Machine Learning A-Z学习笔记4

Machine Learning A-Z学习笔记4

第四章多项式线性回归

1.简单原理

简单线性回归：只有1个自变量

多元线性回归:有多个自变量

多项式线性回归:只有1個自变量，但次数不为1

适用情况

# Polynomial Regression
#导入库
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# 导入数据
dataset = pd.read_csv('Position_Salaries.csv')
X = dataset.iloc[:, 1:2].values
y = dataset.iloc[:, 2].values



# 数据太少，所以不划分训练集和测试集

"""from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)"""

# 特征缩放
"""from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)"""

# 建立简单线性回归模型作为比较

from sklearn.linear_model import LinearRegression
lin_reg = LinearRegression()
lin_reg.fit(X, y)

# 建立多项式回归模型

from sklearn.preprocessing import PolynomialFeatures
poly_reg = PolynomialFeatures(degree = 4)#degree为次数，默认为2，可以不断调整
X_poly = poly_reg.fit_transform(X)
poly_reg.fit(X_poly, y)
lin_reg_2 = LinearRegression()
lin_reg_2.fit(X_poly, y)

# 简单线性模型可视化
plt.scatter(X, y, color = 'red')
plt.plot(X, lin_reg.predict(X), color = 'blue')
plt.title('Truth or Bluff (Linear Regression)')
plt.xlabel('Position level')
plt.ylabel('Salary')
plt.show()

# 多项式模型可视化
plt.scatter(X, y, color = 'red')
plt.plot(X, lin_reg_2.predict(poly_reg.fit_transform(X)), color = 'blue')
plt.title('Truth or Bluff (Polynomial Regression)')
plt.xlabel('Position level')
plt.ylabel('Salary')
plt.show()

# 产生新的数据，使模型变得更平滑

X_grid = np.arange(min(X), max(X), 0.1)
X_grid = X_grid.reshape((len(X_grid), 1))
plt.scatter(X, y, color = 'red')
plt.plot(X_grid, lin_reg_2.predict(poly_reg.fit_transform(X_grid)), color = 'blue')
plt.title('Truth or Bluff (Polynomial Regression)')
plt.xlabel('Position level')
plt.ylabel('Salary')
plt.show()

# 简单线性回归模型预测
lin_reg.predict([[6.5]])

# 多项式线性回归模型预测
lin_reg_2.predict(poly_reg.fit_transform([[6.5]]))