09.10.2023 Views

Advanced Data Analytics Using Python_ With Machine Learning, Deep Learning and NLP Examples ( 2023)

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Chapter 5

Deep Learning and Neural Networks

W = tf.Variable(tf.random_normal([X_train.

shape[1],1],stddev=.01))

b = tf.constant(1.0)

model = tf.matmul(x_t, W) + b

cost_function = tf.reduce_sum(tf.pow((y_t - model),2))

optimizer = tf.train.AdamOptimizer(learning_rate).

minimize(cost_function)

init = tf.initialize_all_variables()

with tf.Session() as sess:

sess.run(init)

w = W.eval(session = sess)

of = b.eval(session = sess)

print("Before Training ########################

#########################")

print(w,of)

print("#######################################

##########################")

step = 0

previous = 0

while(1):

step = step + 1

sess.run(optimizer, feed_dict={x_t: X_

train.reshape(X_train.shape[0],X_train.

shape[1]), y_t: y_train.reshape(y_

train.shape[0],1)})

cost = sess.run(cost_function, feed_

dict={x_t: X_train.reshape(X_train.

shape[0],X_train.shape[1]), y_t: y_

train.reshape(y_train.shape[0],1)})

107

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!