Bernoulli RBM

xxxxxxxxxx

 

1

import numpy as np

2

from sklearn import datasets,model_selection,\

3

linear_model,pipeline,neural_network,metrics

4

digits=datasets.load_digits()

5

X,y=digits.data,digits.target

6

X_train,X_test,y_train,y_test=\

7

model_selection.train_test_split(

8

    X,y,test_size=.2,random_state=1)

9

X_train_scaled=\

10

(X_train-np.min(X_train,0))/(np.max(X_train,0)+.1^4)

11

X_test_scaled=\

12

(X_test-np.min(X_test,0))/(np.max(X_test,0)+.1^4)

13

logistic=linear_model.LogisticRegression(

14

    max_iter=50,solver='liblinear',multi_class='ovr')

15

logistic.C=2000.

16

brbm=neural_network.BernoulliRBM(

17

    random_state=0,verbose=False)

18

brbm.learning_rate,brbm.n_iter,brbm.n_components=.05,50,96

19

nn_clf=pipeline.Pipeline(steps=[('brbm',brbm),

20

                                ('logistic',logistic)])

21

nn_clf.fit(X_train_scaled,y_train)

22

print('Logistic regression using BRBM features:\n%s\n'%\

23

     (metrics.classification_report(

24

          y_test,nn_clf.predict(X_test_scaled))))

Language: Sage Gap GP HTML Macaulay2 Maxima Octave Python R Singular

---

Messages