FlowerPower 0.11.6.12__py3-none-any.whl → 0.11.6.13__py3-none-any.whl

flowerpower/fs/ext.py

@@ -951,7 +951,7 @@ def _read_parquet(
         if isinstance(tables, list):
             if len(tables) > 1:
                 schemas = [t.schema for t in tables]
-                unified_schema = unify_schemas_pa(schemas)
+                unified_schema = unify_schemas_pa(schemas, standardize_timezones=True)
                 tables = [cast_schema(t, unified_schema) for t in tables]
 
             tables = [table for table in tables if table.num_rows > 0]
@@ -1095,7 +1095,7 @@ def _read_parquet_batches(
             # Unify schemas before concatenation
             if len(batch_tables) > 1:
                 schemas = [t.schema for t in batch_tables]
-                unified_schema = unify_schemas_pa(schemas)
+                unified_schema = unify_schemas_pa(schemas, standardize_timezones=True)
                 batch_tables = [cast_schema(t, unified_schema) for t in batch_tables]
             batch_tables = [table for table in batch_tables if table.num_rows > 0]
             if not batch_tables:

flowerpower/plugins/io/helpers/pyarrow.py

@@ -28,18 +28,133 @@ F32_MIN = float(np.finfo(np.float32).min)
 F32_MAX = float(np.finfo(np.float32).max)
 
 
+def dominant_timezone_per_column(
+    schemas: list[pa.Schema],
+) -> dict[str, tuple[str | None, str | None]]:
+    """
+    For each timestamp column (by name) across all schemas, detect the most frequent timezone (including None).
+    If None and a timezone are tied, prefer the timezone.
+    Returns a dict: {column_name: dominant_timezone}
+    """
+    from collections import Counter, defaultdict
+
+    tz_counts = defaultdict(Counter)
+    units = {}
+
+    for schema in schemas:
+        for field in schema:
+            if pa.types.is_timestamp(field.type):
+                tz = field.type.tz
+                name = field.name
+                tz_counts[name][tz] += 1
+                # Track unit for each column (assume consistent)
+                if name not in units:
+                    units[name] = field.type.unit
+
+    dominant = {}
+    for name, counter in tz_counts.items():
+        most_common = counter.most_common()
+        if not most_common:
+            continue
+        top_count = most_common[0][1]
+        # Find all with top_count
+        top_tzs = [tz for tz, cnt in most_common if cnt == top_count]
+        # If tie and one is not None, prefer not-None
+        if len(top_tzs) > 1 and any(tz is not None for tz in top_tzs):
+            tz = next(tz for tz in top_tzs if tz is not None)
+        else:
+            tz = most_common[0][0]
+        dominant[name] = (units[name], tz)
+    return dominant
+
+
+def standardize_schema_timezones_by_majority(
+    schemas: list[pa.Schema],
+) -> list[pa.Schema]:
+    """
+    For each timestamp column (by name) across all schemas, set the timezone to the most frequent (with tie-breaking).
+    Returns a new list of schemas with updated timestamp timezones.
+    """
+    dom = dominant_timezone_per_column(schemas)
+    new_schemas = []
+    for schema in schemas:
+        fields = []
+        for field in schema:
+            if pa.types.is_timestamp(field.type) and field.name in dom:
+                unit, tz = dom[field.name]
+                fields.append(
+                    pa.field(
+                        field.name,
+                        pa.timestamp(unit, tz),
+                        field.nullable,
+                        field.metadata,
+                    )
+                )
+            else:
+                fields.append(field)
+        new_schemas.append(pa.schema(fields, schema.metadata))
+    return new_schemas
+
+
+def standardize_schema_timezones(
+    schemas: list[pa.Schema], timezone: str | None = None
+) -> list[pa.Schema]:
+    """
+    Standardize timezone info for all timestamp columns in a list of PyArrow schemas.
+
+    Args:
+        schemas (list of pa.Schema): List of PyArrow schemas.
+        timezone (str or None): If None, remove timezone from all timestamp columns.
+                                If str, set this timezone for all timestamp columns.
+                                If "auto", use the most frequent timezone across schemas.
+
+    Returns:
+        list of pa.Schema: New schemas with standardized timezone info.
+    """
+    if timezone == "auto":
+        # Use the most frequent timezone for each column
+        return standardize_schema_timezones_by_majority(schemas)
+    new_schemas = []
+    for schema in schemas:
+        fields = []
+        for field in schema:
+            if pa.types.is_timestamp(field.type):
+                fields.append(
+                    pa.field(
+                        field.name,
+                        pa.timestamp(field.type.unit, timezone),
+                        field.nullable,
+                        field.metadata,
+                    )
+                )
+            else:
+                fields.append(field)
+        new_schemas.append(pa.schema(fields, schema.metadata))
+    return new_schemas
+
+
 def unify_schemas(
-    schemas: list[pa.Schema], use_large_dtypes: bool = False
+    schemas: list[pa.Schema],
+    use_large_dtypes: bool = False,
+    timezone: str | None = None,
+    standardize_timezones: bool = True,
 ) -> pa.Schema:
     """
     Unify a list of PyArrow schemas into a single schema.
 
     Args:
         schemas (list[pa.Schema]): List of PyArrow schemas to unify.
+        use_large_dtypes (bool): If True, keep large types like large_string.
+        timezone (str | None): If specified, standardize all timestamp columns to this timezone.
+            If "auto", use the most frequent timezone across schemas.
+            If None, remove timezone from all timestamp columns.
+        standardize_timezones (bool): If True, standardize all timestamp columns to the most frequent timezone.
 
     Returns:
         pa.Schema: A unified PyArrow schema.
     """
+    if standardize_timezones:
+        schemas = standardize_schema_timezones(schemas, timezone)
     try:
         return pa.unify_schemas(schemas, promote_options="permissive")
     except (pa.lib.ArrowInvalid, pa.lib.ArrowTypeError) as e:

{flowerpower-0.11.6.12.dist-info → flowerpower-0.11.6.13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: FlowerPower
-Version: 0.11.6.12
+Version: 0.11.6.13
 Summary: A simple workflow framework. Hamilton + APScheduler = FlowerPower
 Author-email: "Volker L." <ligno.blades@gmail.com>
 Project-URL: Homepage, https://github.com/legout/flowerpower

{flowerpower-0.11.6.12.dist-info → flowerpower-0.11.6.13.dist-info}/RECORD

@@ -18,7 +18,7 @@ flowerpower/cli/pipeline.py,sha256=60P6u_QOSgp0jJXEMxazEEo5Sh7-SWFo-Kkuaz21YuI,3
 flowerpower/cli/utils.py,sha256=nDSSj_1nlYlMmj252kRZeohhFqHv9yvdgDEduQCyWOc,5152
 flowerpower/fs/__init__.py,sha256=uZaPXErEfQqQRbKRIjkB9yiygd45X5_psYn9-VVrBTQ,910
 flowerpower/fs/base.py,sha256=TqgqBsaFj13O1NpAr8kHuGJ9CTlaSWViMB8Ai_iuCjs,22761
-flowerpower/fs/ext.py,sha256=gVmca4UVC1y33Y-8BIstO5a7oyw20bcSxtA19F0Limk,70548
+flowerpower/fs/ext.py,sha256=2-BkLdNFORW-OtrmlCXMmUJtYxxhmTmhrzxVtbbsDSw,70604
 flowerpower/fs/storage_options.py,sha256=msq5TpxAU8tcE_Bxjw6SyxaFa75UjdYnR4-O9U2wmbk,48034
 flowerpower/job_queue/__init__.py,sha256=a25hIqv2xoFKb4JZlyUukS0ppZ9-2sJKH3XAvbk3rlk,10788
 flowerpower/job_queue/base.py,sha256=YwLunDQSyqkSU_vJ69C5SSybJeJP1bAiZ3teUtOchxA,13640
@@ -48,7 +48,7 @@ flowerpower/plugins/io/base.py,sha256=oGxTKobs0M19hPV842EelAeJ01EBz6kDdGv_4GTyFz
 flowerpower/plugins/io/metadata.py,sha256=PCrepLilXRWKDsB5BKFF_-OFs712s1zBeitW-84lDLQ,7005
 flowerpower/plugins/io/helpers/datetime.py,sha256=1WBUg2ywcsodJQwoF6JiIGc9yhVobvE2IErWp4i95m4,10649
 flowerpower/plugins/io/helpers/polars.py,sha256=6YbPg1UDeZaWLSnXatgvzCNJI8Ui2GhTegYsbV5VgrM,27463
-flowerpower/plugins/io/helpers/pyarrow.py,sha256=r8JNCp_BSte2ly41hpk0Z9Ik02-IouazgNp98GcNCb8,13901
+flowerpower/plugins/io/helpers/pyarrow.py,sha256=umgmM2hZQ-tfbZTl8rYo158K6P0SsAOfm7oe-N5cc_M,18243
 flowerpower/plugins/io/helpers/sql.py,sha256=BPIxjarKF3p93EdtUu-md8KislE9q8IWNSeZ5toFU6U,7298
 flowerpower/plugins/io/loader/__init__.py,sha256=MKH42nvVokaWas0wFgX1yrpU5iLpvHjRqqF-KzwLHCg,780
 flowerpower/plugins/io/loader/csv.py,sha256=Q5bmcbbr530sT1kQ2YiJwvsMUPqi0VcZWsLOygmzRyI,827
@@ -94,9 +94,9 @@ flowerpower/utils/monkey.py,sha256=VPl3yimoWhwD9kI05BFsjNvtyQiDyLfY4Q85Bb6Ma0w,2
 flowerpower/utils/open_telemetry.py,sha256=fQWJWbIQFtKIxMBjAWeF12NGnqT0isO3A3j-DSOv_vE,949
 flowerpower/utils/scheduler.py,sha256=2zJ_xmLXpvXUQNF1XS2Gqm3Ogo907ctZ50GtvQB_rhE,9354
 flowerpower/utils/templates.py,sha256=ouyEeSDqa9PjW8c32fGpcINlpC0WToawRFZkMPtwsLE,1591
-flowerpower-0.11.6.12.dist-info/licenses/LICENSE,sha256=9AkLexxrmr0aBgSHiqxpJk9wgazpP1CTJyiDyr56J9k,1063
-flowerpower-0.11.6.12.dist-info/METADATA,sha256=2_9L9FZ9Chw2Z5IQJXNdkUnfdmrv91cPiq7KRijnrw0,21613
-flowerpower-0.11.6.12.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-flowerpower-0.11.6.12.dist-info/entry_points.txt,sha256=61X11i5a2IwC9LBiP20XCDl5zMOigGCjMCx17B7bDbQ,52
-flowerpower-0.11.6.12.dist-info/top_level.txt,sha256=VraH4WtEUfSxs5L-rXwDQhzQb9eLHTUtgvmFZ2dAYnA,12
-flowerpower-0.11.6.12.dist-info/RECORD,,
+flowerpower-0.11.6.13.dist-info/licenses/LICENSE,sha256=9AkLexxrmr0aBgSHiqxpJk9wgazpP1CTJyiDyr56J9k,1063
+flowerpower-0.11.6.13.dist-info/METADATA,sha256=aDlOA-x27j2YjpomvE0xrtb7MzOPo7L7ljz-rSMLE6c,21613
+flowerpower-0.11.6.13.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+flowerpower-0.11.6.13.dist-info/entry_points.txt,sha256=61X11i5a2IwC9LBiP20XCDl5zMOigGCjMCx17B7bDbQ,52
+flowerpower-0.11.6.13.dist-info/top_level.txt,sha256=VraH4WtEUfSxs5L-rXwDQhzQb9eLHTUtgvmFZ2dAYnA,12
+flowerpower-0.11.6.13.dist-info/RECORD,,