2、简单线性回归/ML100Days by Avik-Jain

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
import matplotlib as mpl

#1-import data
dataset = pd.read_csv('/home/joye/datasets/studentscores.csv')
X = dataset.iloc[:,:-1].values
Y = dataset.iloc[:,-1].values
# data = dataset.values
# X = data[:,:-1]
# Y = data[:,-1]
# print(X,'\n',Y)
X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size=0.25,random_state=0)

#2-Model Fitting
lr = LinearRegression()
lr = lr.fit(X_train,Y_train)

#3-Predict
Y_hat = lr.predict(X_test)

#4-Visualization
mpl.rcParams['font.sans-serif'] = ['simHei']#字体显示设置
mpl.rcParams['axes.unicode_minus'] = False
#训练集显示
plt.scatter(X_train,Y_train,c = Y_train.ravel())
plt.plot(X_train , lr.predict(X_train),color='blue' ,markeredgecolor='k')
plt.xlabel('Hours/h')
plt.ylabel('Score')
plt.title('训练集')
plt.show()
#测试集显示
plt.scatter(X_test , Y_test, c = Y_test.ravel(),edgecolors='k')
plt.plot(X_test , Y_hat, color ='blue')
plt.xlabel('Hours/h')
plt.ylabel('Score')
plt.title('测试集')
plt.show()