Skip to content

Instantly share code, notes, and snippets.

@lukovkin
Last active November 25, 2022 16:23
Show Gist options
  • Save lukovkin/1aefa4509e066690b892 to your computer and use it in GitHub Desktop.
Save lukovkin/1aefa4509e066690b892 to your computer and use it in GitHub Desktop.
Time series prediction with multiple sequences input - LSTM - 1
# Time Series Testing
import keras.callbacks
from keras.models import Sequential
from keras.layers.core import Dense, Activation, Dense, Dropout
from keras.layers.recurrent import LSTM
# Call back to capture losses
class LossHistory(keras.callbacks.Callback):
def on_train_begin(self, logs={}):
self.losses = []
def on_batch_end(self, batch, logs={}):
self.losses.append(logs.get('loss'))
# You should get data frames with prices somewhere, e.g. on Quandl - implementation is up to you
# merge data frames
merged = df1.merge(df2, left_index=True, right_index=True, how='inner').dropna()
# data prep
# use 100 days of historical data to predict 10 days in the future
data = merged.values
examples = 100
y_examples = 10
nb_samples = len(data) - examples - y_examples
# input - 2 features
input_list = [np.expand_dims(np.atleast_2d(data[i:examples+i,:]), axis=0) for i in xrange(nb_samples)]
input_mat = np.concatenate(input_list, axis=0)
# target - the first column in merged dataframe
target_list = [np.atleast_2d(data[i+examples:examples+i+y_examples,0]) for i in xrange(nb_samples)]
target_mat = np.concatenate(target_list, axis=0)
# set up model
trials = input_mat.shape[0]
features = input_mat.shape[2]
hidden = 64
model = Sequential()
model.add(LSTM(hidden, input_shape=(examples, features)))
model.add(Dropout(.2))
model.add(Dense(y_examples))
model.add(Activation('linear'))
model.compile(loss='mse', optimizer='rmsprop')
# Train
history = LossHistory()
model.fit(input_mat, target_mat, nb_epoch=100, batch_size=400, callbacks=[history])
@Sudarsan9966
Copy link

Sudarsan9966 commented Feb 17, 2017

Hi,
Could you please tell me how to predict the next 10 days in future? (i.e.) the steps after model.fit and how to evaluate this model.
Also is it possible to do multiple sequences input with Stateful LSTM?

Thanks in advance.

@bv123
Copy link

bv123 commented Feb 20, 2017

Hi,
I am also looking on how to predict the future 10 days.
Any help on the same will be really helpful.
Thanks in advance.

@ukeshchawal
Copy link

Can you help me solve this issue?

I am new to deep learning and LSTM. I have a very simple question. I have taken a sample of demands for 50 time steps and I am trying to forecast the demand value for the next 10 time steps (up to 60 time steps) using the same 50 samples to train the model.

But unfortunately, the closest I came is splitting the sample demands into 67 training % and 33 testing % and my forecast is only forecasting for the 33% (35 - 50 time steps), but it never goes beyond 50 time steps. Can anybody help me with this issue?

I have attached my code below.

Thank you in advance.

import pandas
import matplotlib.pyplot as plt
dataset = pandas.read_csv('Dmd2ahr.csv')
plt.plot(dataset)
plt.show()

LSTM for international airline passengers problem with window regression framing

import numpy
import matplotlib.pyplot as plt
from pandas import read_csv
import math
from keras.models import Sequential
from keras.layers import Dropout
from keras.layers import Dense
from keras.layers import LSTM
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error

convert an array of values into a dataset matrix

def create_dataset(dataset, look_back=1):
dataX, dataY = [], []
for i in range(len(dataset)-look_back-1):
a = dataset[i:(i+look_back), 0]
dataX.append(a)
dataY.append(dataset[i + look_back, 0])
return numpy.array(dataX), numpy.array(dataY)

fix random seed for reproducibility

numpy.random.seed(7)

load the dataset

dataframe = read_csv('Dmd2ahr.csv')
dataset = dataframe.values
dataset = dataset.astype('float32')

normalize the dataset

scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)

split into train and test sets

train_size = int(len(dataset) * 0.7)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
print(len(train), len(test))

reshape into X=t and Y=t+1

look_back = 3
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)

reshape input to be [samples, time steps, features]

#trainX = numpy.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
#testX = numpy.reshape(testX, (testX.shape[0], 1, testX.shape[1]))

reshape input to be [samples, time steps, features]

trainX = numpy.reshape(trainX, (trainX.shape[0], trainX.shape[1], 1))
testX = numpy.reshape(testX, (testX.shape[0], testX.shape[1], 1))

create and fit the LSTM network

model = Sequential()
model.add(LSTM(32, input_shape=(look_back, 1)))
model.add(Dropout(0.3))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam', metrics = ['accuracy'])
model.fit(trainX, trainY, epochs=300, batch_size=1, verbose=2)

make predictions

trainPredict = model.predict(trainX)
testPredict = model.predict(testX)

invert predictions

trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])

calculate root mean squared error

trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
print('Test Score: %.2f RMSE' % (testScore))

shift train predictions for plotting

trainPredictPlot = numpy.empty_like(dataset)
trainPredictPlot[:, :] = numpy.nan
trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict

shift test predictions for plotting

testPredictPlot = numpy.empty_like(dataset)
testPredictPlot[:, :] = numpy.nan
testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1, :] = testPredict

plot baseline and predictions

plt.plot(scaler.inverse_transform(dataset))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.show()
print (trainPredict)
print (testPredict)

@sarahboufelja
Copy link

Dear lukovkin, Suppose I have multiple time series as input and I need to predict all these time series at once for the next 10 days, how should I reshape the input and target datasets?
Regards

@kascesar
Copy link

Hi,
Could you please tell me how to predict the next 10 days in future? (i.e.) the steps after model.fit and how to evaluate this model.
Also is it possible to do multiple sequences input with Stateful LSTM?

Thanks in advance.

u need tu put a Dense layer as output with 10 units, and train your network with the same structure N-imputs and 10 outputs values

@SyedHasnat
Copy link

Hello!
Would you like to help me?
I am stuck on a problem, how to fit a multiple input CNN or LSTM model.
I have a time series data divided (split) into train, test, and validation
I want to give the same training data to two different CNN models and concatenate them. I have built the model as shown in the figure, input shape =168,23
IMG-20220810-WA0058
My network is;
IMG-20220810-WA0055
but I am not getting how to fit this model.
once I tried to fit the model I face the error
IMG-20220810-WA0059(1)

@sarahboufelja @bv123 @kascesar @Sudarsan9966 will be waiting for your kind reply.
Thank you

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment