-
Notifications
You must be signed in to change notification settings - Fork 0
/
model.py
212 lines (146 loc) · 4.91 KB
/
model.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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
# -*- coding: utf-8 -*-
"""Untitled.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1YPE7cupT5P6H07WMjq7WKNH8LCUVXt5C
### Stock Market Prediction And Forecasting Using Stacked LSTM
"""
### Keras and Tensorflow >2.0
### Data Collection
import pandas_datareader as pdr
key="613e326124e4bc913a40eac66f133572b2f62811"
df = pdr.get_data_tiingo('AAPL', api_key=key)
df.to_csv('AAPL.csv')
import pandas as pd
df=pd.read_csv('AAPL.csv')
df.head()
df.tail()
df1=df.reset_index()['close']
df1
import matplotlib.pyplot as plt
plt.plot(df1)
### LSTM are sensitive to the scale of the data. so we apply MinMax scaler
import numpy as np
df1
from sklearn.preprocessing import MinMaxScaler
scaler=MinMaxScaler(feature_range=(0,1))
df1=scaler.fit_transform(np.array(df1).reshape(-1,1))
df1
print(df1)
##splitting dataset into train and test split
training_size=int(len(df1)*0.65)
test_size=len(df1)-training_size
train_data,test_data=df1[0:training_size,:],df1[training_size:len(df1),:1]
training_size,test_size
train_data
import numpy
# convert an array of values into a dataset matrix
def create_dataset(dataset, time_step=1):
dataX, dataY = [], []
for i in range(len(dataset)-time_step-1):
a = dataset[i:(i+time_step), 0] ###i=0, 0,1,2,3-----99 100
dataX.append(a)
dataY.append(dataset[i + time_step, 0])
return numpy.array(dataX), numpy.array(dataY)
# reshape into X=t,t+1,t+2,t+3 and Y=t+4
time_step = 100
X_train, y_train = create_dataset(train_data, time_step)
X_test, ytest = create_dataset(test_data, time_step)
print(X_train.shape), print(y_train.shape)
print(X_test.shape), print(ytest.shape)
# reshape input to be [samples, time steps, features] which is required for LSTM
X_train =X_train.reshape(X_train.shape[0],X_train.shape[1] , 1)
X_test = X_test.reshape(X_test.shape[0],X_test.shape[1] , 1)
### Create the Stacked LSTM model
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import LSTM
model=Sequential()
model.add(LSTM(50,return_sequences=True,input_shape=(100,1)))
model.add(LSTM(50,return_sequences=True))
model.add(LSTM(50))
model.add(Dense(1))
model.compile(loss='mean_squared_error',optimizer='adam')
model.summary()
model.summary()
model.fit(X_train,y_train,validation_data=(X_test,ytest),epochs=100,batch_size=64,verbose=1)
import tensorflow as tf
tf.__version__
### Lets Do the prediction and check performance metrics
train_predict=model.predict(X_train)
test_predict=model.predict(X_test)
##Transformback to original form
train_predict=scaler.inverse_transform(train_predict)
test_predict=scaler.inverse_transform(test_predict)
### Calculate RMSE performance metrics
import math
from sklearn.metrics import mean_squared_error
math.sqrt(mean_squared_error(y_train,train_predict))
### Test Data RMSE
math.sqrt(mean_squared_error(ytest,test_predict))
### Plotting
# shift train predictions for plotting
look_back=100
trainPredictPlot = numpy.empty_like(df1)
trainPredictPlot[:, :] = np.nan
trainPredictPlot[look_back:len(train_predict)+look_back, :] = train_predict
# shift test predictions for plotting
testPredictPlot = numpy.empty_like(df1)
testPredictPlot[:, :] = numpy.nan
testPredictPlot[len(train_predict)+(look_back*2)+1:len(df1)-1, :] = test_predict
# plot baseline and predictions
plt.plot(scaler.inverse_transform(df1))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.show()
len(test_data)
x_input=test_data[340:].reshape(1,-1)
x_input.shape
temp_input=list(x_input)
temp_input=temp_input[0].tolist()
temp_input
# demonstrate prediction for next 10 days
from numpy import array
lst_output=[]
n_steps=100
i=0
while(i<30):
if(len(temp_input)>100):
#print(temp_input)
x_input=np.array(temp_input[1:])
print("{} day input {}".format(i,x_input))
x_input=x_input.reshape(1,-1)
x_input = x_input.reshape((1, n_steps, 1))
#print(x_input)
yhat = model.predict(x_input, verbose=0)
print("{} day output {}".format(i,yhat))
temp_input.extend(yhat[0].tolist())
temp_input=temp_input[1:]
#print(temp_input)
lst_output.extend(yhat.tolist())
i=i+1
else:
x_input = x_input.reshape((1, n_steps,1))
yhat = model.predict(x_input, verbose=0)
print(yhat[0])
temp_input.extend(yhat[0].tolist())
print(len(temp_input))
lst_output.extend(yhat.tolist())
i=i+1
print(lst_output)
day_new=np.arange(1,101)
day_pred=np.arange(101,131)
import matplotlib.pyplot as plt
len(df1)
print()
print(y_train)
plt.plot(day_new,scaler.inverse_transform(df1[1157:]))
plt.plot(day_pred,scaler.inverse_transform(lst_output))
df3=df1.tolist()
df3.extend(lst_output)
plt.plot(df3[1200:])
df3=scaler.inverse_transform(df3).tolist()
plt.plot(df3)
import pickle
pickle.dump(yhat, open('model.pkl','wb'))
model = pickle.load(open('model.pkl','rb'))