FlowerPower 0.11.6.14__tar.gz → 0.11.6.16__tar.gz

{flowerpower-0.11.6.14/src/FlowerPower.egg-info → flowerpower-0.11.6.16}/PKG-INFO

@@ -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 → flowerpower-0.11.6.16}/pyproject.toml

@@ -4,7 +4,7 @@ description = "A simple workflow framework. Hamilton + APScheduler = FlowerPower
 authors = [{ name = "Volker L.", email = "ligno.blades@gmail.com" }]
 readme = "README.md"
 requires-python = ">= 3.11"
-version = "0.11.6.14"
+version = "0.11.6.16"
 keywords = [
   "hamilton",
   "workflow",

{flowerpower-0.11.6.14 → flowerpower-0.11.6.16/src/FlowerPower.egg-info}/PKG-INFO

@@ -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 → flowerpower-0.11.6.16}/src/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: