100-Days-Of-ML twoday

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
dataset = pd.read_csv(‘C:\Users\Administrator\Desktop\ml 100day\MLDayTwoData.csv’)
#创建X和Y,注意一点dataframe切片包左不包右
X = dataset.iloc[ : , :1].values
Y = dataset.iloc[ : ,1].values
#由于数据量小没有存在脏数据一目了然，不需要percenttime统计空值异常值等
#直接进行数据切分,注意random_state选的数字一样，那么每次切分所得也都一样
from sklearn.model_selection import train_test_split
#创建切分器对象
X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size=0.25,random_state=0)
from sklearn.linear_model import LinearRegression
#创建线型回归对象
lr = LinearRegression()
lr = lr.fit(X_train,Y_train)
#预测结果
Y_pred = lr.predict(X_test)
#Visualization可视化
#训练集结果可视化
plt.scatter(X_train,Y_train)
plt.plot(X_train,lr.predict(X_train))
plt.show()

#测试集结果可视化
plt.scatter(X_test,Y_test)
plt.plot(X_test,lr.predict(X_test))
plt.show()