FlowerPower 0.11.6.14__py3-none-any.whl → 0.11.6.16__py3-none-any.whl

flowerpower/plugins/io/helpers/polars.py

@@ -46,15 +46,32 @@ def _can_downcast_to_float32(series: pl.Series) -> bool:
     return F32_MIN <= min_val <= max_val <= F32_MAX
 
 
-def _optimize_numeric_column(series: pl.Series, col_name: str, shrink: bool) -> pl.Expr:
-    """Optimize numeric column types."""
+def _optimize_numeric_column(
+    series: pl.Series, col_name: str, shrink: bool, allow_unsigned: bool = False
+) -> pl.Expr:
+    """Optimize numeric column types, optionally converting to unsigned if all values >= 0."""
+    expr = pl.col(col_name)
+    dtype = series.dtype
+
+    if (
+        allow_unsigned
+        and dtype.is_integer()
+        and (series.min() is not None)
+        and series.min() >= 0
+    ):
+        # Convert to unsigned integer type, shrink if requested
+        if shrink:
+            return expr.cast(pl.UInt64).shrink_dtype()
+        else:
+            return expr.cast(pl.UInt64)
+
     if not shrink:
-        return pl.col(col_name)
+        return expr
 
-    if series.dtype == pl.Float64 and not _can_downcast_to_float32(series):
-        return pl.col(col_name)
+    if dtype == pl.Float64 and not _can_downcast_to_float32(series):
+        return expr
 
-    return pl.col(col_name).shrink_dtype()
+    return expr.shrink_dtype()
 
 
 def _optimize_string_column(
@@ -116,7 +133,11 @@ def _optimize_string_column(
 
 
 def _get_column_expr(
-    df: pl.DataFrame, col_name: str, shrink_numerics: bool, time_zone: str | None = None
+    df: pl.DataFrame,
+    col_name: str,
+    shrink_numerics: bool,
+    allow_unsigned: bool,
+    time_zone: str | None = None,
 ) -> pl.Expr:
     """Generate optimization expression for a single column."""
     series = df[col_name]
@@ -127,7 +148,9 @@ def _get_column_expr(
 
     # Process based on current type
     if series.dtype.is_numeric():
-        return _optimize_numeric_column(series, col_name, shrink_numerics)
+        return _optimize_numeric_column(
+            series, col_name, shrink_numerics, allow_unsigned
+        )
     elif series.dtype == pl.Utf8:
         return _optimize_string_column(series, col_name, shrink_numerics, time_zone)
 
@@ -141,6 +164,7 @@ def opt_dtype(
     exclude: str | list[str] | None = None,
     time_zone: str | None = None,
     shrink_numerics: bool = True,
+    allow_unsigned: bool = True,
     strict: bool = False,
 ) -> pl.DataFrame:
     """
@@ -156,6 +180,7 @@ def opt_dtype(
         exclude: Column(s) to exclude from optimization
         time_zone: Optional time zone for datetime parsing
         shrink_numerics: Whether to downcast numeric types when possible
+        allow_unsigned: Whether to allow unsigned integer types
         strict: If True, will raise an error if any column cannot be optimized
 
     Returns:
@@ -179,7 +204,9 @@ def opt_dtype(
     for col_name in cols_to_process:
         try:
             expressions.append(
-                _get_column_expr(df, col_name, shrink_numerics, time_zone)
+                _get_column_expr(
+                    df, col_name, shrink_numerics, allow_unsigned, time_zone
+                )
             )
         except Exception as e:
             if strict:

{flowerpower-0.11.6.14.dist-info → flowerpower-0.11.6.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: FlowerPower
-Version: 0.11.6.14
+Version: 0.11.6.16
 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-0.11.6.14.dist-info → flowerpower-0.11.6.16.dist-info}/RECORD

@@ -47,7 +47,7 @@ flowerpower/pipeline/visualizer.py,sha256=amjMrl5NetErE198HzZBPWVZBi_t5jj9ydxWpu
 flowerpower/plugins/io/base.py,sha256=oGxTKobs0M19hPV842EelAeJ01EBz6kDdGv_4GTyFzk,97098
 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/polars.py,sha256=ESA2YHZmWCmyhjwNULQO9_7G_sFcgF9x3q-IGatbP-0,28124
 flowerpower/plugins/io/helpers/pyarrow.py,sha256=lYZHbPklzYvd7L5XqDjoTUV42cHi_c9Wh8xf1HYtS2M,18592
 flowerpower/plugins/io/helpers/sql.py,sha256=BPIxjarKF3p93EdtUu-md8KislE9q8IWNSeZ5toFU6U,7298
 flowerpower/plugins/io/loader/__init__.py,sha256=MKH42nvVokaWas0wFgX1yrpU5iLpvHjRqqF-KzwLHCg,780
@@ -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-0.11.6.14.dist-info/licenses/LICENSE,sha256=9AkLexxrmr0aBgSHiqxpJk9wgazpP1CTJyiDyr56J9k,1063
-flowerpower-0.11.6.14.dist-info/METADATA,sha256=XbPfuXRqDDFH6pT7FgUBC_Z1CiOBAw-EhtFYlGQwPfI,21613
-flowerpower-0.11.6.14.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-flowerpower-0.11.6.14.dist-info/entry_points.txt,sha256=61X11i5a2IwC9LBiP20XCDl5zMOigGCjMCx17B7bDbQ,52
-flowerpower-0.11.6.14.dist-info/top_level.txt,sha256=VraH4WtEUfSxs5L-rXwDQhzQb9eLHTUtgvmFZ2dAYnA,12
-flowerpower-0.11.6.14.dist-info/RECORD,,
+flowerpower-0.11.6.16.dist-info/licenses/LICENSE,sha256=9AkLexxrmr0aBgSHiqxpJk9wgazpP1CTJyiDyr56J9k,1063
+flowerpower-0.11.6.16.dist-info/METADATA,sha256=X1bvOqBHxJgYBRCceoHrE3huch9jf2VB3bwj-5LMLbE,21613
+flowerpower-0.11.6.16.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+flowerpower-0.11.6.16.dist-info/entry_points.txt,sha256=61X11i5a2IwC9LBiP20XCDl5zMOigGCjMCx17B7bDbQ,52
+flowerpower-0.11.6.16.dist-info/top_level.txt,sha256=VraH4WtEUfSxs5L-rXwDQhzQb9eLHTUtgvmFZ2dAYnA,12
+flowerpower-0.11.6.16.dist-info/RECORD,,