Multivariate Time Series Forecasting with LSTMs in Keras

README.md

REF

https://machinelearningmastery.com/multivariate-time-series-forecasting-lstms-keras/ https://archive.ics.uci.edu/ml/datasets/Beijing+PM2.5+Data

s0.py

from pandas import read_csv
from datetime import datetime

def parse(x):
  return datetime.strptime(x, '%Y %m %d %H')

dataset = read_csv('raw.csv',
  parse_dates=[['year', 'month', 'day', 'hour',]],
  index_col=0,
  date_parser=parse)

dataset.drop('No', axis=1, inplace=True)
dataset.columns = ['pollution', 'dew', 'temp', 'press', 'wnd_dir', 'wnd_spd', 'snow', 'rain']
dataset.index.name = 'date'
dataset['pollution'].fillna(0, inplace=True)
dataset = dataset[24:]
print(dataset.head(5))
dataset.to_csv('pollution.csv')

"""
from pandas import read_csv
from datetime import datetime
# load data
def parse(x):
  return datetime.strptime(x, '%Y %m %d %H')
  dataset = read_csv('raw.csv',  parse_dates = [['year', 'month', 'day', 'hour']], index_col=0, date_parser=parse)
  dataset.drop('No', axis=1, inplace=True)
  # manually specify column names
  dataset.columns = ['pollution', 'dew', 'temp', 'press', 'wnd_dir', 'wnd_spd', 'snow', 'rain']
  dataset.index.name = 'date'
  # mark all NA values with 0
  dataset['pollution'].fillna(0, inplace=True)
  # drop the first 24 hours
  dataset = dataset[24:]
  # summarize first 5 rows
  print(dataset.head(5))
  # save to file
  dataset.to_csv('pollution.csv')
"""
# vim:ts=2 sts=2 ai sw=2 expandtab

s2.py

from pandas import DataFrame
from pandas import concat

def series_to_supervised(data, n_in=1, n_out=1, dropnan=True):
  n_var = 1 if type(data) is list else data.shape[1]
  df = DataFrame(data)
  cols, names = list(), list()

  for i in range(n_in, 0, -1):
    cols.append(df.shift(i))
    names += [('var%d(t-%d)' % (j + 1, i)) for j in range(n_vars)]

  for i in range(0, n_out):
    cols.append(df.shift(-i))
    if i == 0:
      names += [('var%d(t)' % (j + 1)) for j in range(n_vars)]
    else:
      names += [('var%d(t+%d)' %(j + 1, i)) for j in range(n_vars)]

  agg = concat(cols, axis=1)
  if dropnan:
    agg.dropnan(inplace=True)
  return dropnan

dataset = read_csv('pollution.csv', header=0, index_col=0)
values = dataset.values
encoder = LabelEncoder()
values[:,4] = encoder.fit_transform(values[:,4])
values = values.astype('float32')
scalar = MinMaxScalar(feature_range(0, 1))
scaled = scalar.fit_transform(values)
reframed = series_to_supervised(scaled, 1, 1)
reframed.drop(reframed.columns[[9,10,11,12,13,14,15]], axis=1, inplace=True)
print(reframed.head(5))

# vim: ts=2 sts=2 sw=2 expandtab ai

s3.py

from math import sqrt
from numpy import concatenate
from matplotlib import pyplot
from pandas import read_csv
from pandas import DataFrame
from pandas import concat
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import mean_squared_error
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM

# convert series to supervised learning
def series_to_supervised(data, n_in=1, n_out=1, dropnan=True):
	n_vars = 1 if type(data) is list else data.shape[1]
	df = DataFrame(data)
	cols, names = list(), list()
	# input sequence (t-n, ... t-1)
	for i in range(n_in, 0, -1):
		cols.append(df.shift(i))
		names += [('var%d(t-%d)' % (j+1, i)) for j in range(n_vars)]
	# forecast sequence (t, t+1, ... t+n)
	for i in range(0, n_out):
		cols.append(df.shift(-i))
		if i == 0:
			names += [('var%d(t)' % (j+1)) for j in range(n_vars)]
		else:
			names += [('var%d(t+%d)' % (j+1, i)) for j in range(n_vars)]
	# put it all together
	agg = concat(cols, axis=1)
	agg.columns = names
	# drop rows with NaN values
	if dropnan:
		agg.dropna(inplace=True)
	return agg

# load dataset
dataset = read_csv('pollution.csv', header=0, index_col=0)
values = dataset.values
# integer encode direction
encoder = LabelEncoder()
values[:,4] = encoder.fit_transform(values[:,4])
# ensure all data is float
values = values.astype('float32')
# normalize features
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(values)
# specify the number of lag hours
n_hours = 3
n_features = 8
# frame as supervised learning
reframed = series_to_supervised(scaled, n_hours, 1)
print(reframed.shape)

# split into train and test sets
values = reframed.values
n_train_hours = 365 * 24
train = values[:n_train_hours, :]
test = values[n_train_hours:, :]
# split into input and outputs
n_obs = n_hours * n_features
train_X, train_y = train[:, :n_obs], train[:, -n_features]
test_X, test_y = test[:, :n_obs], test[:, -n_features]
print(train_X.shape, len(train_X), train_y.shape)
# reshape input to be 3D [samples, timesteps, features]
train_X = train_X.reshape((train_X.shape[0], n_hours, n_features))
test_X = test_X.reshape((test_X.shape[0], n_hours, n_features))
print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)

# design network
model = Sequential()
model.add(LSTM(50, input_shape=(train_X.shape[1], train_X.shape[2])))
model.add(Dense(1))
model.compile(loss='mae', optimizer='adam')
# fit network
history = model.fit(train_X, train_y, epochs=50, batch_size=72, validation_data=(test_X, test_y), verbose=2, shuffle=False)
# plot history
pyplot.plot(history.history['loss'], label='train')
pyplot.plot(history.history['val_loss'], label='test')
pyplot.legend()
pyplot.show()

# make a prediction
yhat = model.predict(test_X)
test_X = test_X.reshape((test_X.shape[0], n_hours*n_features))
# invert scaling for forecast
inv_yhat = concatenate((yhat, test_X[:, -7:]), axis=1)
inv_yhat = scaler.inverse_transform(inv_yhat)
inv_yhat = inv_yhat[:,0]
# invert scaling for actual
test_y = test_y.reshape((len(test_y), 1))
inv_y = concatenate((test_y, test_X[:, -7:]), axis=1)
inv_y = scaler.inverse_transform(inv_y)
inv_y = inv_y[:,0]
# calculate RMSE
rmse = sqrt(mean_squared_error(inv_y, inv_yhat))
print('Test RMSE: %.3f' % rmse)

s4.py

from math import sqrt
from numpy import concatenate
from matplotlib import pyplot
from pandas import read_csv
from pandas import DataFrame
from pandas import concat
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import mean_squared_error
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM

# convert series to supervised learning
def series_to_supervised(data, n_in=1, n_out=1, dropnan=True):
	n_vars = 1 if type(data) is list else data.shape[1]
	df = DataFrame(data)
	cols, names = list(), list()
	# input sequence (t-n, ... t-1)
	for i in range(n_in, 0, -1):
		cols.append(df.shift(i))
		names += [('var%d(t-%d)' % (j+1, i)) for j in range(n_vars)]
	# forecast sequence (t, t+1, ... t+n)
	for i in range(0, n_out):
		cols.append(df.shift(-i))
		if i == 0:
			names += [('var%d(t)' % (j+1)) for j in range(n_vars)]
		else:
			names += [('var%d(t+%d)' % (j+1, i)) for j in range(n_vars)]
	# put it all together
	agg = concat(cols, axis=1)
	agg.columns = names
	# drop rows with NaN values
	if dropnan:
		agg.dropna(inplace=True)
	return agg

# load dataset
dataset = read_csv('pollution.csv', header=0, index_col=0)
values = dataset.values
# integer encode direction
encoder = LabelEncoder()
values[:,4] = encoder.fit_transform(values[:,4])
# ensure all data is float
values = values.astype('float32')
# normalize features
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(values)
# specify the number of lag hours
n_hours = 3
n_features = 8
# frame as supervised learning
reframed = series_to_supervised(scaled, n_hours, 1)
print(reframed.shape)

# split into train and test sets
values = reframed.values
n_train_hours = 365 * 24
train = values[:n_train_hours, :]
test = values[n_train_hours:, :]
# split into input and outputs
n_obs = n_hours * n_features
train_X, train_y = train[:, :n_obs], train[:, -n_features]
test_X, test_y = test[:, :n_obs], test[:, -n_features]
print(train_X.shape, len(train_X), train_y.shape)
# reshape input to be 3D [samples, timesteps, features]
train_X = train_X.reshape((train_X.shape[0], n_hours, n_features))
test_X = test_X.reshape((test_X.shape[0], n_hours, n_features))
print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)

# design network
model = Sequential()
model.add(LSTM(50, input_shape=(train_X.shape[1], train_X.shape[2])))
model.add(Dense(1))
model.compile(loss='mae', optimizer='adam')
# fit network
history = model.fit(train_X, train_y, epochs=50, batch_size=72, validation_data=(test_X, test_y), verbose=2, shuffle=False)
# plot history
pyplot.plot(history.history['loss'], label='train')
pyplot.plot(history.history['val_loss'], label='test')
pyplot.legend()
pyplot.show()

# make a prediction
yhat = model.predict(test_X)
test_X = test_X.reshape((test_X.shape[0], n_hours*n_features))
# invert scaling for forecast
inv_yhat = concatenate((yhat, test_X[:, -7:]), axis=1)
inv_yhat = scaler.inverse_transform(inv_yhat)
inv_yhat = inv_yhat[:,0]
# invert scaling for actual
test_y = test_y.reshape((len(test_y), 1))
inv_y = concatenate((test_y, test_X[:, -7:]), axis=1)
inv_y = scaler.inverse_transform(inv_y)
inv_y = inv_y[:,0]
# calculate RMSE
rmse = sqrt(mean_squared_error(inv_y, inv_yhat))
print('Test RMSE: %.3f' % rmse)