Restricted Boltzmann Machine:
Geoff Hinton发明
降低维度, 分类, 回归, 特征学习
非监督学习(unsupervised learning)
plot_rbm_logistic_classfica.py :对数据直接扩大5倍并进行处理
# Authors: Yann N. Dauphin, Vlad Niculae, Gabriel Synnaeve
# License: BSD
import numpy as np
import matplotlib.pyplot as plt
from scipy.ndimage import convolve
from sklearn import linear_model, datasets, metrics
from sklearn.model_selection import train_test_split
from sklearn.neural_network import BernoulliRBM
from sklearn.pipeline import Pipeline
###############################################################################
# Setting up
def nudge_dataset(X, Y):
direction_vectors = [[[0, 1, 0],[0, 0, 0],
[0, 0, 0]],
[[0, 0, 0],
[1, 0, 0],
[0, 0, 0]],
[[0, 0, 0],
[0, 0, 1],
[0, 0, 0]],
[[0, 0, 0],
[0, 0, 0],
[0, 1, 0]]]
shift = lambda x, w: convolve(x.reshape((8, 8)), mode='constant',weights=w).ravel()
X = np.concatenate([X] +[np.apply_along_axis(shift, 1, X, vector) for vector in direction_vectors])
Y = np.concatenate([Y for _ in range(5)], axis=0)
return X, Y
# Load Data
digits = datasets.load_digits()
X = np.asarray(digits.data, 'float32')
X, Y = nudge_dataset(X, digits.target) #返回扩大集之后的feature 与 label
X = (X - np.min(X, 0)) / (np.max(X, 0) + 0.0001) # 0-1 scaling
X_train, X_test, Y_train, Y_test = train_test_split(X, Y,test_size=0.2,random_state=0)
# Models we will use
logistic = linear_model.LogisticRegression()
rbm = BernoulliRBM(random_state=0, verbose=True)
classifier = Pipeline(steps=[('rbm', rbm), ('logistic', logistic)])
###############################################################################
# Training
# Hyper-parameters. These were set by cross-validation,
# using a GridSearchCV. Here we are not performing cross-validation to
# save time.
rbm.learning_rate = 0.06
rbm.n_iter = 20
# More components tend to give better prediction performance, but larger
# fitting time
rbm.n_components = 100
logistic.C = 6000.0
# Training RBM-Logistic Pipeline
classifier.fit(X_train, Y_train)
# Training Logistic regression
logistic_classifier = linear_model.LogisticRegression(C=100.0)
logistic_classifier.fit(X_train, Y_train)
###############################################################################
# Evaluation
print()
print("Logistic regression using RBM features:\n%s\n" % (metrics.classification_report(Y_test,classifier.predict(X_test))))
print("Logistic regression using raw pixel features:\n%s\n" % (metrics.classification_report(Y_test,logistic_classifier.predict(X_test))))
###############################################################################
# Plotting
plt.figure(figsize=(4.2, 4))
for i, comp in enumerate(rbm.components_):
plt.subplot(10, 10, i + 1)
plt.imshow(comp.reshape((8, 8)), cmap=plt.cm.gray_r,interpolation='nearest')
plt.xticks(())
plt.yticks(())
plt.suptitle('100 components extracted by RBM', fontsize=16)
plt.subplots_adjust(0.08, 0.02, 0.92, 0.85, 0.08, 0.23)
plt.show()
代码调试:
Rutuen X,Y
→
'return' outside of function
→注意定义def后,需要缩进