lab-12-6-rnn_softmax_stock_prediction.py

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

tf.set_random_seed(777)  # reproducibility


def MinMaxScaler(data):
    num_row = np.shape(data)[0]
    num_col = np.shape(data)[1]
    array = np.zeros((num_row, num_col))
    for i in range(num_col):
        input = data[:, i]
        array[:, i] = (input - np.min(input)) / (np.max(input) - np.min(input))
    return array

timesteps = seq_length = 7
data_dim = 5
output_dim = 3

# Open,High,Low,Close,Volume
xy = np.loadtxt('data-02-stock_daily.csv', delimiter=',')
xy = xy[::-1]  # reverse order (chronically ordered)
xy = MinMaxScaler(xy)

x = xy
y = xy[:, [-1]]  # Close as label

dataX = []
dataY = []
for i in range(0, len(y) - seq_length):
    _x = x[i:i + seq_length]
    _y = y[i + seq_length]  # Next close price as target
    print(_x, "->", _y)
    dataX.append(_x)
    dataY.append(_y)

# split to train and testing
train_size = int(len(dataY) * 0.7)
test_size = len(dataY) - train_size
trainX, testX = np.array(dataX[0:train_size]), np.array(
    dataX[train_size:len(dataX)])
trainY, testY = np.array(dataY[0:train_size]), np.array(
    dataY[train_size:len(dataY)])

# input place holders
X = tf.placeholder(tf.float32, [None, seq_length, data_dim])
Y = tf.placeholder(tf.float32, [None, 1])

cell = tf.contrib.rnn.BasicLSTMCell(num_units=output_dim, state_is_tuple=True)
cell = tf.contrib.rnn.MultiRNNCell([cell] * 2, state_is_tuple=True)
outputs, _states = tf.nn.dynamic_rnn(cell, X, dtype=tf.float32)
last_output = outputs[:, -1]  # We use the last cell's output

# Softmax layer (rnn_hidden_size -> num_classes)
softmax_w = tf.get_variable("softmax_w", [output_dim, 1])
softmax_b = tf.get_variable("softmax_b", [1])
Y_pred = tf.matmul(last_output,  softmax_w) + softmax_b

# cost/loss
loss = tf.reduce_sum(tf.square(Y_pred - Y))  # sum of the squares
# optimizer
optimizer = tf.train.GradientDescentOptimizer(0.001)
train = optimizer.minimize(loss)

# RMSE
targets = tf.placeholder(tf.float32, [None, 1])
predictions = tf.placeholder(tf.float32, [None, 1])
rmse = tf.sqrt(tf.reduce_mean(tf.square(targets - predictions)))

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

for i in range(1000):
    _, l = sess.run([train, loss], feed_dict={X: trainX, Y: trainY})
    print(i, l)

testPredict = sess.run(Y_pred, feed_dict={X: testX})
print("RMSE", sess.run(rmse, feed_dict={
      targets: testY, predictions: testPredict}))
plt.plot(testY)
plt.plot(testPredict)
plt.show()