Machine Learning Stock Prediction with LSTM and Keras – Python Source Code

Python Source Code for Machine Learning Stock Prediction with LSTM and Keras – Python Source Code with LSTM and Keras Below is the code for machine learning stock prediction with LSTM neural network.

# -*- coding: utf-8 -*-

import numpy as np
import pandas as pd
from sklearn import preprocessing
import matplotlib.pyplot as plt

data_csv = pd.read_csv (fname)

#how many data we will use 
# (should not be more than dataset length )
data_to_use= 100

# number of training data
# should be less than data_to_use
train_end =70


#most recent data is in the end 
#so need offset
start=total_data - data_to_use

#currently doing prediction only for 1 step ahead
steps_to_predict =1

yt = data_csv.iloc [start:total_data ,4]    #Close price
yt1 = data_csv.iloc [start:total_data ,1]   #Open
yt2 = data_csv.iloc [start:total_data ,2]   #High
yt3 = data_csv.iloc [start:total_data ,3]   #Low
vt = data_csv.iloc [start:total_data ,6]    # volume

print ("yt head :")
print (yt.head())

yt_ = yt.shift (-1)
data = pd.concat ([yt, yt_, vt, yt1, yt2, yt3], axis =1)
data. columns = ['yt', 'yt_', 'vt', 'yt1', 'yt2', 'yt3']
data = data.dropna()
print (data)
# target variable - closed price
# after shifting
y = data ['yt_']

#       closed,  volume,   open,  high,   low    
cols =['yt',    'vt',  'yt1', 'yt2', 'yt3']
x = data [cols]

scaler_x = preprocessing.MinMaxScaler ( feature_range =( -1, 1))
x = np. array (x).reshape ((len( x) ,len(cols)))
x = scaler_x.fit_transform (x)

scaler_y = preprocessing. MinMaxScaler ( feature_range =( -1, 1))
y = np.array (y).reshape ((len( y), 1))
y = scaler_y.fit_transform (y)

x_train = x [0: train_end,]
x_test = x[ train_end +1:len(x),]    
y_train = y [0: train_end] 
y_test = y[ train_end +1:len(y)]  
x_train = x_train.reshape (x_train. shape + (1,)) 
x_test = x_test.reshape (x_test. shape + (1,))


from keras.models import Sequential
from keras.layers.core import Dense
from keras.layers.recurrent import LSTM
from keras.layers import  Dropout

seed =2016 
np.random.seed (seed)
fit1 = Sequential ()
fit1.add (LSTM (  1000 , activation = 'tanh', inner_activation = 'hard_sigmoid' , input_shape =(len(cols), 1) ))
fit1.add (Dense (output_dim =1, activation = 'linear'))

fit1.compile (loss ="mean_squared_error" , optimizer = "adam") (x_train, y_train, batch_size =16, nb_epoch =25, shuffle = False)

print (fit1.summary())

score_train = fit1.evaluate (x_train, y_train, batch_size =1)
score_test = fit1.evaluate (x_test, y_test, batch_size =1)
print (" in train MSE = ", round( score_train ,4)) 
print (" in test MSE = ", score_test )

pred1 = fit1.predict (x_test) 
pred1 = scaler_y.inverse_transform (np. array (pred1). reshape ((len( pred1), 1)))

prediction_data = pred1[-1]     

print ("Inputs: {}".format(fit1.input_shape))
print ("Outputs: {}".format(fit1.output_shape))
print ("Actual input: {}".format(x_test.shape))
print ("Actual output: {}".format(y_test.shape))

print ("prediction data:")
print (prediction_data)

print ("actual data")
x_test = scaler_x.inverse_transform (np. array (x_test). reshape ((len( x_test), len(cols))))
print (x_test)

plt.plot(pred1, label="predictions")

y_test = scaler_y.inverse_transform (np. array (y_test). reshape ((len( y_test), 1)))
plt.plot( [row[0] for row in y_test], label="actual")

plt.legend(loc='upper center', bbox_to_anchor=(0.5, -0.05),
          fancybox=True, shadow=True, ncol=2)

import matplotlib.ticker as mtick
fmt = '$%.0f'
tick = mtick.FormatStrFormatter(fmt)

ax = plt.axes()

1. Machine Learning Stock Prediction with LSTM and Keras – Python Source Code with LSTM and Keras

9 thoughts on “Machine Learning Stock Prediction with LSTM and Keras – Python Source Code

  1. Hi owygs156,

    Thanks for writing this, it was very helpful. One quick question, shouldn’t we be plotting pred1 in relation to y_test, not x_test[:, 0]? pred1[0] contains the prediction corresponding to y_test[0], which is the close price from x_test[1, 0].


  2. Hi Alan,
    glad that you find it helpful. You are correct, it should be in relation to y_test. I updated code and graphs. Thanks for pointing out on this.

  3. Very impressive! I see that you have used 1 LSTM layer for each model and it had good results. Is there a way to make these predictions for the future? rather than comparing them to actual past data?

  4. Can you please kindly share full code after fixing the issue outlined in above comment?

    pred1 in relation to y_test, not x_test[:, 0]?


Leave a Comment