[scikit-learn 机器学习] 5. 多元线性回归

from numpy.linalg import inv
from numpy import dot, transpose
X = [[1, 6, 2], [1, 8, 1], [1, 10, 0], [1, 14, 2], [1, 18, 0]]
y = [[7], [9], [13], [17.5], [18]]
print(dot(inv(dot(transpose(X),X)), dot(transpose(X),y)))

from numpy.linalg import lstsq
# help(lstsq)
print(lstsq(X,y))

[[1.1875    ]
 [1.01041667]
 [0.39583333]]
 
(array([[1.1875    ],
       [1.01041667],
       [0.39583333]]), array([8.22916667]), 3, array([26.97402951,  2.46027806,  0.59056212]))
	     系数， 			残差，     			秩， 奇异值

from sklearn.linear_model import LinearRegression
X = [[6, 2], [8, 1], [10, 0], [14, 2], [18, 0]]
y = [[7], [9], [13], [17.5], [18]]

model = LinearRegression()
model.fit(X, y)

X_test = [[8, 2], [9, 0], [11, 2], [16, 2], [12, 0]]
y_test = [[11], [8.5], [15], [18], [11]]
predictions = model.predict(X_test)

for i, pred in enumerate(predictions):
    print("预测值：%s, 实际值：%s" %(pred, y_test[i]))
print(model.score(X_test,y_test))

预测值：[10.0625], 实际值：[11]
预测值：[10.28125], 实际值：[8.5]
预测值：[13.09375], 实际值：[15]
预测值：[18.14583333], 实际值：[18]
预测值：[13.3125], 实际值：[11]
0.7701677731318468 # r_squared

import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures

X_train = [[6], [8], [10], [14], [18]] # 直径
y_train = [[7], [9], [13], [17.5], [18]]
X_test = [[6], [8], [11], [16]] # 价格
y_test = [[8], [12], [15], [18]]
regressor = LinearRegression()
regressor.fit(X_train, y_train)
xx = np.linspace(0, 26, 100)
yy = regressor.predict(xx.reshape(xx.shape[0], 1))
plt.plot(xx, yy, c='g',linestyle='-')

# 2次项特征转换器
quadratic_featurizer = PolynomialFeatures(degree=2)
X_train_quadratic = quadratic_featurizer.fit_transform(X_train)
X_test_quadratic = quadratic_featurizer.transform(X_test)
print("原特征\n",X_train)
print("二次项特征\n",X_train_quadratic)

regressor_quadratic = LinearRegression()
regressor_quadratic.fit(X_train_quadratic, y_train)
xx_quadratic = quadratic_featurizer.transform(xx.reshape(xx.shape[0], 1))
plt.plot(xx, regressor_quadratic.predict(xx_quadratic), c='r', linestyle='--')
plt.rcParams['font.sans-serif'] = 'SimHei'  # 消除中文乱码
plt.title('披萨价格 VS 直径')
plt.xlabel('直径')
plt.ylabel('价格')
plt.axis([0, 25, 0, 25])
plt.grid(True)
plt.scatter(X_train, y_train)
plt.show()

print('简单线性回归 r-squared值', regressor.score(X_test, y_test))
print('二次多项式回归 r-squared值', regressor_quadratic.score(X_test_quadratic, y_test))

原特征
 [[6], [8], [10], [14], [18]]
二次项特征
 [[  1.   6.  36.]
 [  1.   8.  64.]
 [  1.  10. 100.]
 [  1.  14. 196.]
 [  1.  18. 324.]]

简单线性回归 r-squared值 0.809726797707665
二次多项式回归 r-squared值 0.8675443656345054 # 决定系数更大

# 酒质量预测
import pandas as pd
data = pd.read_csv("winequality-red.csv",sep=';')
data.describe()

from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split

X = data[list(data.columns)[:-1]]
y = data['quality']
X_train,X_test,y_train,y_test = train_test_split(X,y)

regressor = LinearRegression()
regressor.fit(X_train,y_train)
y_pred = regressor.predict(X_test)
print("决定系数：", regressor.score(X_test,y_test))
# 决定系数： 0.3602241149540347

from sklearn.model_selection import cross_val_score
scores = cross_val_score(regressor, X, y, cv=5)
scores.mean() # 0.2900416288421962
scores # array([0.13200871, 0.31858135, 0.34955348, 0.369145  , 0.2809196 ])

import numpy as np
from sklearn.datasets import load_boston
from sklearn.linear_model import SGDRegressor
from sklearn.model_selection import cross_val_score
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split

data = load_boston()
X_train, X_test, y_train, y_test = train_test_split(data.data, data.target)

X_scaler = StandardScaler()
y_scaler = StandardScaler()
X_train = X_scaler.fit_transform(X_train)
y_train = y_scaler.fit_transform(y_train.reshape(-1, 1))
X_test = X_scaler.transform(X_test)
y_test = y_scaler.transform(y_test.reshape(-1, 1))

regressor = SGDRegressor(loss='squared_loss')
scores = cross_val_score(regressor, X_train, y_train, cv=5)

print('Cross validation r-squared scores: %s' % scores)
print('Average cross validation r-squared score: %s' % np.mean(scores))

regressor.fit(X_train, y_train)
print('Test set r-squared score %s' % regressor.score(X_test, y_test))

Cross validation r-squared scores: [0.57365322 0.73833251 0.69391029 0.67979254 0.73491949]
Average cross validation r-squared score: 0.6841216111623614
Test set r-squared score 0.7716363798764403

class SGDRegressor(BaseSGDRegressor)
 |  SGDRegressor(loss='squared_loss', penalty='l2', alpha=0.0001, 
			 l1_ratio=0.15, fit_intercept=True, max_iter=1000, tol=0.001, 
			 shuffle=True, verbose=0, epsilon=0.1, random_state=None,
			  learning_rate='invscaling', eta0=0.01, power_t=0.25, 
			  early_stopping=False, validation_fraction=0.1, 
			  n_iter_no_change=5, warm_start=False, average=False)
 |  
 |  Linear model fitted by minimizing a regularized empirical loss with SGD
 |  
 |  SGD stands for Stochastic Gradient Descent: the gradient of the loss is
 |  estimated each sample at a time and the model is updated along the way with
 |  a decreasing strength schedule (aka learning rate).
 |  
 |  The regularizer is a penalty added to the loss function that shrinks model
 |  parameters towards the zero vector using either the squared euclidean norm
 |  L2 or the absolute norm L1 or a combination of both (Elastic Net). If the
 |  parameter update crosses the 0.0 value because of the regularizer, the
 |  update is truncated to 0.0 to allow for learning sparse models and achieve
 |  online feature selection.