sklearn实践_普通线性回归

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
data = pd.read_csv(r"C:\Users\Oscar\Downloads\Advertising.csv")

x = data[["TV","Radio","Newspaper"]]
y=data["Sales"]
plt.plot(data["TV"],y,"ro",Label="TV")
plt.plot(data["Radio"],y,"g^",Label="Radio")
plt.plot(data["Newspaper"],y,"bo",Label="Newspaper")
plt.legend(loc="lower right")
plt.grid()
plt.show

plt.figure(figsize=(10,10))

plt.subplot(311)
plt.plot(data["TV"],y,"ro",Label="TV")
plt.title("TV")

plt.subplot(312)#plt.subplot(3,1,2)
plt.plot(data["Newspaper"],y,"g^",Label="Newspaper")
plt.title("Newspaper")

plt.subplot(313)
plt.plot(data["Radio"],y,"bo",Label="Radio")
plt.title("Radio")

#建模
feature_cols = ["TV","Radio","Newspaper"]
X = data[feature_cols]
y = data["Sales"]
from sklearn.cross_validation import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y)
from sklearn.linear_model import LinearRegression
model = LinearRegression()
model.fit(X_train,y_train)
print(model)
print(model.coef_)
print(model.intercept_)
y_rep = model.predict(X_test)

#评估
from sklearn import metrics
import numpy as np
sum_mean = 0
for i in range(len(y_rep)):
    sum_mean+=(y_rep[i]-y_test.values[i])**2
print("RMSE:",np.sqrt(sum_mean/len(y_rep)))

#作图
plt.figure()
plt.plot(range(len(y_rep)),y_rep,"b",Label="pre")
plt.plot(range(len(y_rep)),y_test,"r",Label="test")
plt.legend(loc="upper right")
plt.xlabel("the number of sales")
plt.ylabel("values of sales")