1、获取数据集;
2、使用matplotlib工具将数据画出来;
import matplotlib.pyplot as plt
import pandas as pd
#数据地址,需要梯子访问
# url = "https://raw.githubusercontent.com/GrandmaCan/ML/main/Resgression/Salary_Data.csv"
# 保存在本地
SALARY_DATA_URL = '.\LOCATE_DATA\salary_year_data.csv'
# 将数据读出来
def getData(url):
data = pd.read_csv(url)
return data
#使用matplot将数据画出来
def plotRealData(x,y):
plt.scatter(x,y,marker='x',color='red')
plt.xlabel('years')
plt.ylabel('salary')
plt.title('years-salary')
plt.show()
#在真实数据图形中增加一条直线:y=w*x + b (w=0,b=20)
def plotRealAndPreData(x,y,w,b):
plt.scatter(x, y, marker='x', color='blue',label='real data')
plt.xlabel('years')
plt.ylabel('salary')
plt.title('years-salary')
plt.xlim([0,12])
plt.ylim([0,120])
y_pred = w*x + b
plt.plot(x,y_pred,color='red',label='pred data')
plt.show()
if __name__ == '__main__':
print('Run python file...')
print('this file just for fun...')
data = getData(SALARY_DATA_URL)
# print(f'data type is {type(data)}')
# print(data)
#get data for x y
x = data['YearsExperience']
y = data['Salary']
#show data
# plotRealData(x,y)
# pred_data y = w*x + b
# w=0 b=20
plotRealAndPreData(x,y,0,20)
原始数据加预测线:y=w*x + b (w= 0,b=20) (只是为了练习matplotlib,多画一条线耍一耍)
总结:感觉matplotlib很哇塞,以前不晓得这个这么好耍,以后可以多研究一哈!!