dragon-ml-toolbox 7.0.0__py3-none-any.whl → 8.1.0__py3-none-any.whl

{dragon_ml_toolbox-7.0.0.dist-info → dragon_ml_toolbox-8.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 7.0.0
+Version: 8.1.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
@@ -147,6 +147,7 @@ ensemble_learning
 ETL_engineering
 ML_callbacks
 ML_datasetmaster
+ML_evaluation_multi
 ML_evaluation
 ML_inference
 ML_models

{dragon_ml_toolbox-7.0.0.dist-info → dragon_ml_toolbox-8.1.0.dist-info}/RECORD

@@ -1,25 +1,27 @@
-dragon_ml_toolbox-7.0.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-7.0.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+dragon_ml_toolbox-8.1.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-8.1.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
 ml_tools/ETL_engineering.py,sha256=4wwZXi9_U7xfCY70jGBaKniOeZ0m75ppxWpQBd_DmLc,39369
 ml_tools/GUI_tools.py,sha256=n4ZZ5kEjwK5rkOCFJE41HeLFfjhpJVLUSzk9Kd9Kr_0,45410
 ml_tools/MICE_imputation.py,sha256=oFHg-OytOzPYTzBR_wIRHhP71cMn3aupDeT59ABsXlQ,11576
 ml_tools/ML_callbacks.py,sha256=noedVMmHZ72Odbg28zqx5wkhhvX2v-jXicKE_NCAiqU,13838
-ml_tools/ML_datasetmaster.py,sha256=dqda1E4ZEdSBwpRpdCO7pTLWcD6hzp-LzwreDRlNQdg,26452
-ml_tools/ML_evaluation.py,sha256=lTynGYqp3nAKc3kJDc7DDuWLYXW395zbWAZqTicQm9U,15949
-ml_tools/ML_inference.py,sha256=ctgVtpsnQw9OZ-lxIRih93u2JRHBq5zzVtaYOQrZ5eA,14465
-ml_tools/ML_models.py,sha256=NhlRHL_eoAQDih59SpoCmdNXLiLK6ZzS02tV_vYqko0,28159
+ml_tools/ML_datasetmaster.py,sha256=tN-GBPEwXRWFBT8r8K0v9b3Bd77DhqSH5FkjDP6BHTw,28847
+ml_tools/ML_evaluation.py,sha256=BER5dOvSTySNzO92gm8tIpqJ5vT-s0iHMmaoly1uUH8,16018
+ml_tools/ML_evaluation_multi.py,sha256=uVtKGYWgOLv34Xj_jz6E_HAYzNb0HwRbMwA8oFZWpUk,12395
+ml_tools/ML_inference.py,sha256=hwtAdyDCE1xtqLgJgyOTAPck0eTmkOCJK1cM_IJSdck,22824
+ml_tools/ML_models.py,sha256=xZiSFh7S6eitl-VjjvNpsikojDvurK8n_ueLEh6_5pM,27979
 ml_tools/ML_optimization.py,sha256=GX-qZ2mCI3gWRCTP5w7lXrZpfGle3J_mE0O68seIoio,13475
 ml_tools/ML_scaler.py,sha256=pGkp1nUpeuoBvbq5hUkieQdxex6kNef1mEbeS_HUCJs,7471
-ml_tools/ML_trainer.py,sha256=DrGF7fTbYNOa34v5lN__770F59ZJ_75t3vnW_8GRfwA,18255
+ml_tools/ML_trainer.py,sha256=6JSmEQaCPSo-S_5plNBTPw-SYgzZpyMNwiqpShJf7qU,23726
 ml_tools/PSO_optimization.py,sha256=9Y074d-B5h4Wvp9YPiy6KAeXM-Yv6Il3gWalKvOLVgo,22705
 ml_tools/RNN_forecast.py,sha256=2CyjBLSYYc3xLHxwLXUmP5Qv8AmV1OB_EndETNX1IBk,1956
 ml_tools/SQL.py,sha256=bkSTmMV4CtEqa67hApYWaRxTqwAlKIc5_b28P1bnDwg,10475
 ml_tools/VIF_factor.py,sha256=2nUMupfUoogf8o6ghoFZk_OwWhFXU0R3C9Gj0HOlI14,10415
+ml_tools/_ML_optimization_multi.py,sha256=DrNG3Vf1uUw-3CpYfXREgSGuR4dTpLWY1F3R9j-PYqQ,9816
 ml_tools/__init__.py,sha256=q0y9faQ6e17XCQ7eUiCZ1FJ4Bg5EQqLjZ9f_l5REUUY,41
 ml_tools/_logger.py,sha256=TpgYguxO-CWYqqgLW0tqFjtwZ58PE_W2OCfWNGZr0n0,1175
 ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/custom_logger.py,sha256=nyLRxaRxkqYOFdSjI0X2BWXB8C2IU18QfmqIFKqSedI,5820
-ml_tools/data_exploration.py,sha256=P4f8OpRa7Q4i-11nkppxXw5Lx2lwlpn20GwWBbN_xbM,23901
+ml_tools/data_exploration.py,sha256=RuMHWagXrSQi1MzAMlYeBeVg7UxhVvEq8gJ9bIam2BM,27103
 ml_tools/ensemble_evaluation.py,sha256=wnqoTPg4WYWf2A8z5XT0eSlW4snEuLCXQVj88sZKzQ4,24683
 ml_tools/ensemble_inference.py,sha256=rtU7eUaQne615n2g7IHZCJI-OvrBCcjxbTkEIvtCGFQ,9414
 ml_tools/ensemble_learning.py,sha256=dAyFgSTyvxJWjc_enJ_8EUoWwiekBeoNyJNxVY-kcUU,21868
@@ -28,7 +30,7 @@ ml_tools/keys.py,sha256=HtPG8-MWh89C32A7eIlfuuA-DLwkxGkoDfwR2TGN9CQ,1074
 ml_tools/optimization_tools.py,sha256=EL5tgNFwRo-82pbRE1CFVy9noNhULD7wprWuKadPheg,5090
 ml_tools/path_manager.py,sha256=Z8e7w3MPqQaN8xmTnKuXZS6CIW59BFwwqGhGc00sdp4,13692
 ml_tools/utilities.py,sha256=LqXXTovaHbA5AOKRk6Ru6DgAPAM0wPfYU70kUjYBryo,19231
-dragon_ml_toolbox-7.0.0.dist-info/METADATA,sha256=FrQMXquPof2JQ7Kt5B7q7yytVJ2rI8fDKFbytcvJ4nU,6758
-dragon_ml_toolbox-7.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-7.0.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-7.0.0.dist-info/RECORD,,
+dragon_ml_toolbox-8.1.0.dist-info/METADATA,sha256=qGTl4__H1ZsbyJHtExcDt14i8ziWXpEy2WaRAELPmTI,6778
+dragon_ml_toolbox-8.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-8.1.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-8.1.0.dist-info/RECORD,,

ml_tools/ML_datasetmaster.py

@@ -18,6 +18,7 @@ from .ML_scaler import PytorchScaler
 
 __all__ = [
     "DatasetMaker",
+    "DatasetMakerMulti",
     "VisionDatasetMaker",
     "SequenceMaker",
     "ResizeAspectFill",
@@ -57,71 +58,26 @@ class _PytorchDataset(Dataset):
         return self.features[index], self.labels[index]
 
 
-# Streamlined DatasetMaker version
-class DatasetMaker:
+# --- Abstract Base Class (New) ---
+# --- Abstract Base Class (Corrected) ---
+class _BaseDatasetMaker(ABC):
     """
-    A simplified dataset maker for pre-processed, numerical pandas DataFrames.
-
-    This class takes a DataFrame, automatically splits it into training and
-    testing sets, and converts them into PyTorch Datasets. It assumes the
-    target variable is the last column. It can also create, apply, and
-    save a PytorchScaler for standardizing continuous features.
-    
-    Attributes:
-        `scaler` -> PytorchScaler | None
-        `train_dataset` -> PyTorch Dataset
-        `test_dataset`  -> PyTorch Dataset
-        `feature_names` -> list[str]
-        `target_name`   -> str
-        `id` -> str | None
-        
-    The ID can be manually set to any string if needed, it is `None` by default.
+    Abstract base class for dataset makers. Contains shared logic for
+    splitting, scaling, and accessing datasets to reduce code duplication.
     """
-    def __init__(self, 
-                 pandas_df: pandas.DataFrame, 
-                 kind: Literal["regression", "classification"], 
-                 test_size: float = 0.2, 
-                 random_state: int = 42,
-                 scaler: Optional[PytorchScaler] = None,
-                 continuous_feature_columns: Optional[Union[List[int], List[str]]] = None):
-        """
-        Args:
-            pandas_df (pandas.DataFrame): The pre-processed input DataFrame with numerical data.
-            kind (Literal["regression", "classification"]): The type of ML task. This determines the data type of the labels.
-            test_size (float): The proportion of the dataset to allocate to the test split.
-            random_state (int): The seed for the random number generator for reproducibility.
-            scaler (PytorchScaler | None): A pre-fitted PytorchScaler instance.
-            continuous_feature_columns (List[int] | List[str] | None): Column indices or names of continuous features to scale. If provided creates a new PytorchScaler.
-        """
-        # Validation
-        if not isinstance(pandas_df, pandas.DataFrame):
-            raise TypeError("Input must be a pandas.DataFrame.")
-        if kind not in ["regression", "classification"]:
-            raise ValueError("`kind` must be 'regression' or 'classification'.")
-
-        # 1. Identify features and target
-        features = pandas_df.iloc[:, :-1]
-        target = pandas_df.iloc[:, -1]
-
-        self._feature_names = features.columns.tolist()
-        self._target_name = str(target.name)
-        
-        #set id
+    def __init__(self):
+        self._train_ds: Optional[Dataset] = None
+        self._test_ds: Optional[Dataset] = None
+        self.scaler: Optional[PytorchScaler] = None
         self._id: Optional[str] = None
-        # set scaler
-        self.scaler = scaler
-
-        # 2. Split the data
-        X_train, X_test, y_train, y_test = train_test_split(
-            features, target, test_size=test_size, random_state=random_state
-        )
-
-        self._X_train_shape = X_train.shape
-        self._X_test_shape = X_test.shape
-        self._y_train_shape = y_train.shape
-        self._y_test_shape = y_test.shape
-        
-        # 3. Handle Column to Index Conversion
+        self._feature_names: List[str] = []
+        self._X_train_shape = (0,0)
+        self._X_test_shape = (0,0)
+        self._y_train_shape = (0,)
+        self._y_test_shape = (0,)
+
+    def _prepare_scaler(self, X_train: pandas.DataFrame, y_train: Union[pandas.Series, pandas.DataFrame], X_test: pandas.DataFrame, label_dtype: torch.dtype, continuous_feature_columns: Optional[Union[List[int], List[str]]]):
+        """Internal helper to fit and apply a PytorchScaler."""
         continuous_feature_indices: Optional[List[int]] = None
         if continuous_feature_columns:
             if all(isinstance(c, str) for c in continuous_feature_columns):
@@ -129,108 +85,201 @@ class DatasetMaker:
                 try:
                     continuous_feature_indices = [name_to_idx[name] for name in continuous_feature_columns] # type: ignore
                 except KeyError as e:
-                    raise ValueError(f"Feature column '{e.args[0]}' not found in DataFrame.")
+                    raise ValueError(f"Feature column '{e.args[0]}' not found.")
             elif all(isinstance(c, int) for c in continuous_feature_columns):
                 continuous_feature_indices = continuous_feature_columns # type: ignore
             else:
                 raise TypeError("`continuous_feature_columns` must be a list of all strings or all integers.")
-        
-        # 4. Handle Scaling
+
         X_train_values = X_train.values
         X_test_values = X_test.values
-        
-        # If no scaler is provided, fit a new one from the training data
-        if self.scaler is None:
-            if continuous_feature_indices:
-                _LOGGER.info("Feature indices provided. Fitting a new PytorchScaler on training data.")
-                # A temporary dataset is needed for the PytorchScaler.fit method
-                temp_label_dtype = torch.float32 if kind == "regression" else torch.int64
-                temp_train_ds = _PytorchDataset(X_train_values, y_train.values, labels_dtype=temp_label_dtype)
-                self.scaler = PytorchScaler.fit(temp_train_ds, continuous_feature_indices)
-        
-        # If a scaler exists (either passed in or just fitted), apply it
+
+        if self.scaler is None and continuous_feature_indices:
+            _LOGGER.info("Fitting a new PytorchScaler on training data.")
+            temp_train_ds = _PytorchDataset(X_train_values, y_train, label_dtype) # type: ignore
+            self.scaler = PytorchScaler.fit(temp_train_ds, continuous_feature_indices)
+
         if self.scaler and self.scaler.mean_ is not None:
             _LOGGER.info("Applying scaler transformation to train and test feature sets.")
             X_train_tensor = self.scaler.transform(torch.tensor(X_train_values, dtype=torch.float32))
             X_test_tensor = self.scaler.transform(torch.tensor(X_test_values, dtype=torch.float32))
-            # Convert back to numpy for the _PytorchDataset class
-            X_train_values = X_train_tensor.numpy()
-            X_test_values = X_test_tensor.numpy()
+            return X_train_tensor.numpy(), X_test_tensor.numpy()
 
-        # 5. Convert to final PyTorch Datasets
-        label_dtype = torch.float32 if kind == "regression" else torch.int64
-        self._train_ds = _PytorchDataset(X_train_values, y_train.values, labels_dtype=label_dtype)
-        self._test_ds = _PytorchDataset(X_test_values, y_test.values, labels_dtype=label_dtype)
+        return X_train_values, X_test_values
 
     @property
     def train_dataset(self) -> Dataset:
-        """Returns the training PyTorch dataset."""
+        if self._train_ds is None: raise RuntimeError("Dataset not yet created.")
         return self._train_ds
 
     @property
     def test_dataset(self) -> Dataset:
-        """Returns the testing PyTorch dataset."""
+        if self._test_ds is None: raise RuntimeError("Dataset not yet created.")
         return self._test_ds
 
     @property
     def feature_names(self) -> list[str]:
-        """Returns the list of feature column names."""
         return self._feature_names
 
-    @property
-    def target_name(self) -> str:
-        """Returns the name of the target column."""
-        return self._target_name
-    
     @property
     def id(self) -> Optional[str]:
-        """Returns the object identifier if any."""
         return self._id
-    
+
     @id.setter
     def id(self, dataset_id: str):
-        """Sets the ID value"""
-        if not isinstance(dataset_id, str):
-            raise ValueError(f"Dataset ID '{type(dataset_id)}' is not a string.")
+        if not isinstance(dataset_id, str): raise ValueError("ID must be a string.")
         self._id = dataset_id
 
     def dataframes_info(self) -> None:
-        """Prints the shape information of the split pandas DataFrames."""
-        print("--- Original DataFrame Shapes After Split ---")
-        print(f"  X_train shape: {self._X_train_shape}")
-        print(f"  y_train shape: {self._y_train_shape}\n")
-        print(f"  X_test shape:  {self._X_test_shape}")
-        print(f"  y_test shape:  {self._y_test_shape}")
-        print("-------------------------------------------")
-        
+        print("--- DataFrame Shapes After Split ---")
+        print(f"  X_train shape: {self._X_train_shape}, y_train shape: {self._y_train_shape}")
+        print(f"  X_test shape:  {self._X_test_shape}, y_test shape:  {self._y_test_shape}")
+        print("------------------------------------")
+    
     def save_feature_names(self, directory: Union[str, Path], verbose: bool=True) -> None:
         """Saves a list of feature names as a text file"""
         save_list_strings(list_strings=self._feature_names,
                           directory=directory,
                           filename="feature_names",
-                          verbose=verbose)
-        
+                          verbose=verbose)    
+
     def save_scaler(self, save_dir: Union[str, Path]):
         """
         Saves the fitted PytorchScaler's state to a .pth file.
 
-        The filename is automatically generated based on the target name.
+        The filename is automatically generated based on the dataset id.
         
         Args:
             save_dir (str | Path): The directory where the scaler will be saved.
         """
-        if not self.scaler:
-            _LOGGER.error("❌ No scaler was fitted or provided.")
-            return
-
+        if not self.scaler: raise RuntimeError("No scaler was fitted or provided.")
+        if not self.id: raise ValueError("Must set the `id` before saving scaler.")
         save_path = make_fullpath(save_dir, make=True, enforce="directory")
-        
-        # Sanitize the target name for use in a filename
-        sanitized_target = sanitize_filename(self.target_name)
-        filename = f"scaler_{sanitized_target}.pth"
-        
+        sanitized_id = sanitize_filename(self.id)
+        filename = f"scaler_{sanitized_id}.pth"
         filepath = save_path / filename
         self.scaler.save(filepath)
+        _LOGGER.info(f"Scaler for dataset '{self.id}' saved to '{filepath.name}'.")
+
+
+# Single target dataset
+class DatasetMaker(_BaseDatasetMaker):
+    """
+    Dataset maker for pre-processed, numerical pandas DataFrames with a single target column.
+
+    This class takes a DataFrame, automatically splits it into training and
+    testing sets, and converts them into PyTorch Datasets. It assumes the
+    target variable is the last column. It can also create, apply, and
+    save a PytorchScaler for standardizing continuous features.
+    
+    Attributes:
+        `scaler` -> PytorchScaler | None
+        `train_dataset` -> PyTorch Dataset
+        `test_dataset`  -> PyTorch Dataset
+        `feature_names` -> list[str]
+        `target_name`   -> str
+        `id` -> str
+        
+    The ID can be manually set to any string if needed, it is the target name by default.
+    """
+    def __init__(self,
+                 pandas_df: pandas.DataFrame,
+                 kind: Literal["regression", "classification"],
+                 test_size: float = 0.2,
+                 random_state: int = 42,
+                 scaler: Optional[PytorchScaler] = None,
+                 continuous_feature_columns: Optional[Union[List[int], List[str]]] = None):
+        """
+        Args:
+            pandas_df (pandas.DataFrame): The pre-processed input DataFrame with numerical data.
+            kind (Literal["regression", "classification"]): The type of ML task. This determines the data type of the labels.
+            test_size (float): The proportion of the dataset to allocate to the test split.
+            random_state (int): The seed for the random number generator for reproducibility.
+            scaler (PytorchScaler | None): A pre-fitted PytorchScaler instance.
+            continuous_feature_columns (List[int] | List[str] | None): Column indices or names of continuous features to scale. If provided creates a new PytorchScaler.
+        """
+        super().__init__()
+        self.scaler = scaler
+        
+        # --- 1. Identify features and target (single-target logic) ---
+        features = pandas_df.iloc[:, :-1]
+        target = pandas_df.iloc[:, -1]
+        self._feature_names = features.columns.tolist()
+        self._target_name = str(target.name)
+        self._id = self._target_name
+
+        # --- 2. Split ---
+        X_train, X_test, y_train, y_test = train_test_split(
+            features, target, test_size=test_size, random_state=random_state
+        )
+        self._X_train_shape, self._X_test_shape = X_train.shape, X_test.shape
+        self._y_train_shape, self._y_test_shape = y_train.shape, y_test.shape
+        
+        label_dtype = torch.float32 if kind == "regression" else torch.int64
+
+        # --- 3. Scale ---
+        X_train_final, X_test_final = self._prepare_scaler(
+            X_train, y_train, X_test, label_dtype, continuous_feature_columns
+        )
+        
+        # --- 4. Create Datasets ---
+        self._train_ds = _PytorchDataset(X_train_final, y_train.values, label_dtype)
+        self._test_ds = _PytorchDataset(X_test_final, y_test.values, label_dtype)
+
+    @property
+    def target_name(self) -> str:
+        return self._target_name
+
+
+# --- New Multi-Target Class ---
+class DatasetMakerMulti(_BaseDatasetMaker):
+    """
+    Dataset maker for pre-processed, numerical pandas DataFrames with a multiple target columns.
+
+    This class takes a DataFrame, automatically splits it into training and testing sets, and converts them into PyTorch Datasets.
+    """
+    def __init__(self,
+                 pandas_df: pandas.DataFrame,
+                 target_columns: List[str],
+                 test_size: float = 0.2,
+                 random_state: int = 42,
+                 scaler: Optional[PytorchScaler] = None,
+                 continuous_feature_columns: Optional[Union[List[int], List[str]]] = None):
+        """
+        Args:
+            pandas_df (pandas.DataFrame): The pre-processed input DataFrame with numerical data.
+            target_columns (list[str]): List of target column names.
+            test_size (float): The proportion of the dataset to allocate to the test split.
+            random_state (int): The seed for the random number generator for reproducibility.
+            scaler (PytorchScaler | None): A pre-fitted PytorchScaler instance.
+            continuous_feature_columns (List[int] | List[str] | None): Column indices or names of continuous features to scale. If provided creates a new PytorchScaler.
+        """
+        super().__init__()
+        self.scaler = scaler
+
+        self._target_names = target_columns
+        self._feature_names = [col for col in pandas_df.columns if col not in target_columns]
+        features = pandas_df[self._feature_names]
+        target = pandas_df[self._target_names]
+
+        X_train, X_test, y_train, y_test = train_test_split(
+            features, target, test_size=test_size, random_state=random_state
+        )
+        self._X_train_shape, self._X_test_shape = X_train.shape, X_test.shape
+        self._y_train_shape, self._y_test_shape = y_train.shape, y_test.shape
+        
+        label_dtype = torch.float32
+
+        X_train_final, X_test_final = self._prepare_scaler(
+            X_train, y_train, X_test, label_dtype, continuous_feature_columns
+        )
+        
+        self._train_ds = _PytorchDataset(X_train_final, y_train, label_dtype)
+        self._test_ds = _PytorchDataset(X_test_final, y_test, label_dtype)
+
+    @property
+    def target_names(self) -> list[str]:
+        return self._target_names
 
 
 # --- Private Base Class ---

ml_tools/ML_evaluation.py

@@ -249,8 +249,11 @@ def regression_metrics(y_true: np.ndarray, y_pred: np.ndarray, save_dir: Union[s
     plt.close(fig_hist)
 
 
-def shap_summary_plot(model, background_data: Union[torch.Tensor,np.ndarray], instances_to_explain: Union[torch.Tensor,np.ndarray], 
-                      feature_names: Optional[list[str]], save_dir: Union[str, Path]):
+def shap_summary_plot(model, 
+                      background_data: Union[torch.Tensor,np.ndarray], 
+                      instances_to_explain: Union[torch.Tensor,np.ndarray], 
+                      feature_names: Optional[list[str]], 
+                      save_dir: Union[str, Path]):
     """
     Calculates SHAP values and saves summary plots and data.