linear_regression.py

def run_training(train_X, train_Y):
    # inputs
    X = tf.placeholder(tf.float32, [m, n])
    Y = tf.placeholder(tf.float32, [m, 1])

    # weight and bias
    W = tf.Variable(tf.zeros([n, 1], dtype=np.float32), name="weight")
    b = tf.Variable(tf.zeros([1], dtype=np.float32), name="bias")

    # linear model
    with tf.name_scope("linear_Wx_b") as scope:
        activation = tf.add(tf.matmul(X, W), b)

    # cost
    with tf.name_scope("cost") as scope:
        cost = tf.reduce_sum(tf.square(activation - Y)) / (2 * m)
        tf.summary.scalar("cost", cost)

    # train
    with tf.name_scope("train") as scope:
        optimizer = tf.train.GradientDescentOptimizer(0.07).minimize(cost)

    # tensorflow session
    with tf.Session() as sess:
        merged = tf.summary.merge_all()
        writer = tf.summary.FileWriter(log_file, sess.graph)

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

        for step in range(1500):
            result, _ = sess.run([merged, optimizer], feed_dict={X: np.asarray(train_X), Y: np.asarray(train_Y)})
            writer.add_summary(result, step)

        print "Optimization"
        training_cost = sess.run(cost, feed_dict={X: np.asarray(train_X), Y: np.asarray(train_Y)})
        print "Training Cost: ", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n'

        print "Prediction for 3.5 years"
        predict_X = np.array([3.5], dtype=np.float32).reshape([1, 1])

        predict_X = (predict_X - mean) / std
        predict_Y = tf.add(tf.matmul(predict_X, W), b)
        print "Child height(Y) =", sess.run(predict_Y)

        print "Predict for 7 years"
        predict_X_2 = np.array([7], dtype=np.float32).reshape([1, 1])
        predict_X_2 = (predict_X_2 - mean) / std
        predict_Y_2 = tf.add(tf.matmul(predict_X_2, W), b)
        print "Child height(Y) =", sess.run(predict_Y_2)