github地址 github.com/yangjinghit…
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
/anaconda3/envs/py35/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
return f(*args, **kwds)
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
plt.style.use('ggplot')
data = pd.read_csv('Advertising.csv')
data.head()
| Unnamed: 0 | TV | radio | newspaper | sales | |
|---|---|---|---|---|---|
| 0 | 1 | 230.1 | 37.8 | 69.2 | 22.1 |
| 1 | 2 | 44.5 | 39.3 | 45.1 | 10.4 |
| 2 | 3 | 17.2 | 45.9 | 69.3 | 9.3 |
| 3 | 4 | 151.5 | 41.3 | 58.5 | 18.5 |
| 4 | 5 | 180.8 | 10.8 | 58.4 | 12.9 |
plt.scatter(data.TV, data.sales)
<matplotlib.collections.PathCollection at 0x1a179bb908>
plt.scatter(data.radio, data.sales)
<matplotlib.collections.PathCollection at 0x115dd47b8>
plt.scatter(data.newspaper, data.sales)
<matplotlib.collections.PathCollection at 0x1a17a132e8>
x = data[['TV', 'radio', 'newspaper']]
y = data.sales
x_train, x_test, y_train, y_test = train_test_split(x, y)
len(x_train), len(y_train)
(150, 150)
len(x_test)
50
model = LinearRegression()
model.fit(x_train, y_train)
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)
model.coef_
array([ 0.04466416, 0.19594144, -0.00469486])
for i in zip(x_train.columns, model.coef_):
print(i)
('TV', 0.04466415613441986)
('radio', 0.1959414384329583)
('newspaper', -0.0046948632484331895)
mean_squared_error(model.predict(x_test), y_test)
3.927556655626268
