def RBM():
filename = "../data/smaller.dta"
raw_data = open(filename, 'rt')
data = np.loadtxt(raw_data, delimiter=" ")
X = data[:, :3]
Y = data[:, 3]
print(X)
print(Y)
print("training on RBM")
rbm = BernoulliRBM(random_state=0, verbose=True)
rbm.learning_rate = 0.06
rbm.n_iter = 20
rbm.n_components = 100
rbm.fit(X, Y)
predictions = rbm.transform(X)
params = rbm.get_params()
print("predictions = ", predictions)
print("rbm = ", rbm)
print("params = ", params)
y = ub_data['Personal Loan']
# for bernoullirbm all values should be of float type
X = X.astype("float32")
#scale x values from 0-1
X = scale(X)
# construct the training/testing split
(trainX, testX, trainY, testY) = train_test_split(X,
y,
test_size=0.3,
random_state=42)
# initialize the RBM + Logistic Regression pipeline
logistic = LogisticRegression()
# BernoulliRBM parameters,n_componets:int,number of binary hidden units;learning_rate:float,rate for weight updates
# n_iter : int, Number of iterations/sweeps over the training dataset to perform during training.
# verbose : int,verbosity level;verbose : int,A random number generator instance to define the state of the random permutations generator
rbm = BernoulliRBM(n_components=2,learning_rate=0.1,n_iter=10,\
random_state=None,verbose=10)
classifier = Pipeline(steps=[('rbm', rbm), ('logistic', logistic)])
classifier.fit(trainX, trainY)
# Get parameters for this estimator.deep: boolean,If True, will return the parameters for this estimator and contained subobjects that are estimators.
print rbm.get_params(deep=True)
#Compute the pseudo-likelihood of argument.it computes a quantity called the free energy on X, then on a randomly corrupted version of X,
# and returns the log of the logistic function of the difference.
#print rbm.score_samples(trainX)
print("using RBM features:\n%s\n" %
(classification_report(testY, classifier.predict(testX))))
