dragon-ml-toolbox 3.5.0__tar.gz → 3.6.0__tar.gz

{dragon_ml_toolbox-3.5.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-3.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 3.5.0
+Version: 3.6.0
 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-3.5.0 → dragon_ml_toolbox-3.6.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 3.5.0
+Version: 3.6.0
 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-3.5.0 → dragon_ml_toolbox-3.6.0}/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-3.6.0}/ml_tools/data_exploration.py

@@ -15,7 +15,7 @@ import re
 # Keep track of all available tools, show using `info()`
 __all__ = [
     "summarize_dataframe",
-    "drop_zero_only_columns",
+    "drop_constant_columns",
     "drop_rows_with_missing_data",
     "split_features_targets", 
     "show_null_columns",
@@ -62,44 +62,49 @@ def summarize_dataframe(df: pd.DataFrame, round_digits: int = 2):
     return summary
 
 
-def drop_zero_only_columns(df: pd.DataFrame, verbose: bool=True) -> pd.DataFrame:
+def drop_constant_columns(df: pd.DataFrame, verbose: bool = True) -> pd.DataFrame:
     """
-    Removes columns from a pandas DataFrame that contain only zeros and null/NaN values.
+    Removes columns from a pandas DataFrame that contain only a single unique 
+    value or are entirely null/NaN.
 
-    This utility is useful for cleaning data after dummification steps that may result in empty columns.
+    This utility is useful for cleaning data by removing constant features that 
+    have no predictive value.
 
     Args:
         df (pd.DataFrame): 
             The pandas DataFrame to clean.
+        verbose (bool): 
+            If True, prints the names of the columns that were dropped. 
+            Defaults to True.
 
     Returns:
         pd.DataFrame: 
-            A new DataFrame with the empty columns removed.
+            A new DataFrame with the constant columns removed.
     """
     if not isinstance(df, pd.DataFrame):
         raise TypeError("Input must be a pandas DataFrame.")
-    
+
     original_columns = set(df.columns)
-    
     cols_to_keep = []
+
     for col_name in df.columns:
         column = df[col_name]
         
-        # Keep any column that is not numeric by default
-        if not is_numeric_dtype(column):
+        # We can apply this logic to all columns or only focus on numeric ones.
+        # if not is_numeric_dtype(column):
+        #     cols_to_keep.append(col_name)
+        #     continue
+        
+        # Keep a column if it has more than one unique value (nunique ignores NaNs by default)
+        if column.nunique(dropna=True) > 1:
             cols_to_keep.append(col_name)
-            continue
 
-        # For numeric columns, check if there's at least one non-zero value.
-        if (column != 0).any():
-            cols_to_keep.append(col_name)
-    
-    dropped_columns = original_columns - set(cols_to_keep)      
+    dropped_columns = original_columns - set(cols_to_keep)
     if dropped_columns and verbose:
-        print(f"Dropped {len(dropped_columns)} columns:")
+        print(f"Dropped {len(dropped_columns)} constant columns:")
         for dropped_column in dropped_columns:
             print(f"    {dropped_column}")
-    
+
     return df[cols_to_keep]
 
 

{dragon_ml_toolbox-3.5.0 → dragon_ml_toolbox-3.6.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "3.5.0"
+version = "3.6.0"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl Loza", email = "luigiloza@gmail.com" }