forked from umeshpalai/Algorithmic-trading
-
Notifications
You must be signed in to change notification settings - Fork 0
/
StockPrediction_Deep learning_ANN_TF.py
163 lines (131 loc) · 5.34 KB
/
StockPrediction_Deep learning_ANN_TF.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
# -*- coding: utf-8 -*-
"""
Created on Sat Sep 1 20:22:56 2018
@author: Umesh
"""
# Importing Libraries
import tensorflow as tf
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
import talib
import random
# Importing dataset
dataset = pd.read_csv('TATAMOTORS.NS.csv')
dataset = dataset.dropna()
dataset = dataset[['Open', 'High', 'Low', 'Close']]
#Preparing the dataset
dataset['H-L'] = dataset['High'] - dataset['Low']
dataset['O-C'] = dataset['Close'] - dataset['Open']
dataset['3day MA'] = dataset['Close'].shift(1).rolling(window = 3).mean()
dataset['10day MA'] = dataset['Close'].shift(1).rolling(window = 10).mean()
dataset['30day MA'] = dataset['Close'].shift(1).rolling(window = 30).mean()
dataset['Std_dev']= dataset['Close'].rolling(5).std()
dataset['RSI'] = talib.RSI(dataset['Close'].values, timeperiod = 9)
dataset['Williams %R'] = talib.WILLR(dataset['High'].values, dataset['Low'].values, dataset['Close'].values, 7)
dataset['Price_Rise'] = np.where(dataset['Close'].shift(-1) > dataset['Close'], 1, 0)
dataset = dataset.dropna()
data = dataset.iloc[:, 4:]
# Dimensions of data
n = data.shape[0]
p = data.shape[1]
# Make data a np.array
data = data.values
# Splitting the dataset- Training and test data
train_start = 0
train_end = int(np.floor(0.8*n))
test_start = train_end + 1
test_end = n
data_train = data[np.arange(train_start, train_end), :]
data_test = data[np.arange(test_start, test_end), :]
# Scale data
scaler = MinMaxScaler(feature_range=(-1, 1))
scaler.fit(data_train)
data_train = scaler.transform(data_train)
data_test = scaler.transform(data_test)
# Build X and y
X_train = data_train[:, 0:-1]
y_train = data_train[:, -1]
X_test = data_test[:, 0:-1]
y_test = data_test[:, -1]
# Building the Artificial Neural Network:
# Number of features in training data
n_features = X_train.shape[1]
# Neurons
n_neurons_1 = 512
n_neurons_2 = 256
n_neurons_3 = 128
# Session
net = tf.InteractiveSession()
# Placeholder
X = tf.placeholder(dtype=tf.float32, shape=[None, n_features])
Y = tf.placeholder(dtype=tf.float32, shape=[None])
# Initializers
sigma = 1
weight_initializer = tf.variance_scaling_initializer(mode="fan_avg", distribution="uniform", scale=sigma)
bias_initializer = tf.zeros_initializer()
# Hidden weights:
#Layer 1: Variables for hidden weights and biases
W_hidden_1 = tf.Variable(weight_initializer([n_features, n_neurons_1]))
bias_hidden_1 = tf.Variable(bias_initializer([n_neurons_1]))
#Layer 2: Variables for hidden weights and biases
W_hidden_2 = tf.Variable(weight_initializer([n_neurons_1, n_neurons_2]))
bias_hidden_2 = tf.Variable(bias_initializer([n_neurons_2]))
#Layer 3: Variables for hidden weights and biases
W_hidden_3 = tf.Variable(weight_initializer([n_neurons_2, n_neurons_3]))
bias_hidden_3 = tf.Variable(bias_initializer([n_neurons_3]))
# Output weights:
#Output layer: Variables for output weights and biases
W_out = tf.Variable(weight_initializer([n_neurons_3, 1]))
bias_out = tf.Variable(bias_initializer([1]))
# Hidden layer
hidden_1 = tf.nn.relu(tf.add(tf.matmul(X, W_hidden_1), bias_hidden_1))
hidden_2 = tf.nn.relu(tf.add(tf.matmul(hidden_1, W_hidden_2), bias_hidden_2))
hidden_3 = tf.nn.relu(tf.add(tf.matmul(hidden_2, W_hidden_3), bias_hidden_3))
# Output layer (transpose!)
out = tf.transpose(tf.add(tf.matmul(hidden_3, W_out), bias_out))
# Cost function
mse = tf.reduce_mean(tf.squared_difference(out, Y))
# Optimizer
opt = tf.train.AdamOptimizer().minimize(mse)
# Run initializer
net.run(tf.global_variables_initializer())
# Fitting the neural network
batch_size = 100
epochs = 10
# Run
for e in range(epochs):
# Shuffle training data
shuffle_data = np.random.permutation(np.arange(len(y_train)))
X_train = X_train[shuffle_data]
y_train = y_train[shuffle_data]
# Minibatch training
for i in range(0, len(y_train) // batch_size):
start = i * batch_size
batch_x = X_train[start:start + batch_size]
batch_y = y_train[start:start + batch_size]
# Run optimizer with batch
net.run(opt, feed_dict={X: batch_x, Y: batch_y})
#Predicting the movement of the stock
pred = net.run(out, feed_dict={X: X_test})
y_pred = pred[0]
y_pred = pred[0] > 0.5
dataset['y_pred'] = np.NaN
dataset.iloc[(len(dataset) - len(y_pred)):,-1:] = y_pred
trade_dataset = dataset.dropna()
#Computing Strategy Returns
trade_dataset['Tomorrows Returns'] = 0.
trade_dataset['Tomorrows Returns'] = np.log(trade_dataset['Close']/trade_dataset['Close'].shift(1))
trade_dataset['Tomorrows Returns'] = trade_dataset['Tomorrows Returns'].shift(-1)
trade_dataset['Strategy Returns'] = 0.
trade_dataset['Strategy Returns'] = np.where(trade_dataset['y_pred'] == True,
trade_dataset['Tomorrows Returns'], - trade_dataset['Tomorrows Returns'])
trade_dataset['Cumulative Market Returns'] = np.cumsum(trade_dataset['Tomorrows Returns'])
trade_dataset['Cumulative Strategy Returns'] = np.cumsum(trade_dataset['Strategy Returns'])
#Plotting the graph of returns
plt.figure(figsize=(10,5))
plt.plot(trade_dataset['Cumulative Market Returns'], color='r', label='Market Returns')
plt.plot(trade_dataset['Cumulative Strategy Returns'], color='g', label='Strategy Returns')
plt.legend()
plt.show()