Difference between revisions of "Keras-timeseries-stock-tata-predict"

From OnnoWiki
Jump to navigation Jump to search
 
(One intermediate revision by the same user not shown)
Line 1: Line 1:
 
Sumber: https://www.kdnuggets.com/2018/11/keras-long-short-term-memory-lstm-model-predict-stock-prices.html
 
Sumber: https://www.kdnuggets.com/2018/11/keras-long-short-term-memory-lstm-model-predict-stock-prices.html
 +
 +
 +
 +
# '''
 +
# https://www.kdnuggets.com/2018/11/keras-long-short-term-memory-lstm-model-predict-stock-prices.html
 +
# '''
 +
 +
import numpy as np
 +
import matplotlib.pyplot as plt
 +
import pandas as pd
 +
 +
# https://raw.githubusercontent.com/mwitiderrick/stockprice/master/NSE-TATAGLOBAL.csv
 +
dataset_train = pd.read_csv('NSE-TATAGLOBAL.csv')
 +
training_set = dataset_train.iloc[:, 1:2].values
 +
 +
# check head
 +
dataset_train.head()
 +
 +
# scaling
 +
from sklearn.preprocessing import MinMaxScaler
 +
sc = MinMaxScaler(feature_range = (0, 1))
 +
training_set_scaled = sc.fit_transform(training_set)
 +
 +
# create data with time step
 +
X_train = []
 +
y_train = []
 +
for i in range(60, 2035):
 +
    X_train.append(training_set_scaled[i-60:i, 0])
 +
    y_train.append(training_set_scaled[i, 0])
 +
X_train, y_train = np.array(X_train), np.array(y_train)
 +
 +
X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))
 +
 +
# train
 +
from keras.models import Sequential
 +
from keras.layers import Dense
 +
from keras.layers import LSTM
 +
from keras.layers import Dropout
 +
 +
regressor = Sequential()
 +
regressor.add(LSTM(units = 50, return_sequences = True, input_shape = (X_train.shape[1], 1)))
 +
regressor.add(Dropout(0.2))
 +
regressor.add(LSTM(units = 50, return_sequences = True))
 +
regressor.add(Dropout(0.2))
 +
regressor.add(LSTM(units = 50, return_sequences = True))
 +
regressor.add(Dropout(0.2))
 +
regressor.add(LSTM(units = 50))
 +
regressor.add(Dropout(0.2))
 +
regressor.add(Dense(units = 1))
 +
regressor.compile(optimizer = 'adam', loss = 'mean_squared_error')
 +
regressor.fit(X_train, y_train, epochs = 100, batch_size = 32)
 +
 +
# test
 +
# https://raw.githubusercontent.com/mwitiderrick/stockprice/master/tatatest.csv
 +
dataset_test = pd.read_csv('tatatest.csv')
 +
real_stock_price = dataset_test.iloc[:, 1:2].values
 +
 +
dataset_total = pd.concat((dataset_train['Open'], dataset_test['Open']), axis = 0)
 +
inputs = dataset_total[len(dataset_total) - len(dataset_test) - 60:].values
 +
inputs = inputs.reshape(-1,1)
 +
inputs = sc.transform(inputs)
 +
X_test = []
 +
for i in range(60, 76):
 +
    X_test.append(inputs[i-60:i, 0])
 +
X_test = np.array(X_test)
 +
X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))
 +
predicted_stock_price = regressor.predict(X_test)
 +
predicted_stock_price = sc.inverse_transform(predicted_stock_price)
 +
 +
# Plot
 +
plt.plot(real_stock_price, color = 'black', label = 'TATA Stock Price')
 +
plt.plot(predicted_stock_price, color = 'green', label = 'Predicted TATA Stock Price')
 +
plt.title('TATA Stock Price Prediction')
 +
plt.xlabel('Time')
 +
plt.ylabel('TATA Stock Price')
 +
plt.legend()
 +
plt.show()
 +
 +
==Pranala Menarik==
 +
 +
* [[Keras]]

Latest revision as of 08:11, 6 August 2019

Sumber: https://www.kdnuggets.com/2018/11/keras-long-short-term-memory-lstm-model-predict-stock-prices.html


# 
# https://www.kdnuggets.com/2018/11/keras-long-short-term-memory-lstm-model-predict-stock-prices.html
# 

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# https://raw.githubusercontent.com/mwitiderrick/stockprice/master/NSE-TATAGLOBAL.csv
dataset_train = pd.read_csv('NSE-TATAGLOBAL.csv')
training_set = dataset_train.iloc[:, 1:2].values

# check head
dataset_train.head()

# scaling
from sklearn.preprocessing import MinMaxScaler
sc = MinMaxScaler(feature_range = (0, 1))
training_set_scaled = sc.fit_transform(training_set)

# create data with time step
X_train = []
y_train = []
for i in range(60, 2035):
    X_train.append(training_set_scaled[i-60:i, 0])
    y_train.append(training_set_scaled[i, 0])
X_train, y_train = np.array(X_train), np.array(y_train) 

X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))

# train
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Dropout

regressor = Sequential()
regressor.add(LSTM(units = 50, return_sequences = True, input_shape = (X_train.shape[1], 1)))
regressor.add(Dropout(0.2))
regressor.add(LSTM(units = 50, return_sequences = True))
regressor.add(Dropout(0.2))
regressor.add(LSTM(units = 50, return_sequences = True))
regressor.add(Dropout(0.2))
regressor.add(LSTM(units = 50))
regressor.add(Dropout(0.2))
regressor.add(Dense(units = 1))
regressor.compile(optimizer = 'adam', loss = 'mean_squared_error')
regressor.fit(X_train, y_train, epochs = 100, batch_size = 32)

# test
# https://raw.githubusercontent.com/mwitiderrick/stockprice/master/tatatest.csv
dataset_test = pd.read_csv('tatatest.csv')
real_stock_price = dataset_test.iloc[:, 1:2].values

dataset_total = pd.concat((dataset_train['Open'], dataset_test['Open']), axis = 0)
inputs = dataset_total[len(dataset_total) - len(dataset_test) - 60:].values
inputs = inputs.reshape(-1,1)
inputs = sc.transform(inputs)
X_test = []
for i in range(60, 76):
    X_test.append(inputs[i-60:i, 0])
X_test = np.array(X_test)
X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))
predicted_stock_price = regressor.predict(X_test)
predicted_stock_price = sc.inverse_transform(predicted_stock_price)

# Plot
plt.plot(real_stock_price, color = 'black', label = 'TATA Stock Price')
plt.plot(predicted_stock_price, color = 'green', label = 'Predicted TATA Stock Price')
plt.title('TATA Stock Price Prediction')
plt.xlabel('Time')
plt.ylabel('TATA Stock Price')
plt.legend()
plt.show()

Pranala Menarik