batch-analytics 0.3.28__tar.gz → 0.3.30__tar.gz

{batch_analytics-0.3.28 → batch_analytics-0.3.30}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: batch-analytics
-Version: 0.3.28
+Version: 0.3.30
 Summary: PySpark batch analytics: Extract, Transform, Stage, and analytical modules (linear regression, correlation, PCA, t-test).
 Author: Litewave Analytics Team
 License: MIT

{batch_analytics-0.3.28 → batch_analytics-0.3.30}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "batch-analytics"
-version = "0.3.28"
+version = "0.3.30"
 description = "PySpark batch analytics: Extract, Transform, Stage, and analytical modules (linear regression, correlation, PCA, t-test)."
 readme = "README.md"
 requires-python = ">=3.8"

{batch_analytics-0.3.28 → batch_analytics-0.3.30}/src/batch_analytics/analytics/equipment_oee.py

@@ -137,7 +137,13 @@ def run_equipment_oee(
     ideal = _load_ideal_cycle(spark, config)
     avail = _staging_availability(df)
     perf_ops = _staging_performance(df, ideal)
-    perf_tot = _staging_performance_totals(df, ideal)
+    # Only ideal totals are joined here; avail already has actual_run_minutes.
+    # Keeping both would make F.col("actual_run_minutes") ambiguous after the join.
+    perf_tot = _staging_performance_totals(df, ideal).select(
+        "equipment_id",
+        "batch_id",
+        "ideal_cycle_time_minutes",
+    )
 
     joined = (
         avail.join(perf_tot, on=["equipment_id", "batch_id"], how="inner")
@@ -189,13 +195,19 @@ def run_equipment_oee(
     n = result_df.count()
     logger.info("equipment_oee: %d equipment×batch rows", n)
 
-    return {
+    out: Dict[str, Any] = {
         "row_count": n,
-        "staging_availability": _rows_to_dicts(avail.orderBy("equipment_id", "batch_id")),
-        "staging_batch_quality": _rows_to_dicts(batch_q.orderBy("batch_id")),
-        "staging_ideal_cycle": _rows_to_dicts(ideal.orderBy("equipment_id", "operation_id")),
-        "staging_performance_by_operation": _rows_to_dicts(
-            perf_ops.orderBy("equipment_id", "batch_id", "operation_id")
-        ),
         "equipment_oee": _rows_to_dicts(result_df),
     }
+    if config.analytics.equipment_oee_include_staging:
+        out["staging_availability"] = _rows_to_dicts(
+            avail.orderBy("equipment_id", "batch_id")
+        )
+        out["staging_batch_quality"] = _rows_to_dicts(batch_q.orderBy("batch_id"))
+        out["staging_ideal_cycle"] = _rows_to_dicts(
+            ideal.orderBy("equipment_id", "operation_id")
+        )
+        out["staging_performance_by_operation"] = _rows_to_dicts(
+            perf_ops.orderBy("equipment_id", "batch_id", "operation_id")
+        )
+    return out

{batch_analytics-0.3.28 → batch_analytics-0.3.30}/src/batch_analytics/config.py

@@ -184,6 +184,10 @@ class AnalyticsConfig:
     equipment_oee_ideal_cycle_table: str = os.environ.get(
         "BATCH_OEE_IDEAL_CYCLE_TABLE", ""
     ).strip()
+    # If true, equipment_oee result includes intermediate staging_* arrays (large payloads).
+    equipment_oee_include_staging: bool = os.environ.get(
+        "BATCH_OEE_INCLUDE_STAGING", ""
+    ).lower() in ("true", "1", "yes", "on")
 
 
 @dataclass

{batch_analytics-0.3.28 → batch_analytics-0.3.30}/src/batch_analytics.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: batch-analytics
-Version: 0.3.28
+Version: 0.3.30
 Summary: PySpark batch analytics: Extract, Transform, Stage, and analytical modules (linear regression, correlation, PCA, t-test).
 Author: Litewave Analytics Team
 License: MIT