doubt.datasets.bike_sharing_hourly

  1"""Hourly bike sharing 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 BikeSharingHourly(BaseDataset):
 17    __doc__ = f"""
 18    Bike sharing systems are new generation of traditional bike rentals where whole
 19    process from membership, rental and return back has become automatic. Through these
 20    systems, user is able to easily rent a bike from a particular position and return
 21    back at another position. Currently, there are about over 500 bike-sharing programs
 22    around the world which is composed of over 500 thousands bicycles. Today, there
 23    exists great interest in these systems due to their important role in traffic,
 24    environmental and health issues.
 25
 26    Apart from interesting real world applications of bike sharing systems, the
 27    characteristics of data being generated by these systems make them attractive for
 28    the research. Opposed to other transport services such as bus or subway, the
 29    duration of travel, departure and arrival position is explicitly recorded in these
 30    systems. This feature turns bike sharing system into a virtual sensor network that
 31    can be used for sensing mobility in the city. Hence, it is expected that most of
 32    important events in the city could be detected via monitoring these data.
 33
 34    {BASE_DATASET_DESCRIPTION}
 35
 36    Features:
 37        instant (int):
 38            Record index
 39        season (int):
 40            The season, with 1 = winter, 2 = spring, 3 = summer and 4 = autumn
 41        yr (int):
 42            The year, with 0 = 2011 and 1 = 2012
 43        mnth (int):
 44            The month, from 1 to 12 inclusive
 45        hr (int):
 46            The hour of the day, from 0 to 23 inclusive
 47        holiday (int):
 48            Whether day is a holiday or not, binary valued
 49        weekday (int):
 50            The day of the week, from 0 to 6 inclusive
 51        workingday (int):
 52            Working day, 1 if day is neither weekend nor holiday, otherwise 0
 53        weathersit (int):
 54            Weather, encoded as
 55
 56            1. Clear, few clouds, partly cloudy
 57            2. Mist and cloudy, mist and broken clouds, mist and few clouds
 58            3. Light snow, light rain and thunderstorm and scattered clouds, light rain
 59            and scattered clouds
 60            4. Heavy rain and ice pallets and thunderstorm and mist, or snow and fog
 61
 62        temp (float):
 63            Max-min normalised temperature in Celsius, from -8 to +39
 64        atemp (float):
 65            Max-min normalised feeling temperature in Celsius, from -16 to +50
 66        hum (float):
 67            Scaled max-min normalised humidity, from 0 to 1
 68        windspeed (float):
 69            Scaled max-min normalised wind speed, from 0 to 1
 70
 71    Targets:
 72        casual (int):
 73            Count of casual users
 74        registered (int):
 75            Count of registered users
 76        cnt (int):
 77            Sum of casual and registered users
 78
 79    Source:
 80        https://archive.ics.uci.edu/ml/datasets/Bike+Sharing+Dataset
 81
 82    Examples:
 83        Load in the data set::
 84
 85            >>> dataset = BikeSharingHourly()
 86            >>> dataset.shape
 87            (17379, 16)
 88
 89        Split the data set into features and targets, as NumPy arrays::
 90
 91            >>> X, y = dataset.split()
 92            >>> X.shape, y.shape
 93            ((17379, 13), (17379, 3))
 94
 95        Perform a train/test split, also outputting NumPy arrays::
 96
 97            >>> train_test_split = dataset.split(test_size=0.2, random_seed=42)
 98            >>> X_train, X_test, y_train, y_test = train_test_split
 99            >>> X_train.shape, y_train.shape, X_test.shape, y_test.shape
100            ((13873, 13), (13873, 3), (3506, 13), (3506, 3))
101
102        Output the underlying Pandas DataFrame::
103
104            >>> df = dataset.to_pandas()
105            >>> type(df)
106            <class 'pandas.core.frame.DataFrame'>
107    """
108
109    _url = (
110        "https://archive.ics.uci.edu/ml/machine-learning-databases/"
111        "00275/Bike-Sharing-Dataset.zip"
112    )
113
114    _features = range(13)
115    _targets = [13, 14, 15]
116
117    def _prep_data(self, data: bytes) -> pd.DataFrame:
118        """Prepare the data set.
119
120        Args:
121            data (bytes): The raw data
122
123        Returns:
124            Pandas dataframe: The prepared data
125        """
126        # Convert the bytes into a file-like object
127        buffer = io.BytesIO(data)
128
129        # Unzip the file and pull out hour.csv as a string
130        with zipfile.ZipFile(buffer, "r") as zip_file:
131            csv = zip_file.read("hour.csv").decode("utf-8")
132
133        # Convert the string into a file-like object
134        csv_file = io.StringIO(csv)
135
136        # Read the file-like object into a dataframe
137        cols = [0] + list(range(2, 17))
138        df = pd.read_csv(csv_file, usecols=cols)
139        return df