Numpy实现Regression

from __future__ import print_function, division
import numpy as np
import math
from mlfromscratch.utils import normalize, polynomial_features

class l1_regularization():
    """ Regularization for Lasso Regression """
    def __init__(self, alpha):
        self.alpha = alpha
    
    def __call__(self, w):
        return self.alpha * np.linalg.norm(w)

    def grad(self, w):
        return self.alpha * np.sign(w)

class l2_regularization():
    """ Regularization for Ridge Regression """
    def __init__(self, alpha):
        self.alpha = alpha
    
    def __call__(self, w):
        return self.alpha * 0.5 *  w.T.dot(w)

    def grad(self, w):
        return self.alpha * w

class l1_l2_regularization():
    """ Regularization for Elastic Net Regression """
    def __init__(self, alpha, l1_ratio=0.5):
        self.alpha = alpha
        self.l1_ratio = l1_ratio

    def __call__(self, w):
        l1_contr = self.l1_ratio * np.linalg.norm(w)
        l2_contr = (1 - self.l1_ratio) * 0.5 * w.T.dot(w) 
        return self.alpha * (l1_contr + l2_contr)

    def grad(self, w):
        l1_contr = self.l1_ratio * np.sign(w)
        l2_contr = (1 - self.l1_ratio) * w
        return self.alpha * (l1_contr + l2_contr) 

class Regression(object):
    """ Base regression model. Models the relationship between a scalar dependent variable y and the independent 
    variables X. 
    Parameters:
    -----------
    n_iterations: float
        The number of training iterations the algorithm will tune the weights for.
    learning_rate: float
        The step length that will be used when updating the weights.
    """
    def __init__(self, n_iterations, learning_rate):
        self.n_iterations = n_iterations
        self.learning_rate = learning_rate

    def initialize_weights(self, n_features):
        """ Initialize weights randomly [-1/N, 1/N] """
        limit = 1 / math.sqrt(n_features)
        self.w = np.random.uniform(-limit, limit, (n_features, ))

    def fit(self, X, y):
        # Insert constant ones for bias weights
        X = np.insert(X, 0, 1, axis=1)
        self.training_errors = []
        self.initialize_weights(n_features=X.shape[1])

        # Do gradient descent for n_iterations
        for i in range(self.n_iterations):
            y_pred = X.dot(self.w)
            # Calculate l2 loss
            mse = np.mean(0.5 * (y - y_pred)**2 + self.regularization(self.w))
            self.training_errors.append(mse)
            # Gradient of l2 loss w.r.t w
            grad_w = -(y - y_pred).dot(X) + self.regularization.grad(self.w)
            # Update the weights
            self.w -= self.learning_rate * grad_w

    def predict(self, X):
        # Insert constant ones for bias weights
        X = np.insert(X, 0, 1, axis=1)
        y_pred = X.dot(self.w)
        return y_pred

class LinearRegression(Regression):
    """Linear model.
    Parameters:
    -----------
    n_iterations: float
        The number of training iterations the algorithm will tune the weights for.
    learning_rate: float
        The step length that will be used when updating the weights.
    gradient_descent: boolean
        True or false depending if gradient descent should be used when training. If 
        false then we use batch optimization by least squares.
    """
    def __init__(self, n_iterations=100, learning_rate=0.001, gradient_descent=True):
        self.gradient_descent = gradient_descent
        # No regularization
        self.regularization = lambda x: 0
        self.regularization.grad = lambda x: 0
        super(LinearRegression, self).__init__(n_iterations=n_iterations,
                                            learning_rate=learning_rate)
    def fit(self, X, y):
        # If not gradient descent => Least squares approximation of w
        if not self.gradient_descent:
            # Insert constant ones for bias weights
            X = np.insert(X, 0, 1, axis=1)
            # Calculate weights by least squares (using Moore-Penrose pseudoinverse)
            U, S, V = np.linalg.svd(X.T.dot(X))
            S = np.diag(S)
            X_sq_reg_inv = V.dot(np.linalg.pinv(S)).dot(U.T)
            self.w = X_sq_reg_inv.dot(X.T).dot(y)
        else:
            super(LinearRegression, self).fit(X, y)

class LassoRegression(Regression):
    """Linear regression model with a regularization factor which does both variable selection 
    and regularization. Model that tries to balance the fit of the model with respect to the training 
    data and the complexity of the model. A large regularization factor with decreases the variance of 
    the model and do para.
    Parameters:
    -----------
    degree: int
        The degree of the polynomial that the independent variable X will be transformed to.
    reg_factor: float
        The factor that will determine the amount of regularization and feature
        shrinkage. 
    n_iterations: float
        The number of training iterations the algorithm will tune the weights for.
    learning_rate: float
        The step length that will be used when updating the weights.
    """
    def __init__(self, degree, reg_factor, n_iterations=3000, learning_rate=0.01):
        self.degree = degree
        self.regularization = l1_regularization(alpha=reg_factor)
        super(LassoRegression, self).__init__(n_iterations, 
                                            learning_rate)

    def fit(self, X, y):
        X = normalize(polynomial_features(X, degree=self.degree))
        super(LassoRegression, self).fit(X, y)

    def predict(self, X):
        X = normalize(polynomial_features(X, degree=self.degree))
        return super(LassoRegression, self).predict(X)

class PolynomialRegression(Regression):
    """Performs a non-linear transformation of the data before fitting the model
    and doing predictions which allows for doing non-linear regression.
    Parameters:
    -----------
    degree: int
        The degree of the polynomial that the independent variable X will be transformed to.
    n_iterations: float
        The number of training iterations the algorithm will tune the weights for.
    learning_rate: float
        The step length that will be used when updating the weights.
    """
    def __init__(self, degree, n_iterations=3000, learning_rate=0.001):
        self.degree = degree
        # No regularization
        self.regularization = lambda x: 0
        self.regularization.grad = lambda x: 0
        super(PolynomialRegression, self).__init__(n_iterations=n_iterations,
                                                learning_rate=learning_rate)

    def fit(self, X, y):
        X = polynomial_features(X, degree=self.degree)
        super(PolynomialRegression, self).fit(X, y)

    def predict(self, X):
        X = polynomial_features(X, degree=self.degree)
        return super(PolynomialRegression, self).predict(X)

class RidgeRegression(Regression):
    """Also referred to as Tikhonov regularization. Linear regression model with a regularization factor.
    Model that tries to balance the fit of the model with respect to the training data and the complexity
    of the model. A large regularization factor with decreases the variance of the model.
    Parameters:
    -----------
    reg_factor: float
        The factor that will determine the amount of regularization and feature
        shrinkage. 
    n_iterations: float
        The number of training iterations the algorithm will tune the weights for.
    learning_rate: float
        The step length that will be used when updating the weights.
    """
    def __init__(self, reg_factor, n_iterations=1000, learning_rate=0.001):
        self.regularization = l2_regularization(alpha=reg_factor)
        super(RidgeRegression, self).__init__(n_iterations, 
                                            learning_rate)

class PolynomialRidgeRegression(Regression):
    """Similar to regular ridge regression except that the data is transformed to allow
    for polynomial regression.
    Parameters:
    -----------
    degree: int
        The degree of the polynomial that the independent variable X will be transformed to.
    reg_factor: float
        The factor that will determine the amount of regularization and feature
        shrinkage. 
    n_iterations: float
        The number of training iterations the algorithm will tune the weights for.
    learning_rate: float
        The step length that will be used when updating the weights.
    """
    def __init__(self, degree, reg_factor, n_iterations=3000, learning_rate=0.01, gradient_descent=True):
        self.degree = degree
        self.regularization = l2_regularization(alpha=reg_factor)
        super(PolynomialRidgeRegression, self).__init__(n_iterations, 
                                                        learning_rate)

    def fit(self, X, y):
        X = normalize(polynomial_features(X, degree=self.degree))
        super(PolynomialRidgeRegression, self).fit(X, y)

    def predict(self, X):
        X = normalize(polynomial_features(X, degree=self.degree))
        return super(PolynomialRidgeRegression, self).predict(X)

class ElasticNet(Regression):
    """ Regression where a combination of l1 and l2 regularization are used. The
    ratio of their contributions are set with the 'l1_ratio' parameter.
    Parameters:
    -----------
    degree: int
        The degree of the polynomial that the independent variable X will be transformed to.
    reg_factor: float
        The factor that will determine the amount of regularization and feature
        shrinkage. 
    l1_ration: float
        Weighs the contribution of l1 and l2 regularization.
    n_iterations: float
        The number of training iterations the algorithm will tune the weights for.
    learning_rate: float
        The step length that will be used when updating the weights.
    """
    def __init__(self, degree=1, reg_factor=0.05, l1_ratio=0.5, n_iterations=3000, 
                learning_rate=0.01):
        self.degree = degree
        self.regularization = l1_l2_regularization(alpha=reg_factor, l1_ratio=l1_ratio)
        super(ElasticNet, self).__init__(n_iterations, 
                                        learning_rate)

    def fit(self, X, y):
        X = normalize(polynomial_features(X, degree=self.degree))
        super(ElasticNet, self).fit(X, y)

    def predict(self, X):
        X = normalize(polynomial_features(X, degree=self.degree))
        return super(ElasticNet, self).predict(X)


  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
  
21
  
22
  
23
  
24
  
25
  
26
  
27
  
28
  
29
  
30
  
31
  
32
  
33
  
34
  
35
  
36
  
37
  
38
  
39
  
40
  
41
  
42
  
43
  
44
  
45
  
46
  
47
  
48
  
49
  
50
  
51
  
52
  
53
  
54
  
55
  
56
  
57
  
58
  
59
  
60
  
61
  
62
  
63
  
64
  
65
  
66
  
67
  
68
  
69
  
70
  
71
  
72
  
73
  
74
  
75
  
76
  
77
  
78
  
79
  
80
  
81
  
82
  
83
  
84
  
85
  
86
  
87
  
88
  
89
  
90
  
91
  
92
  
93
  
94
  
95
  
96
  
97
  
98
  
99
  
100
  
101
  
102
  
103
  
104
  
105
  
106
  
107
  
108
  
109
  
110
  
111
  
112
  
113
  
114
  
115
  
116
  
117
  
118
  
119
  
120
  
121
  
122
  
123
  
124
  
125
  
126
  
127
  
128
  
129
  
130
  
131
  
132
  
133
  
134
  
135
  
136
  
137
  
138
  
139
  
140
  
141
  
142
  
143
  
144
  
145
  
146
  
147
  
148
  
149
  
150
  
151
  
152
  
153
  
154
  
155
  
156
  
157
  
158
  
159
  
160
  
161
  
162
  
163
  
164
  
165
  
166
  
167
  
168
  
169
  
170
  
171
  
172
  
173
  
174
  
175
  
176
  
177
  
178
  
179
  
180
  
181
  
182
  
183
  
184
  
185
  
186
  
187
  
188
  
189
  
190
  
191
  
192
  
193
  
194
  
195
  
196
  
197
  
198
  
199
  
200
  
201
  
202
  
203
  
204
  
205
  
206
  
207
  
208
  
209
  
210
  
211
  
212
  
213
  
214
  
215
  
216
  
217
  
218
  
219
  
220
  
221
  
222
  
223
  
224
  
225
  
226
  
227
  
228
  
229
  
230
  
231
  
232
  
233
  
234
  
235
  
236
  
237
  
238
  
239
  
240
  
241
  
242
  
243
  
244
  
245
  
246
  
247
  
248
  
249
  
250
  
251
  
252
  
253
  
254
  
255
  
256
 

文章来源: wanghao.blog.csdn.net，作者：AI浩，版权归原作者所有，如需转载，请联系作者。

原文链接：wanghao.blog.csdn.net/article/details/121558402