#!/usr/bin/env Python
# -*- coding: utf-8 -*-
import numpy as np
import sklearn.datasets
import sklearn.linear_model
import sklearn.neural_network
import sklearn.model_selection
import sklearn.pipeline
import sklearn.metrics
class Constants(object):
    RANDOM_STATE = 39
nist = sklearn.datasets.load_digits()
X_Train, X_Test, y_Train, y_Test = sklearn.model_selection.train_test_split(nist.data / nist.data.max(), nist.target, test_size=.2, random_state=Constants.RANDOM_STATE)
dbn = sklearn.pipeline.Pipeline([
    ("rbm1", sklearn.neural_network.BernoulliRBM(n_components=100, learning_rate=.06, n_iter=100, verbose=1, random_state=Constants.RANDOM_STATE)),
    #("rbm2", sklearn.neural_network.BernoulliRBM(n_components=80, learning_rate=.06, n_iter=100, verbose=1, random_state=Constants.RANDOM_STATE)),
    #("rbm3", sklearn.neural_network.BernoulliRBM(n_components=60, learning_rate=.06, n_iter=100, verbose=1, random_state=Constants.RANDOM_STATE)),
    ("logistic", sklearn.linear_model.LogisticRegression(C=100))
    ]).fit(X_Train, y_Train)
y_Pred = dbn.predict(X_Test)
print(sklearn.metrics.classification_report(y_Test, y_Pred))