dragon-ml-toolbox 20.14.0__py3-none-any.whl → 20.14.1__py3-none-any.whl

{dragon_ml_toolbox-20.14.0.dist-info → dragon_ml_toolbox-20.14.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.14.0
+Version: 20.14.1
 Summary: Complete pipelines and helper tools for data science and machine learning projects.
 Author-email: Karl Luigi Loza Vidaurre <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-20.14.0.dist-info → dragon_ml_toolbox-20.14.1.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-20.14.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-20.14.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
+dragon_ml_toolbox-20.14.1.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-20.14.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
 ml_tools/ETL_cleaning/__init__.py,sha256=gLRHF-qzwpqKTvbbn9chIQELeUDh_XGpBRX28j-5IqI,545
@@ -107,8 +107,8 @@ ml_tools/_core/_script_info.py,sha256=LtFGt10gEvCnhIRMKJPi2yXkiGLcdr7lE-oIP2XGHz
 ml_tools/data_exploration/__init__.py,sha256=XNA8gcRx5ifrv092HA7HSpek8havlk_3RZi9aq9dSjg,1957
 ml_tools/data_exploration/_analysis.py,sha256=JSoFJSkv4-_v9YxxmjHZ_PeFRneDENjSEo2sy_uC4oY,14196
 ml_tools/data_exploration/_cleaning.py,sha256=pAZOXgGK35j7O8q6cnyTwYK1GLNnD04A8p2fSyMB1mg,20906
-ml_tools/data_exploration/_features.py,sha256=twJ6OixU4ItRXA8rPJRfg2N9QVsbn38CFqJiLcXav1A,28664
-ml_tools/data_exploration/_plotting.py,sha256=zH1dPcIoAlOuww23xIoBCsQOAshPPv9OyGposOA2RvI,19883
+ml_tools/data_exploration/_features.py,sha256=_aBMW7eqSm6oUj54ftidsv9zdywOkc1eyZgITb82XF8,29237
+ml_tools/data_exploration/_plotting.py,sha256=Vg9qS46akbAyrZAgBrPWg2p29V5vqqY4Bk4SHwZLZNI,19995
 ml_tools/data_exploration/_schema_ops.py,sha256=Fd6fBGGv4OpxmJ1HG9pith6QL90z0tzssCvzkQxlEEQ,11083
 ml_tools/ensemble_evaluation/__init__.py,sha256=t4Gr8EGEk8RLatyc92-S0BzbQvdvodzoF-qDAH2qjVg,546
 ml_tools/ensemble_evaluation/_ensemble_evaluation.py,sha256=-sX9cLMaa0FOQDikmVv2lsCYtQ56Kftd3tILnNej0Hg,28346
@@ -143,7 +143,7 @@ ml_tools/utilities/__init__.py,sha256=h4lE3SQstg-opcQj6QSKhu-HkqSbmHExsWoM9vC5D9
 ml_tools/utilities/_translate.py,sha256=U8hRPa3PmTpIf9n9yR3gBGmp_hkcsjQLwjAHSHc0WHs,10325
 ml_tools/utilities/_utility_save_load.py,sha256=EFvFaTaHahDQWdJWZr-j7cHqRbG_Xrpc96228JhV-bs,16773
 ml_tools/utilities/_utility_tools.py,sha256=bN0J9d1S0W5wNzNntBWqDsJcEAK7-1OgQg3X2fwXns0,6918
-dragon_ml_toolbox-20.14.0.dist-info/METADATA,sha256=32IleSQa7t7E42ZB5rM32Lf1MlSAMtKkU-TFky3VckA,7889
-dragon_ml_toolbox-20.14.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-dragon_ml_toolbox-20.14.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-20.14.0.dist-info/RECORD,,
+dragon_ml_toolbox-20.14.1.dist-info/METADATA,sha256=oV6v5gFhRVLpuJ3HgL7Qpn8_Dgk9DGkYcOjSfl2kIh0,7889
+dragon_ml_toolbox-20.14.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+dragon_ml_toolbox-20.14.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-20.14.1.dist-info/RECORD,,

ml_tools/data_exploration/_features.py

@@ -168,6 +168,13 @@ def split_continuous_categorical_targets(
         f"  - Categorical: {df_categorical.shape}\n"
         f"  - Targets: {df_targets.shape}"
     )
+    
+    if isinstance(df_continuous, pd.Series):
+        df_continuous = df_continuous.to_frame()
+    if isinstance(df_categorical, pd.Series):
+        df_categorical = df_categorical.to_frame()
+    if isinstance(df_targets, pd.Series):
+        df_targets = df_targets.to_frame()
 
     return df_continuous, df_categorical, df_targets
 
@@ -271,6 +278,7 @@ def encode_classification_target(
     df: pd.DataFrame,
     target_col: str,
     save_dir: Union[str, Path],
+    suffix: str = "",
     verbose: int = 2
 ) -> tuple[pd.DataFrame, dict[str, int]]:
     """
@@ -283,6 +291,7 @@ def encode_classification_target(
         df (pd.DataFrame): Input DataFrame.
         target_col (str): Name of the target column to encode.
         save_dir (str | Path): Directory where the class map JSON will be saved.
+        suffix (str): Suffix to append to the class map filename.
         verbose (int): Verbosity level for logging.
 
     Returns:
@@ -300,9 +309,17 @@ def encode_classification_target(
         _LOGGER.error(f"Target column '{target_col}' contains {n_missing} missing values. Please handle them before encoding.")
         raise ValueError()
     
+    # validate suffix and prepend underscore if needed
+    if suffix:
+        if not suffix.startswith("_"):
+            suffix = f"_{suffix}"
+        sanitized_suffix = suffix
+    else:
+        sanitized_suffix = ''
+        
     # Ensure directory exists
     save_path = make_fullpath(save_dir, make=True, enforce="directory")
-    file_path = save_path / "class_map.json"
+    file_path = save_path / f"class_map{sanitized_suffix}.json"
 
     # Get unique values and sort them to ensure deterministic encoding (0, 1, 2...)
     # Convert to string to ensure the keys in JSON are strings
@@ -322,10 +339,9 @@ def encode_classification_target(
             json.dump(class_map, f, indent=4)
             
         if verbose >= 2:
-            _LOGGER.info(f"Class mapping saved to: '{file_path}'")
-        
+            _LOGGER.info(f"Target '{target_col}' encoded with {len(class_map)} classes. Saved to {file_path}.")
+            
         if verbose >= 3:
-            _LOGGER.info(f"Target '{target_col}' encoded with {len(class_map)} classes.")
             # Print a preview
             if len(class_map) <= 10:
                 print(f"  Mapping: {class_map}")

ml_tools/data_exploration/_plotting.py

@@ -475,6 +475,9 @@ def plot_correlation_heatmap(df: pd.DataFrame,
         save_path = make_fullpath(save_dir, make=True)
         # sanitize the plot title to save the file
         sanitized_plot_title = sanitize_filename(plot_title)
+        # prepend method to filename
+        sanitized_plot_title = f"{method}_{sanitized_plot_title}"
+        
         plot_filename = sanitized_plot_title + ".svg"
         
         full_path = save_path / plot_filename