sklearn_多项式回归

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

data = pd.read_csv('../data_test/Salary_Data.csv')

x = data['YearsExperience']
y = data['Salary']

train_x = pd.DataFrame(x)
train_y = y

import sklearn.pipeline as pl #数据管线
import sklearn.preprocessing as sp #数据预处理
import sklearn.linear_model as lm 

model = pl.make_pipeline(sp.PolynomialFeatures(3),
                         lm.LinearRegression())

model.fit(train_x,train_y)

pred_y = model.predict(train_x)

plt.scatter(x,y,s=50,color='dodgerblue')
plt.plot(x,pred_y,color='orangered')

### 作业:拿到一部分数据,进行评估,寻找到最优的最高次幂