column_profiler.py,sha256=tY8eQ0DQwVMmctDC4kNbbreXNdhRSPtVV8V1nz3fycY,20437
 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
@@ -277,27 +277,27 @@ 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-0.76.1a1.data/data/share/churnkit/exploration_notebooks/00_start_here.ipynb,sha256=zCyhftEd3v9fc0Ta6wvA6b-9LcoGzRi8bS1tMZ3iu9w,21911
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/01_data_discovery.ipynb,sha256=EDhWyKM2stHtWg2bS8HdRMItZ6WtokWRyZ90_MjTPFQ,46500
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/01a_a_temporal_text_deep_dive.ipynb,sha256=uai8T3iJSqOrabBQnVi8Z0k8zZGVgs_VVQWRHyXN8QU,33690
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/01a_temporal_deep_dive.ipynb,sha256=fC1ASNtvI8X1lAe-Lzcw3oX2cptDC-ymPeEtKKWhg20,67326
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/01b_temporal_quality.ipynb,sha256=RU5hxgrTVMZs1ytChVv1t49WpTO0Oj6B_Fu8g0xS0To,23039
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/01c_temporal_patterns.ipynb,sha256=ZGYfztP6JhOEwPmTYdC0l7w579fKXcNEJXq-PnCLc2I,153167
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/01d_event_aggregation.ipynb,sha256=-FT3SoBU0fhaZxGeTo-_UQl6riCrtoJaFnUg31opk64,63244
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/02_column_deep_dive.ipynb,sha256=mbP2LQWsXDyTsWg0bhrCBHEfHsEer_XOXRYV9f8JxAk,60250
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/02a_text_columns_deep_dive.ipynb,sha256=M9YN8yAjjuC6ZaUlc-rVqVLEkWd7Rc_GNILHS9qO3PU,29704
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/03_quality_assessment.ipynb,sha256=H49LLmn1PHbcbAvSQfteESRGk125QwkPI5qbLk3yZgc,68595
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/04_relationship_analysis.ipynb,sha256=Rr-B4-xg0ILuAIgztlZkiGJdTzLuNjOqBFxO8W4o9iU,78624
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/05_multi_dataset.ipynb,sha256=bBxkuZyTl1yZg4kMXO87WRjgZMhj_6hwLGX6m3XC270,62664
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/06_feature_opportunities.ipynb,sha256=cBJF5o4z3Z-dustQ4CVklnfTcQ8saG97tlgswWK9uWE,67409
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/07_modeling_readiness.ipynb,sha256=IiA04fyb-l097Glp3MtR03vPjQsZlS1Icg-hjEHa_Dg,28376
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/08_baseline_experiments.ipynb,sha256=KmjhnDf1JdpEiIcdfQ-ZFo_at6t9JRC30B6NmmvMBmg,34226
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/09_business_alignment.ipynb,sha256=tMNfGM7AH50N1ONzHhGW2HZLpQwraIxVzOiVnI-10X8,17214
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/10_spec_generation.ipynb,sha256=KeUdfL9Mvdi6023XpnfZ6oLEDNZaWiIHUfsAWig24mE,42847
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/11_scoring_validation.ipynb,sha256=5fi3eHMm03ZKZgdFAXMgydtZ3qX2TtR3L9bZS2MpWPE,49937
-churnkit-0.76.1a1.data/data/share/churnkit/exploration_notebooks/12_view_documentation.ipynb,sha256=aQF7CG8HxckqUKOKqnmZgMkSvfVzyO2LlYPrymLYjBY,4405
-churnkit-0.76.1a1.dist-info/METADATA,sha256=CkjX1u5qlqFbTuNbtFC93u25moHVAf2TaxYJwFAMWZY,13005
-churnkit-0.76.1a1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-churnkit-0.76.1a1.dist-info/entry_points.txt,sha256=swQFVe-jjgQSBJQNO2Ulkz2F5odaE-TsnlTor3HQBjw,70
-churnkit-0.76.1a1.dist-info/licenses/LICENSE,sha256=Bud8Oj25tnpoIuXCWW0xcSfmGPeEZAAHrDRoKdSYtZY,11344
-churnkit-0.76.1a1.dist-info/RECORD,,
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/00_start_here.ipynb,sha256=FBfETZrERR885XQYGAYvwRDrffebfqLfhk_m9Lq8yjw,21927
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/01_data_discovery.ipynb,sha256=OwoSunIqy8E47xwjtmqQXst2e8rUj0dhsG-RAEAwggc,46459
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/01a_a_temporal_text_deep_dive.ipynb,sha256=Y4b2Fy2i9SO0cdTD5c9mFkVoScLfXNPdd9vFG2dLYTM,33396
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/01a_temporal_deep_dive.ipynb,sha256=cRyVDtDKhunz_CQP7e44SPxOcqIuntIrtt6dkdCNWOw,67114
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/01b_temporal_quality.ipynb,sha256=lxk2GrrpaemSgDg2u1Kr5buuJ37X3ZGo49vrgFtXuNc,22824
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/01c_temporal_patterns.ipynb,sha256=QI7ItAGNU20mRW9s0iCpUNdWkdXVIhZGMbZ6I8HXdHs,151565
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/01d_event_aggregation.ipynb,sha256=P0uCz8RkfGOutoXwZ5OyObHUKxaa78gYQfxwk7j9zSY,62919
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/02_column_deep_dive.ipynb,sha256=Eg1Zf2kMfKO3cZvcdy0AWH-3tgJJ228TVoy9wUEj82o,59793
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/02a_text_columns_deep_dive.ipynb,sha256=_uH1J-6djvBrJetEF4iVlLsB5N6uMRa3sk-Faf3izoo,29441
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/03_quality_assessment.ipynb,sha256=5wxPf3S-yhE19ViYu6_slAjzTaZ2oMbS9Uenj4TaB9U,68069
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/04_relationship_analysis.ipynb,sha256=iYbe9jfB_EbcisEmb2iUmKA2wYeC__nEuPZ-qAO5bV8,77948
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/05_multi_dataset.ipynb,sha256=G667NbSvjvPDCJq9n1RkrOa2yTBdkLsvWEyUhaXFep8,61927
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/06_feature_opportunities.ipynb,sha256=ZriCpdO_BFBfnxkp2zGWRRfeyZqI57yff5lhyh8l0W0,67027
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/07_modeling_readiness.ipynb,sha256=Mnk9O79SxHWt6UK0sn3auENW5MGVoozAY9ymxbbgdbU,28098
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/08_baseline_experiments.ipynb,sha256=9JA6kZ7DCe7Dk5YU2GXTPR6sbOJbVbBr4lBm7qVJQRA,33993
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/09_business_alignment.ipynb,sha256=uA-WyKnplytnb1rjrph5CPenA2WQ1l48Ix7qnT3DVSY,17013
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/10_spec_generation.ipynb,sha256=lGxwOpmpuTIRhihtnkkMWV0iS1hclCANRGrwLOksaEY,42453
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/11_scoring_validation.ipynb,sha256=PF8RuENHLyyHVUwFSqFoQ0VyEuzV2LSt_jclKCCCddk,49877
+churnkit-0.76.1a2.data/data/share/churnkit/exploration_notebooks/12_view_documentation.ipynb,sha256=VaijwVQeiMpXP0SaEb7P_e_6V-FG9Ww9yGGaXvPZPJ0,4425
+churnkit-0.76.1a2.dist-info/METADATA,sha256=Zj44SOAqqfJn01_4NId1QLm6XENcCBBrIf80MAdG9dM,13005
+churnkit-0.76.1a2.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+churnkit-0.76.1a2.dist-info/entry_points.txt,sha256=swQFVe-jjgQSBJQNO2Ulkz2F5odaE-TsnlTor3HQBjw,70
+churnkit-0.76.1a2.dist-info/licenses/LICENSE,sha256=Bud8Oj25tnpoIuXCWW0xcSfmGPeEZAAHrDRoKdSYtZY,11344
+churnkit-0.76.1a2.dist-info/RECORD,,

customer_retention/__init__.py

@@ -17,7 +17,7 @@ Main module categories:
                 llm_context, iteration)
 """
 
-__version__ = "0.76.1a1"
+__version__ = "0.76.1a2"
 
 # Environment utilities (always available)
 from .core.compat import (

customer_retention/analysis/auto_explorer/explorer.py

@@ -2,7 +2,7 @@ import hashlib
 from pathlib import Path
 from typing import List, Optional, Union
 
-from customer_retention.core.compat import DataFrame, Series, pd, to_pandas
+from customer_retention.core.compat import DataFrame, Series, pd, safe_memory_usage_bytes, to_pandas
 from customer_retention.core.config.column_config import ColumnType
 from customer_retention.stages.profiling import ProfilerFactory, TypeDetector
 from customer_retention.stages.temporal import TEMPORAL_METADATA_COLS
@@ -53,7 +53,7 @@ class DataExplorer:
             source_format=source_format,
             row_count=len(df),
             column_count=len(df.columns),
-            memory_usage_mb=df.memory_usage(deep=True).sum() / (1024 * 1024)
+            memory_usage_mb=safe_memory_usage_bytes(df) / (1024 * 1024)
         )
 
     def _explore_all_columns(self, df: DataFrame, findings: ExplorationFindings, target_hint: Optional[str]):

customer_retention/analysis/notebook_progress.py

@@ -27,7 +27,10 @@ def track_and_export_previous(current_notebook: str) -> None:
     Returns ``None`` — the export runs asynchronously.
     """
     experiments_dir = get_notebook_experiments_dir()
-    experiments_dir.mkdir(parents=True, exist_ok=True)
+    try:
+        experiments_dir.mkdir(parents=True, exist_ok=True)
+    except OSError:
+        return
     progress_file = experiments_dir / "notebook_progress.json"
     docs_dir = experiments_dir / "docs"
 

customer_retention/core/compat/__init__.py

@@ -167,6 +167,15 @@ def _infer_epoch_unit(value: int) -> str:
     return "s"
 
 
+def safe_memory_usage_bytes(obj: Any) -> int:
+    """Return memory usage in bytes, returning 0 when unsupported (e.g. PySpark)."""
+    try:
+        usage = obj.memory_usage(deep=True)
+        return int(usage.sum()) if hasattr(usage, 'sum') else int(usage)
+    except Exception:
+        return 0
+
+
 def safe_to_datetime(series: Any, **kwargs: Any) -> _pandas.Series:
     """Convert a Series to datetime, handling Spark LongType epoch integers.
 
@@ -259,6 +268,7 @@ __all__ = [
     "is_notebook",
     "get_display_function",
     "get_dbutils",
+    "safe_memory_usage_bytes",
     "safe_to_datetime",
     "ensure_datetime_column",
     "ops",

customer_retention/integrations/databricks_init.py

@@ -47,6 +47,7 @@ def databricks_init(
     resolved_experiment_name = _make_absolute_experiment_path(resolved_experiment_name, workspace_path)
     _set_experiment_name_env_var(resolved_experiment_name)
     _reload_config_constants()
+    _ensure_experiments_volume_exists(catalog, schema)
     _setup_experiment_directories()
     _configure_mlflow_experiment(resolved_experiment_name)
     notebooks_copied: list[str] = []
@@ -96,6 +97,18 @@ def _reload_config_constants() -> None:
     reload_config()
 
 
+def _ensure_experiments_volume_exists(catalog: str, schema: str) -> None:
+    from customer_retention.core.compat.detection import get_spark_session
+
+    spark = get_spark_session()
+    if not spark:
+        return
+    try:
+        spark.sql(f"CREATE VOLUME IF NOT EXISTS {catalog}.{schema}.experiments")
+    except Exception:
+        pass
+
+
 def _setup_experiment_directories() -> None:
     from customer_retention.core.config.experiments import setup_experiments_structure
 

customer_retention/stages/profiling/column_profiler.py

@@ -4,7 +4,14 @@ from typing import Optional
 
 import numpy as np
 
-from customer_retention.core.compat import Timestamp, is_bool_dtype, is_datetime64_any_dtype, pd, to_datetime
+from customer_retention.core.compat import (
+    Timestamp,
+    is_bool_dtype,
+    is_datetime64_any_dtype,
+    pd,
+    safe_memory_usage_bytes,
+    to_datetime,
+)
 from customer_retention.core.config.column_config import ColumnType
 
 from .profile_result import (
@@ -31,7 +38,7 @@ class ColumnProfiler(ABC):
         most_common_value = value_counts.index[0] if len(value_counts) > 0 else None
         most_common_frequency = int(value_counts.iloc[0]) if len(value_counts) > 0 else None
 
-        memory_size = series.memory_usage(deep=True)
+        memory_size = safe_memory_usage_bytes(series)
 
         return UniversalMetrics(
             total_count=total_count,