def run_gru(s):
x_dims = len(x_cols[s.dataSet]) if s.dataSet in x_cols else s.lookback
random.seed(6)
np.random.seed(6)
rnn = Sequential()
rnn.add(
GRU(s.nodes,
input_shape=(None, x_dims),
kernel_initializer='he_uniform',
stateful=False))
#rnn.add(Dropout(0.15))
rnn.add(Dense(1, kernel_initializer='he_uniform'))
opt = adam(lr=s.lr, decay=0.0) #1e-3)
rnn.compile(loss='mae', optimizer=opt)
# prepare dataset as pyBrain sequential dataset
sequence = readDataSet(s.dataSet, s.dataSetDetailed, s)
if s.limit_to:
sequence = sequence[:s.limit_to]
dp = DataProcessor()
# standardize data by subtracting mean and dividing by std
#(meanSeq, stdSeq) = dp.normalize('data', sequence)
dp.windowed_normalize(sequence)
for key in sequence.keys():
if key != "data":
dp.normalize(key, sequence)
predictedInput = np.zeros((len(sequence), ))
targetInput = np.zeros((len(sequence), ))
trueData = np.zeros((len(sequence), ))
if s.dataSet in differenceSets:
predictedInputNodiff = np.zeros((len(sequence), ))
targetInputNodiff = np.zeros((len(sequence), ))
if s.dataSet in differenceSets:
backup_sequence = sequence
sequence = dp.difference(sequence, s.lookback)
allX = getX(sequence, s)
allY = np.array(sequence['data'])
allX = allX[48:]
allY = allY[48:]
#if s.dataSet not in x_cols:
# allY = allY[s.lookback:]
trainX = allX[0:s.nTrain]
trainY = allY[s.predictionStep:s.nTrain + s.predictionStep]
trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
curBatch = 1.0
callback = LossCallback()
temp_set = np.array(sequence['data'])[:48 + s.nTrain + 5]
configure_batches(48, s.batch_size,
np.reshape(temp_set, (temp_set.shape[0], 1, 1)))
rnn.fit(trainX,
trainY,
epochs=s.epochs,
batch_size=s.batch_size,
verbose=min(s.max_verbosity, 2),
callbacks=[callback])
for i in xrange(0, s.nTrain):
targetInput[i] = allY[i + s.predictionStep]
for i in tqdm(xrange(s.nTrain + s.predictionStep, len(allX)),
disable=s.max_verbosity == 0):
if i % s.retrain_interval == 0 and i > s.numLags + s.nTrain and s.online:
trainX = allX[i - s.nTrain - s.predictionStep:i - s.predictionStep]
trainY = allY[i - s.nTrain:i]
trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
temp_set = np.array(sequence['data'])[i - s.nTrain -
s.predictionStep - 48:i]
configure_batches(48, s.batch_size,
np.reshape(temp_set, (temp_set.shape[0], 1, 1)))
rnn.fit(trainX,
trainY,
epochs=s.epochs,
batch_size=s.batch_size,
verbose=2,
callbacks=[callback])
targetInput[i] = allY[i + s.predictionStep]
predictedInput[i] = rnn.predict(np.reshape(allX[i], (1, 1, x_dims)))
if s.dataSet in differenceSets:
predictedInputNodiff[i] = predictedInput[i]
targetInputNodiff[i] = targetInput[i]
predictedInput[i] = dp.inverse_difference(backup_sequence['data'],
predictedInput[i], i - 1)
targetInput[i] = dp.inverse_difference(backup_sequence['data'],
targetInput[i], i - 1)
predictedInput[0] = 0
trueData[i] = sequence['data'][i]
#predictedInput = dp.denormalize(predictedInput, meanSeq, stdSeq)
#targetInput = dp.denormalize(targetInput, meanSeq, stdSeq)
dp.windowed_denormalize(predictedInput, targetInput)
if s.dataSet in differenceSets:
# predictedInputNodiff = dp.denormalize(predictedInputNodiff)
# targetInputNodiff = dp.denormalize(targetInputNodiff)
pass
#trueData = (trueData * stdSeq) + meanSeq
dp.saveResultToFile(s.dataSet, predictedInput, targetInput, 'gru',
s.predictionStep, s.max_verbosity)
skipTrain = error_ignore_first[s.dataSet]
from plot import computeSquareDeviation
squareDeviation = computeSquareDeviation(predictedInput, targetInput)
squareDeviation[:skipTrain] = None
nrmse = np.sqrt(np.nanmean(squareDeviation)) / np.nanstd(targetInput)
if s.max_verbosity > 0:
print "", s.nodes, "NRMSE {}".format(nrmse)
mae = np.nanmean(np.abs(targetInput - predictedInput))
if s.max_verbosity > 0:
print "MAE {}".format(mae)
if s.dataSet in differenceSets:
dp.saveResultToFile(s.dataSet, predictedInputNodiff, targetInputNodiff,
'gru_nodiff', s.predictionStep, s.max_verbosity)
squareDeviation = computeSquareDeviation(predictedInputNodiff,
targetInputNodiff)
squareDeviation[:skipTrain] = None
nrmse = np.sqrt(
np.nanmean(squareDeviation)) / np.nanstd(targetInputNodiff)
if s.max_verbosity > 0:
print "", s.nodes, "NRMSE {}".format(nrmse)
mae = np.nanmean(np.abs(targetInputNodiff - predictedInputNodiff))
if s.max_verbosity > 0:
print "MAE {}".format(mae)
mase = errors.get_mase(predictedInput, targetInput,
np.roll(targetInput, 24))
if s.max_verbosity > 0:
print "MAE {}".format(mae)
return nrmse
def run_gru(s):
global global_step
global increment_global_step_op
global reset_global_step_op
global batches
global images_placeholder
global batches_op
global_step = tf.Variable(0,
name='global_step',
trainable=False,
dtype=tf.int32)
increment_global_step_op = tf.assign(global_step, global_step + 1)
reset_global_step_op = tf.assign(global_step, 0)
batches = tf.get_variable(
"batches", [s.nTrain / int(s.batch_size), s.batch_size, 1, 1],
dtype=tf.float32,
initializer=tf.zeros_initializer)
images_placeholder = tf.placeholder(tf.float32,
shape=(s.nTrain / int(s.batch_size),
s.batch_size, 1, 1))
batches_op = tf.assign(batches, images_placeholder)
x_dims = len(x_cols[s.dataSet]) if s.dataSet in x_cols else s.lookback
random.seed(6)
np.random.seed(6)
rnn = Sequential()
rnn.add(
GRU(s.nodes,
input_shape=(None, x_dims),
kernel_initializer='he_uniform',
stateful=False))
#rnn.add(Dropout(0.15))
rnn.add(Dense(1, kernel_initializer='he_uniform'))
opt = adam(lr=s.lr, decay=0.0) #1e-3)
rnn.compile(loss='mae', optimizer=opt)
# prepare dataset as pyBrain sequential dataset
sequence = readDataSet(s.dataSet, s.dataSetDetailed, s)
if s.limit_to:
sequence = sequence[:s.limit_to]
dp = DataProcessor()
# standardize data by subtracting mean and dividing by std
(meanSeq, stdSeq) = dp.normalize('data', sequence, s.nTrain)
#dp.windowed_normalize(sequence)
for key in sequence.keys():
if key != "data":
dp.normalize(key, sequence, s.nTrain)
if s.dataSet in differenceSets:
predictedInputNodiff = np.zeros((len(sequence), ))
targetInputNodiff = np.zeros((len(sequence), ))
if s.dataSet in differenceSets:
backup_sequence = sequence
sequence = dp.difference(sequence, s.lookback)
seq_full = sequence['data'].values
seq_actual = seq_full[s.front_buffer:]
allX = getX(seq_full, s)
allY = seq_actual[s.predictionStep - 1:]
predictedInput = np.full((len(allY), ), np.nan)
#if s.dataSet not in x_cols:
# allY = allY[s.lookback:]
trainX = allX[:s.nTrain]
trainY = allY[:s.nTrain]
trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
rnn.fit(trainX,
trainY,
epochs=s.epochs,
batch_size=s.batch_size,
verbose=min(s.max_verbosity, 2))
#for i in xrange(0,s.nTrain):
# targetInput[i] = allY[i+s.predictionStep]
targetInput = allY
pred_diffs = []
pred_closer_to_actual = []
isFirst = True
for i in tqdm(xrange(s.nTrain + s.predictionStep, len(allX)),
disable=s.max_verbosity == 0):
#for i in tqdm(xrange(0, len(allX)), disable=s.max_verbosity == 0):
if i % s.retrain_interval == 0 and i > s.numLags + s.nTrain and s.online:
trainX = allX[i - s.nTrain - s.predictionStep:i - s.predictionStep]
trainY = allY[i - s.nTrain - s.predictionStep:i - s.predictionStep]
trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
rnn.fit(trainX,
trainY,
epochs=s.epochs,
batch_size=s.batch_size,
verbose=0)
#targetInput[i] = allY[i]
predictedInput[i] = rnn.predict(np.reshape(allX[i], (1, 1, x_dims)))
if isFirst:
print predictedInput[i]
isFirst = False
#predictedInput[i] = targetInput[i-1440]
pred_diffs.append(abs(predictedInput[i] - allX[i][-1]))
pred_closer_to_actual.append(
abs(predictedInput[i] - targetInput[i]) < abs(predictedInput[i] -
allX[i][-1]))
if s.dataSet in differenceSets:
predictedInputNodiff[i] = predictedInput[i]
targetInputNodiff[i] = targetInput[i]
predictedInput[i] = dp.inverse_difference(backup_sequence['data'],
predictedInput[i], i - 1)
targetInput[i] = dp.inverse_difference(backup_sequence['data'],
targetInput[i], i - 1)
for i in range(s.nTrain + s.predictionStep):
predictedInput[i] = np.nan
predictedInput = dp.denormalize(predictedInput, meanSeq, stdSeq)
targetInput = dp.denormalize(targetInput, meanSeq, stdSeq)
#dp.windowed_denormalize(predictedInput, targetInput)
print "FINAL", predictedInput[-1], targetInput[-1], len(
predictedInput), len(targetInput)
if s.dataSet in differenceSets:
# predictedInputNodiff = dp.denormalize(predictedInputNodiff)
# targetInputNodiff = dp.denormalize(targetInputNodiff)
pass
dp.saveResultToFile(s.dataSet, predictedInput, targetInput, 'gru',
s.predictionStep, s.max_verbosity)
skipTrain = error_ignore_first[s.dataSet]
from plot import computeSquareDeviation
squareDeviation = computeSquareDeviation(predictedInput, targetInput)
squareDeviation[:skipTrain] = None
nrmse = np.sqrt(np.nanmean(squareDeviation)) / np.nanstd(targetInput)
if s.max_verbosity > 0:
print "", s.nodes, "NRMSE {}".format(nrmse)
mae = np.nanmean(np.abs(targetInput - predictedInput))
if s.max_verbosity > 0:
print "MAE {}".format(mae)
mase = errors.get_mase(predictedInput, targetInput,
np.roll(targetInput, s.season))
if s.max_verbosity > 0:
print "MASE {}".format(mase)
if s.dataSet in differenceSets:
dp.saveResultToFile(s.dataSet, predictedInputNodiff, targetInputNodiff,
'gru_nodiff', s.predictionStep, s.max_verbosity)
squareDeviation = computeSquareDeviation(predictedInputNodiff,
targetInputNodiff)
squareDeviation[:skipTrain] = None
nrmse = np.sqrt(
np.nanmean(squareDeviation)) / np.nanstd(targetInputNodiff)
if s.max_verbosity > 0:
print "", s.nodes, "NRMSE {}".format(nrmse)
mae = np.nanmean(np.abs(targetInputNodiff - predictedInputNodiff))
if s.max_verbosity > 0:
print "MAE {}".format(mae)
closer_rate = pred_closer_to_actual.count(True) / float(
len(pred_closer_to_actual))
if s.max_verbosity > 0:
pred_diffs.sort()
print pred_diffs[0], pred_diffs[-1], pred_diffs[int(0.9 *
len(pred_diffs))]
print "Good results:", closer_rate
return mase, closer_rate
