dragon-ml-toolbox 5.0.0__py3-none-any.whl → 5.1.0__py3-none-any.whl

{dragon_ml_toolbox-5.0.0.dist-info → dragon_ml_toolbox-5.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 5.0.0
+Version: 5.1.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
@@ -268,5 +268,5 @@ After installation, import modules like this:
 
 ```python
 from ml_tools.utilities import serialize_object, deserialize_object
-from ml_tools.custom_logger import custom_logger
+from ml_tools import custom_logger
 ```

{dragon_ml_toolbox-5.0.0.dist-info → dragon_ml_toolbox-5.1.0.dist-info}/RECORD

@@ -1,10 +1,10 @@
-dragon_ml_toolbox-5.0.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-5.0.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+dragon_ml_toolbox-5.1.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-5.1.0.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=b6ZTs8RedXFifOpuMCzr68xM16mCBVh1Ua6kcGfiVtg,11462
 ml_tools/ML_callbacks.py,sha256=0a-Rbr0Xp_B1FNopOKBBmuJ4MqazS5JgDiT7wx1dHvE,13161
-ml_tools/ML_datasetmaster.py,sha256=_tNC2v98eCQGr3nMW_EFs83TRgRme8Uc7ttg1vosmQU,30106
+ml_tools/ML_datasetmaster.py,sha256=jrRK4fuVhRse4fJm_p3as5YPNXssT4rd6qYR6gJvxls,33327
 ml_tools/ML_evaluation.py,sha256=4dVqe6JF1Ukmk1sAcY8E5EG1oB1_oy2HXE5OT-pZwCs,10273
 ml_tools/ML_inference.py,sha256=Fh-X2UQn3AznWBjf-7iPSxwE-EzkGQm1VEIRUAkURmE,5336
 ml_tools/ML_optimization.py,sha256=u3H-TYGycKDdog-njkMfiAxd8TBtmGeLLFplBPRmmxk,10057
@@ -26,7 +26,7 @@ ml_tools/keys.py,sha256=kK9UF-hek2VcPGFILCKl5geoN6flmMOu7IzhdEA6z5Y,1068
 ml_tools/optimization_tools.py,sha256=MuT4OG7_r1QqLUti-yYix7QeCpglezD0oe9BDCq0QXk,5086
 ml_tools/path_manager.py,sha256=Z8e7w3MPqQaN8xmTnKuXZS6CIW59BFwwqGhGc00sdp4,13692
 ml_tools/utilities.py,sha256=mz-M351DzxWxnYVcLX-7ZQ6c-RGoCV9g4VTS9Qif2Es,18348
-dragon_ml_toolbox-5.0.0.dist-info/METADATA,sha256=N9-274zMIAQmEfaNoET6Ydj96huYS9_twKLBnl37bic,6639
-dragon_ml_toolbox-5.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-5.0.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-5.0.0.dist-info/RECORD,,
+dragon_ml_toolbox-5.1.0.dist-info/METADATA,sha256=I9LBhqNEGmKUyWRKUQM-XW1Hq8h1FC740hq_b4kdgQA,6625
+dragon_ml_toolbox-5.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-5.1.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-5.1.0.dist-info/RECORD,,

ml_tools/ML_datasetmaster.py

@@ -21,6 +21,7 @@ from ._script_info import _script_info
 # --- public-facing API ---
 __all__ = [
     "DatasetMaker",
+    "SimpleDatasetMaker",
     "VisionDatasetMaker",
     "SequenceMaker",
     "ResizeAspectFill",
@@ -328,7 +329,7 @@ class DatasetMaker(_BaseMaker):
 
         return self.scaler.inverse_transform(data_np)
 
-    def get_datasets(self) -> Tuple[_PytorchDataset, _PytorchDataset]:
+    def get_datasets(self) -> Tuple[Dataset, Dataset]:
         """Primary method to get the final PyTorch Datasets."""
         if not self._is_split:
             raise RuntimeError("Data has not been split yet. Call .split_data() or .process() first.")
@@ -370,6 +371,95 @@ class DatasetMaker(_BaseMaker):
         return pandas.DataFrame(full_tensor.numpy(), columns=new_columns, index=cat_df.index)
 
 
+# Streamlined DatasetMaker version
+class SimpleDatasetMaker:
+    """
+    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.
+
+    Args:
+        pandas_df (pandas.DataFrame): The pre-processed input DataFrame with numerical data.
+        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.
+        id (str | None): An optional object identifier.
+    """
+    def __init__(self, pandas_df: pandas.DataFrame, test_size: float = 0.2, random_state: int = 42, id: Optional[str]=None):
+        """          
+        Attributes:
+            `train_dataset` -> PyTorch Dataset
+            `test_dataset`  -> PyTorch Dataset
+            `feature_names` -> list[str]
+            `target_name`   -> str
+            `id` -> str | None
+        """
+        
+        if not isinstance(pandas_df, pandas.DataFrame):
+            raise TypeError("Input must be a pandas.DataFrame.")
+        
+        #set id
+        self._id = id
+
+        # 1. Identify features and target
+        features = pandas_df.iloc[:, :-1]
+        target = pandas_df.iloc[:, -1]
+
+        self._feature_names = features.columns.tolist()
+        self._target_name = target.name
+
+        # 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. Convert to PyTorch Datasets
+        self._train_ds = _PytorchDataset(X_train.values, y_train.values)
+        self._test_ds = _PytorchDataset(X_test.values, y_test.values)
+
+    @property
+    def train_dataset(self) -> Dataset:
+        """Returns the training PyTorch dataset."""
+        return self._train_ds
+
+    @property
+    def test_dataset(self) -> Dataset:
+        """Returns the testing PyTorch dataset."""
+        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 str(self._target_name)
+    
+    @property
+    def id(self) -> Optional[str]:
+        """Returns teh object identifier if any."""
+        return self._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("-------------------------------------------")
+
+
 # --- VisionDatasetMaker ---
 class VisionDatasetMaker(_BaseMaker):
     """