Linear Model Basic ML

linearML.py

import tensorflow as tf

#model parameters
W = tf.Variable([0.3], dtype=tf.float32)
b = tf.Variable([-0.3], dtype=tf.float32)

#model input and output
x = tf.placeholder(tf.float32)
model_output = W*x + b
y = tf.placeholder(tf.float32)

#error
error = tf.reduce_sum(tf.square(model_output - y))

#optimizer
optimizer = tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(error)

#training
x_train = [1, 2, 3, 4]
y_train = [0, -1, -2, -3]

init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

for i in range(2080798758):
	sess.run(train, {x: x_train, y: y_train})


#evaluate
final_W, final_b, final_error = sess.run([W, b, error],{x: x_train, y:y_train})
print("W: %s b: %s error: %s"%(final_W,final_b,final_error))