dragon-ml-toolbox 10.4.0__tar.gz → 10.4.2__tar.gz

{dragon_ml_toolbox-10.4.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-10.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 10.4.0
+Version: 10.4.2
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-10.4.0 → dragon_ml_toolbox-10.4.2/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 10.4.0
+Version: 10.4.2
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-10.4.0 → dragon_ml_toolbox-10.4.2}/ml_tools/ETL_engineering.py

@@ -714,7 +714,11 @@ class TemperatureExtractor:
         if self.average_mode:
             # Extract all numbers and compute their mean. Polars' list.mean()
             # handles the casting to float automatically.
-            celsius_expr = column.str.extract_all(self._avg_mode_pattern).list.mean()
+            celsius_expr = (
+                column.str.extract_all(self._avg_mode_pattern)
+                .list.eval(pl.element().cast(pl.Float64, strict=False))
+                .list.mean()
+            )
         else:
             # Extract a single number using the specified pattern.
             # Cast to Float64, with non-matches becoming null.
@@ -800,7 +804,7 @@ class MultiTemperatureExtractor:
             # --- Step 1: Extract the i-th number as a Celsius value ---
             celsius_expr = (
                 column.str.extract_all(self.regex_pattern)
-                .list.get(i)
+                .list.get(i, null_on_oob=True)
                 .cast(pl.Float64, strict=False)
             )
 
@@ -952,9 +956,9 @@ class TriRatioCalculator:
         all_numbers_expr = pl.col(column.name).str.extract_all(r"(\d+\.?\d*)")
         num_parts_expr = all_numbers_expr.list.len()
 
-        expr_A = all_numbers_expr.list.get(0).cast(pl.Float64)
-        expr_B = all_numbers_expr.list.get(1).cast(pl.Float64)
-        expr_C = all_numbers_expr.list.get(2).cast(pl.Float64)
+        expr_A = all_numbers_expr.list.get(0, null_on_oob=True).cast(pl.Float64)
+        expr_B = all_numbers_expr.list.get(1, null_on_oob=True).cast(pl.Float64)
+        expr_C = all_numbers_expr.list.get(2, null_on_oob=True).cast(pl.Float64)
 
         # Define logic for each output column using expressions
         ratio_ab_expr = pl.when(num_parts_expr == 3).then(

{dragon_ml_toolbox-10.4.0 → dragon_ml_toolbox-10.4.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "10.4.0"
+version = "10.4.2"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl Loza", email = "luigiloza@gmail.com" }