Skip to content

lightdatamodule

LightDataModule

Bases: LightningDataModule

A LightningDataModule for handling data.

Parameters:

Name Type Description Default
batch_size int

The batch size. Required.

 required
dataset Dataset

The dataset from the torch.utils.data Dataset class. It must implement three functions: init, len, and getitem. Required.

 required
test_size float

The test size. if test_size is float, then train_size is 1 - test_size. If test_size is int, then train_size is len(data_full) - test_size. Train size will be split into train and validation sets. So if test size is 0.7, the 0.7 train size will be split into 0.7 * 0.7 = 0.49 train set amd 0.7 * 0.3 = 0.21 validation set.

 required
test_seed int

The test seed. Defaults to 42.

 42
num_workers int

The number of workers. Defaults to 0.

 0
scaler object

The spot scaler object (e.g. TorchStandardScaler). Defaults to None.

 None

Attributes:

Name Type Description
batch_size int

The batch size.
data_full Dataset

The full dataset.
data_test Dataset

The test dataset.
data_train Dataset

The training dataset.
data_val Dataset

The validation dataset.
num_workers int

The number of workers.
test_seed int

The test seed.
test_size float

The test size.

Methods:

Name Description
prepare_data

Usually used for downloading the data. Here: Does nothing, i.e., pass.
setup

Optional[str] = None): Performs the training, validation, and test split.
train_dataloader

Returns a DataLoader instance for the training set.
val_dataloader

Returns a DataLoader instance for the validation set.
test_dataloader

Returns a DataLoader instance for the test set.

Examples:

>>> from spotpython.data.lightdatamodule import LightDataModule
    from spotpython.data.csvdataset import CSVDataset
    from spotpython.utils.scaler import TorchStandardScaler
    import torch
    # data.csv is simple csv file with 11 samples
    dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
    scaler = TorchStandardScaler()
    data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5, scaler=scaler)
    data_module.setup()
    print(f"Training set size: {len(data_module.data_train)}")
    print(f"Validation set size: {len(data_module.data_val)}")
    print(f"Test set size: {len(data_module.data_test)}")
    full_train_size: 0.5
    val_size: 0.25
    train_size: 0.25
    test_size: 0.5
    Training set size: 3
    Validation set size: 3
    Test set size: 6
References

See https://lightning.ai/docs/pytorch/stable/data/datamodule.html

Source code in spotpython/data/lightdatamodule.py 
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
class LightDataModule(L.LightningDataModule):
    """
    A LightningDataModule for handling data.

    Args:
        batch_size (int):
            The batch size. Required.
        dataset (torch.utils.data.Dataset):
            The dataset from the torch.utils.data Dataset class.
            It  must implement three functions: __init__, __len__, and __getitem__.
            Required.
        test_size (float):
            The test size. if test_size is float, then train_size is 1 - test_size.
            If test_size is int, then train_size is len(data_full) - test_size.
            Train size will be split into train and validation sets.
            So if test size is 0.7, the 0.7 train size will be split into 0.7 * 0.7 = 0.49 train set
            amd 0.7 * 0.3 = 0.21 validation set.
        test_seed (int):
            The test seed. Defaults to 42.
        num_workers (int):
            The number of workers. Defaults to 0.
        scaler (object):
            The spot scaler object (e.g. TorchStandardScaler). Defaults to None.

    Attributes:
        batch_size (int): The batch size.
        data_full (Dataset): The full dataset.
        data_test (Dataset): The test dataset.
        data_train (Dataset): The training dataset.
        data_val (Dataset): The validation dataset.
        num_workers (int): The number of workers.
        test_seed (int): The test seed.
        test_size (float): The test size.

    Methods:
        prepare_data(self):
            Usually used for downloading the data. Here: Does nothing, i.e., pass.
        setup(self, stage: Optional[str] = None):
            Performs the training, validation, and test split.
        train_dataloader():
            Returns a DataLoader instance for the training set.
        val_dataloader():
            Returns a DataLoader instance for the validation set.
        test_dataloader():
            Returns a DataLoader instance for the test set.

    Examples:
        >>> from spotpython.data.lightdatamodule import LightDataModule
            from spotpython.data.csvdataset import CSVDataset
            from spotpython.utils.scaler import TorchStandardScaler
            import torch
            # data.csv is simple csv file with 11 samples
            dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
            scaler = TorchStandardScaler()
            data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5, scaler=scaler)
            data_module.setup()
            print(f"Training set size: {len(data_module.data_train)}")
            print(f"Validation set size: {len(data_module.data_val)}")
            print(f"Test set size: {len(data_module.data_test)}")
            full_train_size: 0.5
            val_size: 0.25
            train_size: 0.25
            test_size: 0.5
            Training set size: 3
            Validation set size: 3
            Test set size: 6

    References:
        See https://lightning.ai/docs/pytorch/stable/data/datamodule.html

    """

    def __init__(
        self,
        batch_size: int,
        dataset: object,
        test_size: float,
        test_seed: int = 42,
        num_workers: int = 0,
        scaler: Optional[object] = None,
        verbosity: int = 0,
    ):
        super().__init__()
        self.batch_size = batch_size
        self.data_full = dataset
        self.test_size = test_size
        self.test_seed = test_seed
        self.num_workers = num_workers
        self.scaler = scaler
        self.verbosity = verbosity

    def transform_dataset(self, dataset) -> TensorDataset:
        """Applies the scaler transformation to the dataset.

        Args:
            dataset (List[Tuple[torch.Tensor, Any]]): The dataset to transform, consisting of data and target pairs.

        Returns:
            TensorDataset: A PyTorch TensorDataset containing the transformed and cloned data and targets.

        Raises:
            ValueError: If the input data is not correctly formatted for transformation.
        """
        try:
            # Perform transformations on the data in a single iteration
            transformed_data = [(self.scaler.transform(data), target) for data, target in dataset]
            # Clone and detach data tensors
            data_tensors = [data.clone().detach() for data, _ in transformed_data]
            target_tensors = [target.clone().detach() for _, target in transformed_data]
            # Create a TensorDataset from the processed data
            return TensorDataset(torch.stack(data_tensors).squeeze(1), torch.stack(target_tensors))
        except Exception as e:
            raise ValueError(f"Error transforming dataset: {e}")

    def handle_scaling_and_transform(self) -> None:
        """
        Fits the scaler on the training data and transforms both training and validation datasets.
        This function is only called when self.scaler is not None.
        """
        # Ensure self.scaler is not None before proceeding
        if self.scaler is None:
            raise ValueError("Scaler object is required to perform scaling and transformation.")
        # Fit the scaler on training data
        scaler_train_data = torch.stack([self.data_train[i][0] for i in range(len(self.data_train))]).squeeze(1)
        if self.verbosity > 0:
            print(scaler_train_data.shape)
        self.scaler.fit(scaler_train_data)
        # Transform the training data
        self.data_train = self.transform_dataset(self.data_train)
        # Transform the validation data
        self.data_val = self.transform_dataset(self.data_val)

    def prepare_data(self) -> None:
        """Prepares the data for use."""
        # download
        pass

    def setup(self, stage: Optional[str] = None) -> None:
        """
        Splits the data for use in training, validation, and testing.
        Uses torch.utils.data.random_split() to split the data.
        Splitting is based on the test_size and test_seed.
        The test_size can be a float or an int.
        If a spotpython scaler object is defined, the data will be scaled.

        Args:
            stage (Optional[str]):
                The current stage. Can be "fit" (for training and validation), "test" (testing),
                or None (for all three stages). Defaults to None.

        Examples:
            >>> from spotpython.data.lightdatamodule import LightDataModule
                from spotpython.data.csvdataset import CSVDataset
                import torch
                dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
                data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
                data_module.setup()
                print(f"Training set size: {len(data_module.data_train)}")
                Training set size: 3

        """
        full_train_size, val_size, train_size, test_size = calculate_data_split(
            test_size=self.test_size,
            full_size=len(self.data_full),
            verbosity=self.verbosity,
            stage=stage,
        )

        # Assign train/val datasets for use in dataloaders
        if stage == "fit" or stage is None:
            if self.verbosity > 0:
                print(f"train_size: {train_size}, val_size: {val_size} used for train & val data.")
            generator_fit = torch.Generator().manual_seed(self.test_seed)
            self.data_train, self.data_val, _ = random_split(self.data_full, [train_size, val_size, test_size], generator=generator_fit)
            # Handle scaling and transformation if scaler is provided
            if self.scaler is not None:
                self.handle_scaling_and_transform()

        # Assign test dataset for use in dataloader(s)
        if stage == "test" or stage is None:
            if self.verbosity > 0:
                print(f"test_size: {test_size} used for test dataset.")
            generator_test = torch.Generator().manual_seed(self.test_seed)
            self.data_test, _ = random_split(self.data_full, [test_size, full_train_size], generator=generator_test)
            if self.scaler is not None:
                # Transform the test data
                self.data_test = self.transform_dataset(self.data_test)

        # Assign pred dataset for use in dataloader(s)
        if stage == "predict" or stage is None:
            if self.verbosity > 0:
                print(f"test_size: {test_size} used for predict dataset.")
            generator_predict = torch.Generator().manual_seed(self.test_seed)
            self.data_predict, _ = random_split(self.data_full, [test_size, full_train_size], generator=generator_predict)
            if self.scaler is not None:
                # Transform the predict data
                self.data_predict = self.transform_dataset(self.data_predict)

    def train_dataloader(self) -> DataLoader:
        """
        Returns the training dataloader, i.e., a pytorch DataLoader instance
        using the training dataset.

        Returns:
            DataLoader: The training dataloader.

        Examples:
            >>> from spotpython.data.lightdatamodule import LightDataModule
                from spotpython.data.csvdataset import CSVDataset
                import torch
                dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
                data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
                data_module.setup()
                print(f"Training set size: {len(data_module.data_train)}")
                Training set size: 3

        """
        if self.verbosity > 0:
            print(f"LightDataModule.train_dataloader(). data_train size: {len(self.data_train)}")
        # print(f"LightDataModule: train_dataloader(). batch_size: {self.batch_size}")
        # print(f"LightDataModule: train_dataloader(). num_workers: {self.num_workers}")
        return DataLoader(self.data_train, batch_size=self.batch_size, num_workers=self.num_workers)

    def val_dataloader(self) -> DataLoader:
        """
        Returns the validation dataloader, i.e., a pytorch DataLoader instance
        using the validation dataset.

        Returns:
            DataLoader: The validation dataloader.

        Examples:
            >>> from spotpython.data.lightdatamodule import LightDataModule
                from spotpython.data.csvdataset import CSVDataset
                import torch
                dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
                data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
                data_module.setup()
                print(f"Training set size: {len(data_module.data_val)}")
                Training set size: 3
        """
        if self.verbosity > 0:
            print(f"LightDataModule.val_dataloader(). Val. set size: {len(self.data_val)}")
        # print(f"LightDataModule: val_dataloader(). batch_size: {self.batch_size}")
        # print(f"LightDataModule: val_dataloader(). num_workers: {self.num_workers}")
        return DataLoader(self.data_val, batch_size=self.batch_size, num_workers=self.num_workers)

    def test_dataloader(self) -> DataLoader:
        """
        Returns the test dataloader, i.e., a pytorch DataLoader instance
        using the test dataset.

        Returns:
            DataLoader: The test dataloader.

        Examples:
            >>> from spotpython.data.lightdatamodule import LightDataModule
                from spotpython.data.csvdataset import CSVDataset
                import torch
                dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
                data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
                data_module.setup()
                print(f"Test set size: {len(data_module.data_test)}")
                Test set size: 6

        """
        if self.verbosity > 0:
            print(f"LightDataModule.test_dataloader(). Test set size: {len(self.data_test)}")
        # print(f"LightDataModule: test_dataloader(). batch_size: {self.batch_size}")
        # print(f"LightDataModule: test_dataloader(). num_workers: {self.num_workers}")
        return DataLoader(self.data_test, batch_size=self.batch_size, num_workers=self.num_workers)

    def predict_dataloader(self) -> DataLoader:
        """
        Returns the predict dataloader, i.e., a pytorch DataLoader instance
        using the predict dataset.

        Returns:
            DataLoader: The predict dataloader.

        Examples:
            >>> from spotpython.data.lightdatamodule import LightDataModule
                from spotpython.data.csvdataset import CSVDataset
                import torch
                dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
                data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
                data_module.setup()
                print(f"Predict set size: {len(data_module.data_predict)}")
                Predict set size: 6

        """
        if self.verbosity > 0:
            print(f"LightDataModule.predict_dataloader(). Predict set size: {len(self.data_predict)}")
        # print(f"LightDataModule: predict_dataloader(). batch_size: {self.batch_size}")
        # print(f"LightDataModule: predict_dataloader(). num_workers: {self.num_workers}")
        return DataLoader(self.data_predict, batch_size=len(self.data_predict), num_workers=self.num_workers)

handle_scaling_and_transform()

Fits the scaler on the training data and transforms both training and validation datasets. This function is only called when self.scaler is not None.

Source code in spotpython/data/lightdatamodule.py 
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
def handle_scaling_and_transform(self) -> None:
    """
    Fits the scaler on the training data and transforms both training and validation datasets.
    This function is only called when self.scaler is not None.
    """
    # Ensure self.scaler is not None before proceeding
    if self.scaler is None:
        raise ValueError("Scaler object is required to perform scaling and transformation.")
    # Fit the scaler on training data
    scaler_train_data = torch.stack([self.data_train[i][0] for i in range(len(self.data_train))]).squeeze(1)
    if self.verbosity > 0:
        print(scaler_train_data.shape)
    self.scaler.fit(scaler_train_data)
    # Transform the training data
    self.data_train = self.transform_dataset(self.data_train)
    # Transform the validation data
    self.data_val = self.transform_dataset(self.data_val)

predict_dataloader()

Returns the predict dataloader, i.e., a pytorch DataLoader instance using the predict dataset.

Returns:

Name Type Description
DataLoader DataLoader

The predict dataloader.

Examples:

>>> from spotpython.data.lightdatamodule import LightDataModule
    from spotpython.data.csvdataset import CSVDataset
    import torch
    dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
    data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
    data_module.setup()
    print(f"Predict set size: {len(data_module.data_predict)}")
    Predict set size: 6
Source code in spotpython/data/lightdatamodule.py 
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
def predict_dataloader(self) -> DataLoader:
    """
    Returns the predict dataloader, i.e., a pytorch DataLoader instance
    using the predict dataset.

    Returns:
        DataLoader: The predict dataloader.

    Examples:
        >>> from spotpython.data.lightdatamodule import LightDataModule
            from spotpython.data.csvdataset import CSVDataset
            import torch
            dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
            data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
            data_module.setup()
            print(f"Predict set size: {len(data_module.data_predict)}")
            Predict set size: 6

    """
    if self.verbosity > 0:
        print(f"LightDataModule.predict_dataloader(). Predict set size: {len(self.data_predict)}")
    # print(f"LightDataModule: predict_dataloader(). batch_size: {self.batch_size}")
    # print(f"LightDataModule: predict_dataloader(). num_workers: {self.num_workers}")
    return DataLoader(self.data_predict, batch_size=len(self.data_predict), num_workers=self.num_workers)

prepare_data()

Prepares the data for use.

Source code in spotpython/data/lightdatamodule.py 
140
141
142
143
def prepare_data(self) -> None:
    """Prepares the data for use."""
    # download
    pass

setup(stage=None)

Splits the data for use in training, validation, and testing. Uses torch.utils.data.random_split() to split the data. Splitting is based on the test_size and test_seed. The test_size can be a float or an int. If a spotpython scaler object is defined, the data will be scaled.

Parameters:

Name Type Description Default
stage Optional[str]

The current stage. Can be “fit” (for training and validation), “test” (testing), or None (for all three stages). Defaults to None.

 None

Examples:

>>> from spotpython.data.lightdatamodule import LightDataModule
    from spotpython.data.csvdataset import CSVDataset
    import torch
    dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
    data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
    data_module.setup()
    print(f"Training set size: {len(data_module.data_train)}")
    Training set size: 3
Source code in spotpython/data/lightdatamodule.py 
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
def setup(self, stage: Optional[str] = None) -> None:
    """
    Splits the data for use in training, validation, and testing.
    Uses torch.utils.data.random_split() to split the data.
    Splitting is based on the test_size and test_seed.
    The test_size can be a float or an int.
    If a spotpython scaler object is defined, the data will be scaled.

    Args:
        stage (Optional[str]):
            The current stage. Can be "fit" (for training and validation), "test" (testing),
            or None (for all three stages). Defaults to None.

    Examples:
        >>> from spotpython.data.lightdatamodule import LightDataModule
            from spotpython.data.csvdataset import CSVDataset
            import torch
            dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
            data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
            data_module.setup()
            print(f"Training set size: {len(data_module.data_train)}")
            Training set size: 3

    """
    full_train_size, val_size, train_size, test_size = calculate_data_split(
        test_size=self.test_size,
        full_size=len(self.data_full),
        verbosity=self.verbosity,
        stage=stage,
    )

    # Assign train/val datasets for use in dataloaders
    if stage == "fit" or stage is None:
        if self.verbosity > 0:
            print(f"train_size: {train_size}, val_size: {val_size} used for train & val data.")
        generator_fit = torch.Generator().manual_seed(self.test_seed)
        self.data_train, self.data_val, _ = random_split(self.data_full, [train_size, val_size, test_size], generator=generator_fit)
        # Handle scaling and transformation if scaler is provided
        if self.scaler is not None:
            self.handle_scaling_and_transform()

    # Assign test dataset for use in dataloader(s)
    if stage == "test" or stage is None:
        if self.verbosity > 0:
            print(f"test_size: {test_size} used for test dataset.")
        generator_test = torch.Generator().manual_seed(self.test_seed)
        self.data_test, _ = random_split(self.data_full, [test_size, full_train_size], generator=generator_test)
        if self.scaler is not None:
            # Transform the test data
            self.data_test = self.transform_dataset(self.data_test)

    # Assign pred dataset for use in dataloader(s)
    if stage == "predict" or stage is None:
        if self.verbosity > 0:
            print(f"test_size: {test_size} used for predict dataset.")
        generator_predict = torch.Generator().manual_seed(self.test_seed)
        self.data_predict, _ = random_split(self.data_full, [test_size, full_train_size], generator=generator_predict)
        if self.scaler is not None:
            # Transform the predict data
            self.data_predict = self.transform_dataset(self.data_predict)

test_dataloader()

Returns the test dataloader, i.e., a pytorch DataLoader instance using the test dataset.

Returns:

Name Type Description
DataLoader DataLoader

The test dataloader.

Examples:

>>> from spotpython.data.lightdatamodule import LightDataModule
    from spotpython.data.csvdataset import CSVDataset
    import torch
    dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
    data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
    data_module.setup()
    print(f"Test set size: {len(data_module.data_test)}")
    Test set size: 6
Source code in spotpython/data/lightdatamodule.py 
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
def test_dataloader(self) -> DataLoader:
    """
    Returns the test dataloader, i.e., a pytorch DataLoader instance
    using the test dataset.

    Returns:
        DataLoader: The test dataloader.

    Examples:
        >>> from spotpython.data.lightdatamodule import LightDataModule
            from spotpython.data.csvdataset import CSVDataset
            import torch
            dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
            data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
            data_module.setup()
            print(f"Test set size: {len(data_module.data_test)}")
            Test set size: 6

    """
    if self.verbosity > 0:
        print(f"LightDataModule.test_dataloader(). Test set size: {len(self.data_test)}")
    # print(f"LightDataModule: test_dataloader(). batch_size: {self.batch_size}")
    # print(f"LightDataModule: test_dataloader(). num_workers: {self.num_workers}")
    return DataLoader(self.data_test, batch_size=self.batch_size, num_workers=self.num_workers)

train_dataloader()

Returns the training dataloader, i.e., a pytorch DataLoader instance using the training dataset.

Returns:

Name Type Description
DataLoader DataLoader

The training dataloader.

Examples:

>>> from spotpython.data.lightdatamodule import LightDataModule
    from spotpython.data.csvdataset import CSVDataset
    import torch
    dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
    data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
    data_module.setup()
    print(f"Training set size: {len(data_module.data_train)}")
    Training set size: 3
Source code in spotpython/data/lightdatamodule.py 
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
def train_dataloader(self) -> DataLoader:
    """
    Returns the training dataloader, i.e., a pytorch DataLoader instance
    using the training dataset.

    Returns:
        DataLoader: The training dataloader.

    Examples:
        >>> from spotpython.data.lightdatamodule import LightDataModule
            from spotpython.data.csvdataset import CSVDataset
            import torch
            dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
            data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
            data_module.setup()
            print(f"Training set size: {len(data_module.data_train)}")
            Training set size: 3

    """
    if self.verbosity > 0:
        print(f"LightDataModule.train_dataloader(). data_train size: {len(self.data_train)}")
    # print(f"LightDataModule: train_dataloader(). batch_size: {self.batch_size}")
    # print(f"LightDataModule: train_dataloader(). num_workers: {self.num_workers}")
    return DataLoader(self.data_train, batch_size=self.batch_size, num_workers=self.num_workers)

transform_dataset(dataset)

Applies the scaler transformation to the dataset.

Parameters:

Name Type Description Default
dataset List[Tuple[Tensor, Any]]

The dataset to transform, consisting of data and target pairs.

 required

Returns:

Name Type Description
TensorDataset TensorDataset

A PyTorch TensorDataset containing the transformed and cloned data and targets.

Raises:

Type Description
ValueError

If the input data is not correctly formatted for transformation.
Source code in spotpython/data/lightdatamodule.py 
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
def transform_dataset(self, dataset) -> TensorDataset:
    """Applies the scaler transformation to the dataset.

    Args:
        dataset (List[Tuple[torch.Tensor, Any]]): The dataset to transform, consisting of data and target pairs.

    Returns:
        TensorDataset: A PyTorch TensorDataset containing the transformed and cloned data and targets.

    Raises:
        ValueError: If the input data is not correctly formatted for transformation.
    """
    try:
        # Perform transformations on the data in a single iteration
        transformed_data = [(self.scaler.transform(data), target) for data, target in dataset]
        # Clone and detach data tensors
        data_tensors = [data.clone().detach() for data, _ in transformed_data]
        target_tensors = [target.clone().detach() for _, target in transformed_data]
        # Create a TensorDataset from the processed data
        return TensorDataset(torch.stack(data_tensors).squeeze(1), torch.stack(target_tensors))
    except Exception as e:
        raise ValueError(f"Error transforming dataset: {e}")

val_dataloader()

Returns the validation dataloader, i.e., a pytorch DataLoader instance using the validation dataset.

Returns:

Name Type Description
DataLoader DataLoader

The validation dataloader.

Examples:

>>> from spotpython.data.lightdatamodule import LightDataModule
    from spotpython.data.csvdataset import CSVDataset
    import torch
    dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
    data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
    data_module.setup()
    print(f"Training set size: {len(data_module.data_val)}")
    Training set size: 3
Source code in spotpython/data/lightdatamodule.py 
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
def val_dataloader(self) -> DataLoader:
    """
    Returns the validation dataloader, i.e., a pytorch DataLoader instance
    using the validation dataset.

    Returns:
        DataLoader: The validation dataloader.

    Examples:
        >>> from spotpython.data.lightdatamodule import LightDataModule
            from spotpython.data.csvdataset import CSVDataset
            import torch
            dataset = CSVDataset(csv_file='data.csv', target_column='prognosis', feature_type=torch.long)
            data_module = LightDataModule(dataset=dataset, batch_size=5, test_size=0.5)
            data_module.setup()
            print(f"Training set size: {len(data_module.data_val)}")
            Training set size: 3
    """
    if self.verbosity > 0:
        print(f"LightDataModule.val_dataloader(). Val. set size: {len(self.data_val)}")
    # print(f"LightDataModule: val_dataloader(). batch_size: {self.batch_size}")
    # print(f"LightDataModule: val_dataloader(). num_workers: {self.num_workers}")
    return DataLoader(self.data_val, batch_size=self.batch_size, num_workers=self.num_workers)