Long Short-Term Memory network is a type of Recurrent Neural Network
In [2]:
import numpy
import matplotlib.pyplot as plt
import pandas
import math
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
In [3]:
# fix random seed for reproducibility
numpy.random.seed(7)
In [4]:
# load the dataset
dataframe = pandas.read_csv('netreachvolumes.csv', usecols=[1], engine='python')
dataset = dataframe.values
dataset = dataset.astype('float32')
In [5]:
dataframe.describe()
Out[5]:
In [6]:
# normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
In [7]:
# split into train and test sets - train set ends on May 12
train_size = 61
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size-2:len(dataset),:]
print(len(train), len(test))
In [8]:
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)
In [9]:
# reshape into X=t and Y=t+1
look_back = 1
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
In [10]:
# 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]))
In [11]:
# create and fit the LSTM network
model = Sequential()
model.add(LSTM(4, input_dim=look_back))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, nb_epoch=10, batch_size=1, verbose=2)
Out[11]:
In [12]:
# 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))
In [13]:
# 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)+1-2:len(dataset)-1, :] = testPredict
# plot baseline and predictions
plt.plot(scaler.inverse_transform(dataset))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
#plt.show()
Out[13]:
In [14]:
trainPredictPlot[59]
Out[14]:
In [15]:
testPredictPlot[59]
Out[15]:
In [16]:
import numpy as np
In [17]:
np.count_nonzero(~np.isnan(testPredictPlot))
Out[17]:
In [18]:
testPredictPlot[60]
Out[18]:
In [19]:
trainPredictPlot[60:] = testPredictPlot[60:]
In [20]:
trainPredictPlot
Out[20]:
In [21]:
dataset = scaler.inverse_transform(dataset)
In [22]:
trainPredictPlot[0] = dataset[0]
In [23]:
line_up, = plt.plot(trainPredictPlot, label='predicted')
line_down, = plt.plot(dataset, label='observed')
plt.legend(labels=[line_up, line_down])
plt.show()
In [24]:
differences = trainPredictPlot -dataset
In [25]:
import numpy
differences = numpy.asarray(differences)
In [26]:
import pandas as pd
df = pd.read_csv('netreachvolumes.csv')
df.columns = [['date','volume']]
df['predicted'] = trainPredictPlot
df['difference'] = differences
In [27]:
df.to_csv("netreachdifferences.csv")
In [ ]: