dragon-ml-toolbox 3.5.0__py3-none-any.whl → 3.6.0__py3-none-any.whl

{dragon_ml_toolbox-3.5.0.dist-info → dragon_ml_toolbox-3.6.0.dist-info}/METADATA

@@ -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.dist-info → dragon_ml_toolbox-3.6.0.dist-info}/RECORD

@@ -1,6 +1,6 @@
-dragon_ml_toolbox-3.5.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-3.5.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=6cfpIeQ6D4Mcs10nkogQrkVyq1T7i2qXjjNHFoUMOyE,1892
-ml_tools/ETL_engineering.py,sha256=9dojA9RqE7bq1A70tegsERszoqll7UmcJelVeQeefik,39519
+dragon_ml_toolbox-3.6.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-3.6.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=6cfpIeQ6D4Mcs10nkogQrkVyq1T7i2qXjjNHFoUMOyE,1892
+ml_tools/ETL_engineering.py,sha256=URol7s45fVIdLqnhyOU1Etbi-D7MksFg-qtNwsKiunY,39488
 ml_tools/GUI_tools.py,sha256=uFx6zIrQZzDPSTtOSHz8ptz-fxZiQz-lXHcrqwuYV_E,20385
 ml_tools/MICE_imputation.py,sha256=ed-YeQkEAeHxTNkWIHs09T4YeYNF0aqAnrUTcdIEp9E,11372
 ml_tools/ML_callbacks.py,sha256=gHZk-lyzAax6iEtG26zHuoobdAZCFJ6BmI6pWoXkOrw,13189
@@ -13,13 +13,13 @@ ml_tools/VIF_factor.py,sha256=4b3HmrrolN7ZIAo16TWwLlExqj_xaa8MxbkXD1xPCys,10295
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ml_tools/_particle_swarm_optimization.py,sha256=b_eNNkA89Y40hj76KauivT8KLScH1B9wF2IXptOqkOw,22220
 ml_tools/_pytorch_models.py,sha256=bpWZsrSwCvHJQkR6UfoPpElsMv9AvmiNErNHC8NYB_I,10132
-ml_tools/data_exploration.py,sha256=IkpOyIRPKdu4qKeUdvvMvNPelSVWegNEKMqX3IInmpw,25003
+ml_tools/data_exploration.py,sha256=Ne6LHtHJFkv5SVBvTK-kmSS9OD-N1tT6TacXRVxyI9A,25220
 ml_tools/datasetmaster.py,sha256=N-uwfzWnl_qnoAqjbfS98I1pVNra5u6rhKLdWbFIReA,30122
 ml_tools/ensemble_learning.py,sha256=PPtBBLgLvaYOdY-MlcjXuxWWXf3JQavLNEysFgzjc_s,37470
 ml_tools/handle_excel.py,sha256=lwds7rDLlGSCWiWGI7xNg-Z7kxAepogp0lstSFa0590,12949
 ml_tools/logger.py,sha256=jC4Q2OqmDm8ZO9VpuZqBSWdXryqaJvLscqVJ6caNMOk,6009
 ml_tools/utilities.py,sha256=7cVWXjdxgSoIbZunuxJEOnJDSYp29liYsZexbrVDabs,23132
-dragon_ml_toolbox-3.5.0.dist-info/METADATA,sha256=yxz0lVEDn3k40f3nZk_pocW8WCOXifF6ItuUMJ8LFsM,3273
-dragon_ml_toolbox-3.5.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-3.5.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-3.5.0.dist-info/RECORD,,
+dragon_ml_toolbox-3.6.0.dist-info/METADATA,sha256=B_xp13t4M52KwRnUUv2AedBXAKBqHL04MBFha1eAYsI,3273
+dragon_ml_toolbox-3.6.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-3.6.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-3.6.0.dist-info/RECORD,,

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 = []

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]