churnkit 1.2.8a4__tar.gz → 1.2.8a6__tar.gz

{churnkit-1.2.8a4 → churnkit-1.2.8a6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: churnkit
-Version: 1.2.8a4
+Version: 1.2.8a6
 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-1.2.8a4 → churnkit-1.2.8a6}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "churnkit"
-version = "1.02.8a4"
+version = "1.02.8a6"
 description = "Structured ML framework for customer churn prediction -- from exploration notebooks to production pipelines, locally or on Databricks."
 readme = "README.md"
 license = {text = "Apache-2.0"}

{churnkit-1.2.8a4 → churnkit-1.2.8a6}/src/customer_retention/__init__.py

@@ -17,7 +17,7 @@ Main module categories:
                 llm_context, iteration)
 """
 
-__version__ = "1.02.8a4"
+__version__ = "1.02.8a6"
 
 # Environment utilities (always available)
 from .core.compat import (

{churnkit-1.2.8a4 → churnkit-1.2.8a6}/src/customer_retention/generators/pipeline_generator/databricks_renderer.py

@@ -39,11 +39,17 @@ def _impute_null(col, p):
 def _cap_outlier(col, p):
     lower = p.get("lower", 0)
     upper = p.get("upper", 1000000)
+    # Recommendations registered against exploration's silver-merged frame can
+    # target columns that don't exist in this stage's input (e.g. silver-derived
+    # `days_since_*`/`days_until_*` recency features mistakenly attributed to
+    # bronze). Guard the withColumn so the rec degrades to a no-op at runtime
+    # instead of failing the stage with UNRESOLVED_COLUMN.
     return (
-        f'df.withColumn("{col}", '
+        f'(df.withColumn("{col}", '
         f'F.when(F.col("{col}") < {lower}, {lower})'
         f'.when(F.col("{col}") > {upper}, {upper})'
-        f'.otherwise(F.col("{col}")))'
+        f'.otherwise(F.col("{col}"))) '
+        f'if "{col}" in df.columns else df)'
     )
 
 
@@ -54,20 +60,28 @@ def _drop_column(col, _p):
 def _winsorize(col, p):
     lower = p.get("lower_bound", 0)
     upper = p.get("upper_bound", 1000000)
+    # See `_cap_outlier` — same column-existence guard.
     return (
-        f'df.withColumn("{col}", '
+        f'(df.withColumn("{col}", '
         f'F.when(F.col("{col}") < {lower}, {lower})'
         f'.when(F.col("{col}") > {upper}, {upper})'
-        f'.otherwise(F.col("{col}")))'
+        f'.otherwise(F.col("{col}"))) '
+        f'if "{col}" in df.columns else df)'
     )
 
 
 def _log_transform(col, _p):
-    return f'df.withColumn("{col}", F.log1p(F.col("{col}")))'
+    return (
+        f'(df.withColumn("{col}", F.log1p(F.col("{col}"))) '
+        f'if "{col}" in df.columns else df)'
+    )
 
 
 def _sqrt_transform(col, _p):
-    return f'df.withColumn("{col}", F.sqrt(F.abs(F.col("{col}"))))'
+    return (
+        f'(df.withColumn("{col}", F.sqrt(F.abs(F.col("{col}")))) '
+        f'if "{col}" in df.columns else df)'
+    )
 
 
 def _encode_one_hot(col, _p):

{churnkit-1.2.8a4 → churnkit-1.2.8a6}/src/customer_retention/generators/pipeline_generator/findings_parser.py

@@ -1266,10 +1266,32 @@ class FindingsParser:
         replay the same logic at runtime via the existing template branches
         (`databricks_landing.py.j2` `config.lifecycle_enrichments` /
         `config.filters`).
+
+        Idempotency: when a dataset already carries a step of the same kind
+        from the recommendations registry (post-NB00-migration), the override
+        is skipped instead of double-appended. Without this, the generated
+        landing notebook runs `enrich_lifecycle_dataset(...)` twice and the
+        second call crashes with UNRESOLVED_COLUMN because the first already
+        renamed the lifecycle's `valid_from_column`.
         """
+        already_filter = {
+            ds for ds, lc in (config.landing or {}).items()
+            if getattr(lc, "filters", None)
+        }
+        already_lifecycle = {
+            ds for ds, lc in (config.landing or {}).items()
+            if getattr(lc, "lifecycle_enrichments", None)
+        }
         for dataset, predicate in self._landing_filter_overrides.items():
             if not predicate:
                 continue
+            if dataset in already_filter:
+                logger.warning(
+                    "landing_filter_overrides: dataset %r already has registry-driven "
+                    "filter step(s); skipping operator override to avoid double-apply.",
+                    dataset,
+                )
+                continue
             target = config.landing.get(dataset)
             if target is None:
                 logger.warning(
@@ -1287,6 +1309,13 @@ class FindingsParser:
         for dataset, lifecycle_cfg in self._landing_lifecycle_overrides.items():
             if not lifecycle_cfg:
                 continue
+            if dataset in already_lifecycle:
+                logger.warning(
+                    "landing_lifecycle_overrides: dataset %r already has registry-driven "
+                    "lifecycle step(s); skipping operator override to avoid double-apply.",
+                    dataset,
+                )
+                continue
             target = config.landing.get(dataset)
             if target is None:
                 logger.warning(
@@ -1403,11 +1432,18 @@ class FindingsParser:
                 if name in config.landing:
                     siblings.append(name)
                     seen.add(name)
+            # Translate Python-list `in [a, b]` into Spark-SQL `in (a, b)`
+            # — exploration's filter executor goes through
+            # `_spark_safe_query_expr`, but production's generated landing
+            # script feeds the predicate straight into Spark SQL via
+            # `df.filter(...)` and rejects bracket lists with PARSE_SYNTAX_ERROR.
+            from customer_retention.core.compat import _spark_safe_query_expr
+            sql_predicate = _spark_safe_query_expr(str(predicate))
             target.filters.append(TransformationStep(
                 type=PipelineTransformationType.LANDING_FILTER,
                 column=dataset,
                 parameters={
-                    "predicate": str(predicate),
+                    "predicate": sql_predicate,
                     "sibling_views": list(siblings),
                 },
                 rationale="NB00 SAMPLE_FILTER_COLUMNS (cohort scope)",