jupyter notebook github:
https://github.com/Chufeng-Jiang/Jupyter_Py3_Machine_Learning_Introduction/blob/main/05-Linear-Regression/10-More-about-Linear-Regression.ipynb
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import datasets
data_url = "http://lib.stat.cmu.edu/datasets/boston"
raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
target = raw_df.values[1::2, 2]
data
df = pd.DataFrame(data)
header=[ 'CRIM', 'ZN','INDUS','CHAS','NOX','RM','AGE','DIS', 'RAD','TAX', 'PTRATIO', 'B', 'LSTAT']
df.columns = header
df
X = data
y = target
X = X[y < 50.0]
y = y[y < 50.0]
from sklearn.linear_model import LinearRegression
lin_reg = LinearRegression()
lin_reg.fit(X, y)
lin_reg.coef_
np.argsort(lin_reg.coef_)
df.columns[np.argsort(lin_reg.coef_)]