datasets.py

import numpy as np
import pandas as pd
from sklearn.datasets import load_boston
from sklearn.preprocessing import MinMaxScaler, PolynomialFeatures
from .make_blobs import make_blobs


def make_forge():
    # a carefully hand-designed dataset lol
    X, y = make_blobs(centers=2, random_state=4, n_samples=30)
    y[np.array([7, 27])] = 0
    mask = np.ones(len(X), dtype=np.bool)
    mask[np.array([0, 1, 5, 26])] = 0
    X, y = X[mask], y[mask]
    return X, y


def make_wave(n_samples=100):
    rnd = np.random.RandomState(42)
    x = rnd.uniform(-3, 3, size=n_samples)
    y_no_noise = (np.sin(4 * x) + x)
    y = (y_no_noise + rnd.normal(size=len(x))) / 2
    return x.reshape(-1, 1), y


def load_extended_boston():
    boston = load_boston()
    X = boston.data

    X = MinMaxScaler().fit_transform(boston.data)
    X = PolynomialFeatures(degree=2).fit_transform(X)
    return X, boston.target


def load_citibike():
    data_mine = pd.read_csv("data/citibike.csv")
    data_mine['one'] = 1
    data_mine['starttime'] = pd.to_datetime(data_mine.starttime)
    data_starttime = data_mine.set_index("starttime")
    data_resampled = data_starttime.resample("3h", how="sum").fillna(0)
    return data_resampled.one