doubt.datasets.superconductivity

  1"""Superconductivity data set.
  2
  3This data set is from the UCI data set archive, with the description being the original
  4description verbatim. Some feature names may have been altered, based on the
  5description.
  6"""
  7
  8import io
  9import zipfile
 10
 11import pandas as pd
 12
 13from .dataset import BASE_DATASET_DESCRIPTION, BaseDataset
 14
 15
 16class Superconductivity(BaseDataset):
 17    __doc__ = f"""
 18    This dataset contains data on 21,263 superconductors and their relevant features.
 19    The goal here is to predict the critical temperature based on the features
 20    extracted.
 21
 22    {BASE_DATASET_DESCRIPTION}
 23
 24    Features:
 25        - number_of_elements (int)
 26        - mean_atomic_mass (float)
 27        - wtd_mean_atomic_mass (float)
 28        - gmean_atomic_mass (float)
 29        - wtd_gmean_atomic_mass (float)
 30        - entropy_atomic_mass (float)
 31        - wtd_entropy_atomic_mass (float)
 32        - range_atomic_mass (float)
 33        - wtd_range_atomic_mass (float)
 34        - std_atomic_mass (float)
 35        - wtd_std_atomic_mass (float)
 36        - mean_fie (float)
 37        - wtd_mean_fie (float)
 38        - gmean_fie (float)
 39        - wtd_gmean_fie (float)
 40        - entropy_fie (float)
 41        - wtd_entropy_fie (float)
 42        - range_fie (float)
 43        - wtd_range_fie (float)
 44        - std_fie (float)
 45        - wtd_std_fie (float)
 46        - mean_atomic_radius (float)
 47        - wtd_mean_atomic_radius (float)
 48        - gmean_atomic_radius (float)
 49        - wtd_gmean_atomic_radius (float)
 50        - entropy_atomic_radius (float)
 51        - wtd_entropy_atomic_radius (float)
 52        - range_atomic_radius (float)
 53        - wtd_range_atomic_radius (float)
 54        - std_atomic_radius (float)
 55        - wtd_std_atomic_radius (float)
 56        - mean_Density (float)
 57        - wtd_mean_Density (float)
 58        - gmean_Density (float)
 59        - wtd_gmean_Density (float)
 60        - entropy_Density (float)
 61        - wtd_entropy_Density (float)
 62        - range_Density (float)
 63        - wtd_range_Density (float)
 64        - std_Density (float)
 65        - wtd_std_Density (float)
 66        - mean_ElectronAffinity (float)
 67        - wtd_mean_ElectronAffinity (float)
 68        - gmean_ElectronAffinity (float)
 69        - wtd_gmean_ElectronAffinity (float)
 70        - entropy_ElectronAffinity (float)
 71        - wtd_entropy_ElectronAffinity (float)
 72        - range_ElectronAffinity (float)
 73        - wtd_range_ElectronAffinity (float)
 74        - std_ElectronAffinity (float)
 75        - wtd_std_ElectronAffinity (float)
 76        - mean_FusionHeat (float)
 77        - wtd_mean_FusionHeat (float)
 78        - gmean_FusionHeat (float)
 79        - wtd_gmean_FusionHeat (float)
 80        - entropy_FusionHeat (float)
 81        - wtd_entropy_FusionHeat (float)
 82        - range_FusionHeat (float)
 83        - wtd_range_FusionHeat (float)
 84        - std_FusionHeat (float)
 85        - wtd_std_FusionHeat (float)
 86        - mean_ThermalConductivity (float)
 87        - wtd_mean_ThermalConductivity (float)
 88        - gmean_ThermalConductivity (float)
 89        - wtd_gmean_ThermalConductivity (float)
 90        - entropy_ThermalConductivity (float)
 91        - wtd_entropy_ThermalConductivity (float)
 92        - range_ThermalConductivity (float)
 93        - wtd_range_ThermalConductivity (float)
 94        - std_ThermalConductivity (float)
 95        - wtd_std_ThermalConductivity (float)
 96        - mean_Valence (float)
 97        - wtd_mean_Valence (float)
 98        - gmean_Valence (float)
 99        - wtd_gmean_Valence (float)
100        - entropy_Valence (float)
101        - wtd_entropy_Valence (float)
102        - range_Valence (float)
103        - wtd_range_Valence (float)
104        - std_Valence (float)
105        - wtd_std_Valence (float)
106
107    Targets:
108        - critical_temp (float)
109
110    Source:
111        https://archive.ics.uci.edu/ml/datasets/Superconductivty+Data
112
113    Examples:
114        Load in the data set::
115
116            >>> dataset = Superconductivity()
117            >>> dataset.shape
118            (21263, 82)
119
120        Split the data set into features and targets, as NumPy arrays::
121
122            >>> X, y = dataset.split()
123            >>> X.shape, y.shape
124            ((21263, 81), (21263,))
125
126        Perform a train/test split, also outputting NumPy arrays::
127
128            >>> train_test_split = dataset.split(test_size=0.2, random_seed=42)
129            >>> X_train, X_test, y_train, y_test = train_test_split
130            >>> X_train.shape, y_train.shape, X_test.shape, y_test.shape
131            ((17004, 81), (17004,), (4259, 81), (4259,))
132
133        Output the underlying Pandas DataFrame::
134
135            >>> df = dataset.to_pandas()
136            >>> type(df)
137            <class 'pandas.core.frame.DataFrame'>
138    """
139
140    _url = (
141        "https://archive.ics.uci.edu/ml/machine-learning-databases/"
142        "00464/superconduct.zip"
143    )
144
145    _features = range(81)
146    _targets = [81]
147
148    def _prep_data(self, data: bytes) -> pd.DataFrame:
149        """Prepare the data set.
150
151        Args:
152            data (bytes): The raw data
153
154        Returns:
155            Pandas dataframe: The prepared data
156        """
157        # Convert the bytes into a file-like object
158        buffer = io.BytesIO(data)
159
160        # Unzip the file and pull out the text
161        with zipfile.ZipFile(buffer, "r") as zip_file:
162            txt = zip_file.read("train.csv")
163
164        # Convert text to csv file
165        csv_file = io.BytesIO(txt)
166
167        # Load the csv file into a dataframe
168        df = pd.read_csv(csv_file)
169
170        return df