dragon-ml-toolbox 10.4.1__tar.gz → 10.5.0__tar.gz

{dragon_ml_toolbox-10.4.1/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-10.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 10.4.1
+Version: 10.5.0
 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-10.4.1 → dragon_ml_toolbox-10.5.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 10.4.1
+Version: 10.5.0
 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-10.4.1 → dragon_ml_toolbox-10.5.0}/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.

{dragon_ml_toolbox-10.4.1 → dragon_ml_toolbox-10.5.0}/ml_tools/data_exploration.py

@@ -21,6 +21,7 @@ __all__ = [
     "show_null_columns",
     "drop_columns_with_missing_data",
     "drop_macro",
+    "clean_column_names",
     "split_features_targets", 
     "split_continuous_binary", 
     "plot_correlation_heatmap", 
@@ -300,6 +301,42 @@ def drop_macro(df: pd.DataFrame,
     return df_clean
 
 
+def clean_column_names(df: pd.DataFrame, replacement_char: str = '-', replacement_pattern: str = r'[\[\]{}<>,:"]', verbose: bool = True) -> pd.DataFrame:
+    """
+    Cleans DataFrame column names by replacing special characters.
+
+    This function is useful for ensuring compatibility with libraries like LightGBM,
+    which do not support special JSON characters such as `[]{}<>,:"` in feature names.
+
+    Args:
+        df (pd.DataFrame): The input DataFrame.
+        replacement_char (str): The character to use for replacing characters.
+        replacement_pattern (str): Regex pattern to use for the replacement logic.
+        verbose (bool): If True, prints the renamed columns.
+
+    Returns:
+        pd.DataFrame: A new DataFrame with cleaned column names.
+    """
+    new_df = df.copy()
+    
+    original_columns = new_df.columns
+    new_columns = original_columns.str.replace(replacement_pattern, replacement_char, regex=True)
+    
+    # Create a map of changes for logging
+    rename_map = {old: new for old, new in zip(original_columns, new_columns) if old != new}
+    
+    if verbose:
+        if rename_map:
+            _LOGGER.info(f"Cleaned {len(rename_map)} column name(s) containing special characters:")
+            for old, new in rename_map.items():
+                print(f"    '{old}' -> '{new}'")
+        else:
+            _LOGGER.info("No column names required cleaning.")
+            
+    new_df.columns = new_columns
+    return new_df
+
+
 def split_features_targets(df: pd.DataFrame, targets: list[str]):
     """
     Splits a DataFrame's columns into features and targets.

{dragon_ml_toolbox-10.4.1 → dragon_ml_toolbox-10.5.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "10.4.1"
+version = "10.5.0"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl Loza", email = "luigiloza@gmail.com" }