TensorFlow

tf.py

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plot
import pandas as pd
import csv

def load_data_points(filename):
    print("Opening CSV file")
    with open(filename) as csvfile:
        print("Creating CSV reader")
        reader = csv.reader(csvfile)
        print("Reading CSV")
        return [[[float(p)] for p in row] for row in reader]

flatten = lambda l: [item for sublist in l for item in sublist]

data_points = load_data_points('dataset.csv')

print("Loaded")

prediction_size = 10
num_test_rows = 1
num_data_rows = len(data_points) - num_test_rows
row_size = len(data_points[0]) - prediction_size

# Training data
data_rows = data_points[:-num_test_rows]
x_data_points = np.array([row[:-prediction_size] for row in data_rows]).reshape([-1, row_size, 1])
y_data_points = np.array([row[prediction_size:] for row in data_rows]).reshape([-1, row_size, 1])

# Test data
test_rows = data_points[-num_test_rows:]
x_test_points = np.array([[data_points[0][:-prediction_size]]]).reshape([-1, row_size, 1])
y_test_points = np.array([[data_points[0][prediction_size:]]]).reshape([-1, row_size, 1])

tf.reset_default_graph()

num_hidden = 100

x = tf.placeholder(tf.float32, [None, row_size, 1])
y = tf.placeholder(tf.float32, [None, row_size, 1])

basic_cell = tf.contrib.rnn.BasicRNNCell(num_units=num_hidden, activation=tf.nn.relu)
rnn_outputs, _ = tf.nn.dynamic_rnn(basic_cell, x, dtype=tf.float32)

learning_rate = 0.001

stacked_rnn_outputs = tf.reshape(rnn_outputs, [-1, num_hidden])
stacked_outputs = tf.layers.dense(stacked_rnn_outputs, 1)
outputs = tf.reshape(stacked_outputs, [-1, row_size, 1])

loss = tf.reduce_sum(tf.square(outputs - y))
optimizer = tf.train.AdamOptimizer(learning_rate)
training_op = optimizer.minimize(loss)

init = tf.global_variables_initializer()

iterations = 1000

with tf.Session() as sess:
    init.run()
    for ep in range(iterations):
        sess.run(training_op, feed_dict={x: x_data_points, y: y_data_points})
        if ep % 100 == 0:
            mse = loss.eval(feed_dict={x: x_data_points, y: y_data_points})
            print(ep, "\tMSE:", mse)

    y_pred = sess.run(stacked_outputs, feed_dict={x: x_test_points})
    
    plot.rcParams["figure.figsize"] = (20, 10)

    plot.title("Actual vs Predicted")
    plot.plot(pd.Series(np.ravel(x_test_points)), 'g:', markersize=2, label="X")
    plot.plot(pd.Series(np.ravel(y_test_points)), 'b--', markersize=2, label="Y")
    plot.plot(pd.Series(np.ravel(y_pred)), 'r-', markersize=2, label="Predicted")
    plot.legend(loc='upper left')
    plot.xlabel("Time periods")
    plot.tick_params(
        axis='y',
        which='both',
        left='off',
        right='off',
        labelleft='off')
    plot.show()