doubt.datasets.concrete

 1"""Concrete 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
 9
10import pandas as pd
11
12from .dataset import BASE_DATASET_DESCRIPTION, BaseDataset
13
14
15class Concrete(BaseDataset):
16    __doc__ = f"""
17    Concrete is the most important material in civil engineering. The concrete
18    compressive strength is a highly nonlinear function of age and ingredients.
19
20    {BASE_DATASET_DESCRIPTION}
21
22    Features:
23        Cement (float):
24            Kg of cement in an m3 mixture
25        Blast Furnace Slag (float):
26            Kg of blast furnace slag in an m3 mixture
27        Fly Ash (float):
28            Kg of fly ash in an m3 mixture
29        Water (float):
30            Kg of water in an m3 mixture
31        Superplasticiser (float):
32            Kg of superplasticiser in an m3 mixture
33        Coarse Aggregate (float):
34            Kg of coarse aggregate in an m3 mixture
35        Fine Aggregate (float):
36            Kg of fine aggregate in an m3 mixture
37        Age (int):
38            Age in days, between 1 and 365 inclusive
39
40    Targets:
41        Concrete Compressive Strength (float):
42            Concrete compressive strength in megapascals
43
44    Source:
45        https://archive.ics.uci.edu/ml/datasets/Concrete+Compressive+Strength
46
47    Examples:
48        Load in the data set::
49
50            >>> dataset = Concrete()
51            >>> dataset.shape
52            (1030, 9)
53
54        Split the data set into features and targets, as NumPy arrays::
55
56            >>> X, y = dataset.split()
57            >>> X.shape, y.shape
58            ((1030, 8), (1030,))
59
60        Perform a train/test split, also outputting NumPy arrays::
61
62            >>> train_test_split = dataset.split(test_size=0.2, random_seed=42)
63            >>> X_train, X_test, y_train, y_test = train_test_split
64            >>> X_train.shape, y_train.shape, X_test.shape, y_test.shape
65            ((807, 8), (807,), (223, 8), (223,))
66
67        Output the underlying Pandas DataFrame::
68
69            >>> df = dataset.to_pandas()
70            >>> type(df)
71            <class 'pandas.core.frame.DataFrame'>
72    """
73
74    _url = (
75        "https://archive.ics.uci.edu/ml/machine-learning-databases/"
76        "concrete/compressive/Concrete_Data.xls"
77    )
78
79    _features = range(8)
80    _targets = [8]
81
82    def _prep_data(self, data: bytes) -> pd.DataFrame:
83        """Prepare the data set.
84
85        Args:
86            data (bytes): The raw data
87
88        Returns:
89            Pandas dataframe: The prepared data
90        """
91
92        # Convert the bytes into a file-like object
93        xls_file = io.BytesIO(data)
94
95        # Load the file-like object into a data frame
96        df = pd.read_excel(xls_file)
97        return df