机器学习之——多项式回归

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

1.读取数据

# data = pd.read_csv('job.csv')
# data = np.loadtxt('job.csv', delimiter=',')
data = np.genfromtxt('job.csv', delimiter=',')
# print(data)

2.特征

X_data = data[1:, 1]

3.标签

y_data = data[1:, 2]
# print(X_data)

4.可视化（先以线性方程来预测）

plt.scatter(X_data, y_data)
# plt.show()

5. 建模

X_data 转为二维数组对象

X_data = X_data[:, np.newaxis]
model = LinearRegression()
model.fit(X_data, y_data)

plt.scatter(X_data, y_data)
plt.plot(X_data, model.predict(X_data))
plt.show()

1.将数据处理为多项式回归

from sklearn.preprocessing import PolynomialFeatures

2. 创建多项式对象

poly_reg = PolynomialFeatures(degree=5)

3. 数据处理

x_poly = poly_reg.fit_transform(X_data)
print(x_poly)

line_reg = LinearRegression()
line_reg.fit(x_poly, y_data)
plt.scatter(X_data, y_data, color='r')

plt.plot(X_data, line_reg.predict(x_poly))
plt.show()