RBM受限波兹曼机在特征学习上的使用

'''受限波兹曼机在特征学习上的使用
'''
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
from sklearn import linear_model, datasets, metrics
from sklearn.neural_network import BernoulliRBM
from sklearn.pipeline import Pipeline
from sklearn.datasets import load_digits 
digits = load_digits()
# create numpy array from csv
images = np.genfromtxt('../data/mnist_train.csv', delimiter=',')
# extract the X and y variable
images_X, images_y = images[:,1:], images[:,0]

# scikit-learn RBM version assumes 0-1 scaling
images_X = images_X / 255.
images_X = (images_X > 0.5).astype(float)
np.min(images_X), np.max(images_X)  # (0.0, 1.0)

# instantiate our BernoulliRBM
rbm = BernoulliRBM(random_state=0, verbose=True, n_iter=20,n_components=100)
rbm.fit(images_X)

# 查看RBM 成分
len(rbm.components_)

 #可视化 RBM 提取的成分
plt.figure(figsize=(10, 10))
for i, comp in enumerate(rbm.components_):
	plt.subplot(10, 10, i + 1)
	plt.imshow(comp.reshape((28, 28)), cmap=plt.cm.gray_r)
	plt.xticks(())
	plt.yticks(())
	plt.suptitle('100 components extracted by RBM', fontsize=16)
plt.show()

# Use our Boltzman Machine to transform
image_new_features = rbm.transform(images_X)




#RBMs在机器学习pipeline中的使用

#逻辑回归模型先在原始数据上进行分类预测，获得准确率的baseline。之后在PCA和RBM成分上进行分类预测，看效果是提升还是下降。
# import logistic regression and gridsearch module for some machine learning
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV
# create our logistic regression
lr = LogisticRegression()
params = {'C':[1e-2, 1e-1, 1e0, 1e1, 1e2]}
# instantiate a gridsearch class
grid = GridSearchCV(lr, params)
# fit to our data
grid.fit(images_X, images_y)
# check the best params
grid.best_params_, grid.best_score_

# Use PCA to extract new features
lr = LogisticRegression()
pca = PCA()
# set the params for the pipeline
params = {'clf__C':[1e-1, 1e0, 1e1],'pca__n_components': [10, 100, 200]}
# create our pipeline
pipeline = Pipeline([('pca', pca), ('clf', lr)])
# instantiate a gridsearh class
grid = GridSearchCV(pipeline, params)
# fit to our data
grid.fit(images_X, images_y)
# check the best params
grid.best_params_, grid.best_score_

# Use the RBM to learn new features
rbm = BernoulliRBM(random_state=0)
# set up the params for our pipeline.
params = {'clf__C':[1e-1, 1e0, 1e1],'rbm__n_components': [10, 100, 200]}
# create our pipeline
pipeline = Pipeline([('rbm', rbm), ('clf', lr)])
# instantiate a gridsearch class
grid = GridSearchCV(pipeline, params)
# fit to our data
grid.fit(images_X, images_y)
# check the best params
grid.best_params_, grid.best_score_