Try not to peek at the solutions when you go through the exercises. ;-)

First let's make sure this notebook works well in both Python 2 and Python 3:



In [ ]:

    
from __future__ import absolute_import, division, print_function, unicode_literals



In [ ]:

    
import tensorflow as tf
tf.__version__

From previous notebooks



In [ ]:

    
learning_rate = 0.01
momentum = 0.8

Using Readers



In [ ]:

    
filenames = ["data/life_satisfaction.csv"]
n_epochs = 500

graph = tf.Graph()
with graph.as_default():
    reader = tf.TextLineReader(skip_header_lines=1)

    filename_queue = tf.train.string_input_producer(filenames, num_epochs=n_epochs)
    record_id, record = reader.read(filename_queue)

    record_defaults = [[''], [0.0], [0.0]]
    country, gdp_per_capita, life_satisfaction = tf.decode_csv(record, record_defaults=record_defaults)



In [ ]:

    
batch_size = 5
with graph.as_default():
    X_batch, y_batch = tf.train.batch([gdp_per_capita, life_satisfaction], batch_size=batch_size)
    X_batch_reshaped = tf.reshape(X_batch, [-1, 1])
    y_batch_reshaped = tf.reshape(y_batch, [-1, 1])



In [ ]:

    
with graph.as_default():
    X = tf.placeholder_with_default(X_batch_reshaped, shape=[None, 1], name="X")
    y = tf.placeholder_with_default(y_batch_reshaped, shape=[None, 1], name="y")

    b = tf.Variable(0.0, name="b")
    w = tf.Variable(tf.zeros([1, 1]), name="w")
    y_pred = tf.add(tf.matmul(X / 10000, w), b, name="y_pred")  # X @ w + b
    
    mse = tf.reduce_mean(tf.square(y_pred - y), name="mse")

    global_step = tf.Variable(0, trainable=False, name='global_step')
    optimizer = tf.train.MomentumOptimizer(learning_rate, momentum)
    training_op = optimizer.minimize(mse, global_step=global_step)

    init = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
    saver = tf.train.Saver()



In [ ]:

    
with tf.Session(graph=graph) as sess:
    init.run()
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)
    try:
        while not coord.should_stop():
            _, mse_val, global_step_val = sess.run([training_op, mse, global_step])
            if global_step_val % 100 == 0:
                print(global_step_val, mse_val)
    except tf.errors.OutOfRangeError:
        print("End of training")
    coord.request_stop()
    coord.join(threads)
    saver.save(sess, "./my_life_satisfaction_model")