dragon-ml-toolbox 3.5.0__tar.gz → 3.5.1__tar.gz

{dragon_ml_toolbox-3.5.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-3.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 3.5.0
+Version: 3.5.1
 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-3.5.0 → dragon_ml_toolbox-3.5.1/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 3.5.0
+Version: 3.5.1
 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-3.5.0 → dragon_ml_toolbox-3.5.1}/ml_tools/ETL_engineering.py

@@ -48,13 +48,12 @@ class ColumnCleaner:
     ## Usage Example
 
     ```python
-    phone_rules = {
-        # Matches (123) 456-7890 and reformats to 123-456-7890
-        r'\((\d{3})\)\s*(\d{3})-(\d{4})': r'$1-$2-$3'
+    id_rules = {
+        # Matches 'ID-12345' or 'ID 12345' and reformats to 'ID:12345'
+        r'ID[- ](\d+)': r'ID:$1'
     }
 
-    phone_cleaner = ColumnCleaner(column_name='phone_number', rules=phone_rules)
-
+    id_cleaner = ColumnCleaner(column_name='user_id', rules=id_rules)
     # This object would then be passed to a DataFrameCleaner.
     ```
     """
@@ -529,7 +528,7 @@ class KeywordDummifier:
         
         categorize_expr = categorize_expr.otherwise(None).alias("category")
 
-        temp_df = pl.DataFrame(categorize_expr)
+        temp_df = pl.select(categorize_expr)
         df_with_dummies = temp_df.to_dummies(columns=["category"])
         
         final_columns = []

{dragon_ml_toolbox-3.5.0 → dragon_ml_toolbox-3.5.1}/ml_tools/data_exploration.py

@@ -91,7 +91,7 @@ def drop_zero_only_columns(df: pd.DataFrame, verbose: bool=True) -> pd.DataFrame
             continue
 
         # For numeric columns, check if there's at least one non-zero value.
-        if (column != 0).any():
+        if (column.fillna(0) != 0).any():
             cols_to_keep.append(col_name)
     
     dropped_columns = original_columns - set(cols_to_keep)      

{dragon_ml_toolbox-3.5.0 → dragon_ml_toolbox-3.5.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "3.5.0"
+version = "3.5.1"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl Loza", email = "luigiloza@gmail.com" }