make_regression.py

import pandas as pd
import numpy as np
import time

from sklearn.datasets import make_regression

n_samples = 1000
n_features = 10
n_informative = 3

X, y = make_regression(n_samples=n_samples, n_features=n_features, n_informative=n_informative)

# We convert the X and y arrays into a DataFrame which will be useful later
col_names = []
for i in range(n_features):
    col_names.append("X{}".format(i+1))

df = pd.DataFrame(X, columns=col_names)
df["Y"] = y
display(df)