Skip to content

california

CaliforniaHousing

Bases: Dataset

A PyTorch Dataset for regression. A toy data set from scikit-learn. Features: * MedInc median income in block group * HouseAge median house age in block group * AveRooms average number of rooms per household * AveBedrms average number of bedrooms per household * Population block group population * AveOccup average number of household members * Latitude block group latitude * Longitude block group longitude The target variable is the median house value for California districts, expressed in hundreds of thousands of Dollars ($100,000). Samples total: 20640, Dimensionality: 8, Features: real, Target: real 0.15 - 5. This dataset was derived from the 1990 U.S. census, using one row per census block group. A block group is the smallest geographical unit for which the U.S. Census Bureau publishes sample data (a block group typically has a population of 600 to 3,000 people).

Parameters:

Name Type Description Default
feature_type dtype

The data type of the features. Defaults to torch.float.

 float
target_type dtype

The data type of the targets. Defaults to torch.long.

 float
train bool

Whether the dataset is for training or not. Defaults to True.

 True
n_samples int

The number of samples of the dataset. Defaults to None, which means the entire dataset is used.

 None

Attributes:

Name Type Description
data Tensor

The data features.
targets Tensor

The data targets.

Examples:

>>> from torch.utils.data import DataLoader
    from spotpython.data.diabetes import Diabetes
    import torch
    dataset = Diabetes(feature_type=torch.float32, target_type=torch.float32)
    # Set batch size for DataLoader
    batch_size = 5
    # Create DataLoader
    dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=False)
    # Iterate over the data in the DataLoader
    for batch in dataloader:
        inputs, targets = batch
        print(f"Batch Size: {inputs.size(0)}")
        print("---------------")
        print(f"Inputs: {inputs}")
        print(f"Targets: {targets}")
Source code in spotpython/data/california.py 
  6
  7
  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
class CaliforniaHousing(Dataset):
    """
    A PyTorch Dataset for regression. A toy data set from scikit-learn.
    Features:
        * MedInc median income in block group
        * HouseAge median house age in block group
        * AveRooms average number of rooms per household
        * AveBedrms average number of bedrooms per household
        * Population block group population
        * AveOccup average number of household members
        * Latitude block group latitude
        * Longitude block group longitude
    The target variable is the median house value for California districts,
    expressed in hundreds of thousands of Dollars ($100,000).
    Samples total: 20640, Dimensionality: 8, Features: real, Target: real 0.15 - 5.
    This dataset was derived from the 1990 U.S. census, using one row per census block group.
    A block group is the smallest geographical unit for which the U.S. Census Bureau publishes sample data
    (a block group typically has a population of 600 to 3,000 people).

    Args:
        feature_type (torch.dtype): The data type of the features. Defaults to torch.float.
        target_type (torch.dtype): The data type of the targets. Defaults to torch.long.
        train (bool): Whether the dataset is for training or not. Defaults to True.
        n_samples (int): The number of samples of the dataset. Defaults to None, which means the entire dataset is used.

    Attributes:
        data (Tensor): The data features.
        targets (Tensor): The data targets.

    Examples:
        >>> from torch.utils.data import DataLoader
            from spotpython.data.diabetes import Diabetes
            import torch
            dataset = Diabetes(feature_type=torch.float32, target_type=torch.float32)
            # Set batch size for DataLoader
            batch_size = 5
            # Create DataLoader
            dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=False)
            # Iterate over the data in the DataLoader
            for batch in dataloader:
                inputs, targets = batch
                print(f"Batch Size: {inputs.size(0)}")
                print("---------------")
                print(f"Inputs: {inputs}")
                print(f"Targets: {targets}")
    """

    def __init__(
        self,
        feature_type: torch.dtype = torch.float,
        target_type: torch.dtype = torch.float,
        train: bool = True,
        n_samples: int = None,
    ) -> None:
        super().__init__()
        self.feature_type = feature_type
        self.target_type = target_type
        self.train = train
        self.n_samples = n_samples
        self.data, self.targets = self._load_data()

    def _load_data(self) -> tuple:
        """Loads the data from scikit-learn and returns the features and targets.

        Returns:
            tuple: A tuple containing the features and targets.

        Examples:
            >>> from spotpython.data.diabetes import Diabetes
                dataset = Diabetes()
                print(dataset.data.shape)
                print(dataset.targets.shape)
                torch.Size([442, 10])
                torch.Size([442])
        """
        feature_df, target_df = fetch_california_housing(return_X_y=True, as_frame=True)
        if self.n_samples is not None:
            feature_df = feature_df[: self.n_samples]
            target_df = target_df[: self.n_samples]
        # Convert DataFrames to PyTorch tensors
        feature_tensor = torch.tensor(feature_df.values, dtype=self.feature_type)
        target_tensor = torch.tensor(target_df.values, dtype=self.target_type)

        return feature_tensor, target_tensor

    def __getitem__(self, idx: int) -> tuple:
        """
        Returns the feature and target at the given index.

        Args:
            idx (int): The index.

        Returns:
            tuple: A tuple containing the feature and target at the given index.

        Examples:
            >>> from spotpython.light.csvdataset import CSVDataset
                dataset = CSVDataset(filename='./data/spotpython/data.csv', target_column='prognosis')
                print(dataset.data.shape)
                print(dataset.targets.shape)
                torch.Size([11, 65])
                torch.Size([11])
        """
        feature = self.data[idx]
        target = self.targets[idx]
        return feature, target

    def __len__(self) -> int:
        """
        Returns the length of the dataset.

        Returns:
            int: The length of the dataset.

        Examples:
            >>> from spotpython.light import CSVDataset
            >>> dataset = CSVDataset()
            >>> print(len(dataset))
            60000

        """
        return len(self.data)

    def extra_repr(self) -> str:
        """
        Returns a string representation of the dataset.

        Returns:
            str: A string representation of the dataset.

        Examples:
            >>> from spotpython.light import CSVDataset
            >>> dataset = CSVDataset()
            >>> print(dataset)
            Split: Train

        """
        split = "Train" if self.train else "Test"
        return f"Split: {split}"

__getitem__(idx)

Returns the feature and target at the given index.

Parameters:

Name Type Description Default
idx int

The index.

 required

Returns:

Name Type Description
tuple tuple

A tuple containing the feature and target at the given index.

Examples:

>>> from spotpython.light.csvdataset import CSVDataset
    dataset = CSVDataset(filename='./data/spotpython/data.csv', target_column='prognosis')
    print(dataset.data.shape)
    print(dataset.targets.shape)
    torch.Size([11, 65])
    torch.Size([11])
Source code in spotpython/data/california.py 
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
def __getitem__(self, idx: int) -> tuple:
    """
    Returns the feature and target at the given index.

    Args:
        idx (int): The index.

    Returns:
        tuple: A tuple containing the feature and target at the given index.

    Examples:
        >>> from spotpython.light.csvdataset import CSVDataset
            dataset = CSVDataset(filename='./data/spotpython/data.csv', target_column='prognosis')
            print(dataset.data.shape)
            print(dataset.targets.shape)
            torch.Size([11, 65])
            torch.Size([11])
    """
    feature = self.data[idx]
    target = self.targets[idx]
    return feature, target

__len__()

Returns the length of the dataset.

Returns:

Name Type Description
int int

The length of the dataset.

Examples:

>>> from spotpython.light import CSVDataset
>>> dataset = CSVDataset()
>>> print(len(dataset))
60000
Source code in spotpython/data/california.py 
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
def __len__(self) -> int:
    """
    Returns the length of the dataset.

    Returns:
        int: The length of the dataset.

    Examples:
        >>> from spotpython.light import CSVDataset
        >>> dataset = CSVDataset()
        >>> print(len(dataset))
        60000

    """
    return len(self.data)

extra_repr()

Returns a string representation of the dataset.

Returns:

Name Type Description
str str

A string representation of the dataset.

Examples:

>>> from spotpython.light import CSVDataset
>>> dataset = CSVDataset()
>>> print(dataset)
Split: Train
Source code in spotpython/data/california.py 
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
def extra_repr(self) -> str:
    """
    Returns a string representation of the dataset.

    Returns:
        str: A string representation of the dataset.

    Examples:
        >>> from spotpython.light import CSVDataset
        >>> dataset = CSVDataset()
        >>> print(dataset)
        Split: Train

    """
    split = "Train" if self.train else "Test"
    return f"Split: {split}"