def test_forecasts(method_name):
if method_name == "mlp":
# https://stackoverflow.com/questions/56254321/error-in-ifncol-matrix-rep-argument-is-of-length-zero
# https://cran.r-project.org/web/packages/neuralnet/index.html
# published before the bug fix: https://github.com/bips-hb/neuralnet/pull/21
# The issue is still open on nnfor package: https://github.com/trnnick/nnfor/issues/8
# TODO: look for a workaround.
pytest.xfail(
"MLP currently does not work because "
"the `neuralnet` package is not yet updated with a known bug fix in ` bips-hb/neuralnet`"
)
dataset = datasets.get_dataset("constant")
(train_dataset, test_dataset, metadata) = (
dataset.train,
dataset.test,
dataset.metadata,
)
freq = metadata.freq
prediction_length = metadata.prediction_length
params = dict(
freq=freq, prediction_length=prediction_length, method_name=method_name
)
predictor = RForecastPredictor(**params)
predictions = list(predictor.predict(train_dataset))
forecast_type = (
QuantileForecast
if method_name in QUANTILE_FORECAST_METHODS
else SampleForecast
)
assert all(
isinstance(prediction, forecast_type) for prediction in predictions
)
assert all(prediction.freq == freq for prediction in predictions)
assert all(
prediction.prediction_length == prediction_length
for prediction in predictions
)
assert all(
prediction.start_date == forecast_start(data)
for data, prediction in zip(train_dataset, predictions)
)
evaluator = Evaluator()
agg_metrics, item_metrics = backtest_metrics(
test_dataset=test_dataset,
predictor=predictor,
evaluator=evaluator,
)
assert agg_metrics["mean_wQuantileLoss"] < TOLERANCE
assert agg_metrics["NRMSE"] < TOLERANCE
assert agg_metrics["RMSE"] < TOLERANCE
def gluonts_r(dataset,freq, pred_length,period=None,trunc_length=None, method_name = "ets"):
params = dict(freq=freq, prediction_length=pred_length, method_name = method_name)
predictor = RForecastPredictor(**params)
fcst = predictor.predict(dataset)
fcstlist = []
for i in fcst:
fcstlist.append(i)
return fcstlist
def r_forecast_package():
import ast
from gluonts.model.r_forecast import RForecastPredictor
dataset = get_dataset("exchange_rate", regenerate=False)
prediction_length = dataset.metadata.prediction_length
freq = dataset.metadata.freq
cardinality = ast.literal_eval(dataset.metadata.feat_static_cat[0].cardinality)
train_ds = dataset.train
test_ds = dataset.test
#--------------------
# ETS.
ets_predictor = RForecastPredictor(
freq=freq,
prediction_length=prediction_length,
method_name="ets",
)
ets_forecast = list(ets_predictor.predict(train_ds))
# ARIMA.
arima_predictor = RForecastPredictor(
freq=freq,
prediction_length=prediction_length,
method_name="arima",
)
arima_forecast = list(arima_predictor.predict(train_ds))
def train(args):
freq = args.freq.replace('"', '')
prediction_length = args.prediction_length
context_length = args.context_length
use_feat_dynamic_real = args.use_feat_dynamic_real
use_past_feat_dynamic_real = args.use_past_feat_dynamic_real
use_feat_static_cat = args.use_feat_static_cat
use_log1p = args.use_log1p
print('freq:', freq)
print('prediction_length:', prediction_length)
print('context_length:', context_length)
print('use_feat_dynamic_real:', use_feat_dynamic_real)
print('use_past_feat_dynamic_real:', use_past_feat_dynamic_real)
print('use_feat_static_cat:', use_feat_static_cat)
print('use_log1p:', use_log1p)
batch_size = args.batch_size
print('batch_size:', batch_size)
train = load_json(os.path.join(args.train, 'train_'+freq+'.json'))
test = load_json(os.path.join(args.test, 'test_'+freq+'.json'))
num_timeseries = len(train)
print('num_timeseries:', num_timeseries)
train_ds = ListDataset(parse_data(train, use_log1p=use_log1p), freq=freq)
test_ds = ListDataset(parse_data(test, use_log1p=use_log1p), freq=freq)
predictor = None
trainer= Trainer(ctx="cpu",
epochs=args.epochs,
num_batches_per_epoch=args.num_batches_per_epoch,
learning_rate=args.learning_rate,
learning_rate_decay_factor=args.learning_rate_decay_factor,
patience=args.patience,
minimum_learning_rate=args.minimum_learning_rate,
clip_gradient=args.clip_gradient,
weight_decay=args.weight_decay,
init=args.init.replace('"', ''),
hybridize=args.hybridize)
print('trainer:', trainer)
cardinality = None
if args.cardinality != '':
cardinality = args.cardinality.replace('"', '').replace(' ', '').replace('[', '').replace(']', '').split(',')
for i in range(len(cardinality)):
cardinality[i] = int(cardinality[i])
print('cardinality:', cardinality)
embedding_dimension = [min(50, (cat+1)//2) for cat in cardinality] if cardinality is not None else None
print('embedding_dimension:', embedding_dimension)
algo_name = args.algo_name.replace('"', '')
print('algo_name:', algo_name)
if algo_name == 'CanonicalRNN':
estimator = CanonicalRNNEstimator(
freq=freq,
prediction_length=prediction_length,
context_length=context_length,
trainer=trainer,
batch_size=batch_size,
num_layers=5,
num_cells=50,
cell_type='lstm',
num_parallel_samples=100,
cardinality=cardinality,
embedding_dimension=10,
)
elif algo_name == 'DeepFactor':
estimator = DeepFactorEstimator(
freq=freq,
prediction_length=prediction_length,
context_length=context_length,
trainer=trainer,
batch_size=batch_size,
cardinality=cardinality,
embedding_dimension=10,
)
elif algo_name == 'DeepAR':
estimator = DeepAREstimator(
freq = freq, # – Frequency of the data to train on and predict
prediction_length = prediction_length, # – Length of the prediction horizon
trainer = trainer, # – Trainer object to be used (default: Trainer())
context_length = context_length, # – Number of steps to unroll the RNN for before computing predictions (default: None, in which case context_length = prediction_length)
num_layers = 2, # – Number of RNN layers (default: 2)
num_cells = 40, # – Number of RNN cells for each layer (default: 40)
cell_type = 'lstm', # – Type of recurrent cells to use (available: ‘lstm’ or ‘gru’; default: ‘lstm’)
dropoutcell_type = 'ZoneoutCell', # – Type of dropout cells to use (available: ‘ZoneoutCell’, ‘RNNZoneoutCell’, ‘VariationalDropoutCell’ or ‘VariationalZoneoutCell’; default: ‘ZoneoutCell’)
dropout_rate = 0.1, # – Dropout regularization parameter (default: 0.1)
use_feat_dynamic_real = use_feat_dynamic_real, # – Whether to use the feat_dynamic_real field from the data (default: False)
use_feat_static_cat = use_feat_static_cat, # – Whether to use the feat_static_cat field from the data (default: False)
use_feat_static_real = False, # – Whether to use the feat_static_real field from the data (default: False)
cardinality = cardinality, # – Number of values of each categorical feature. This must be set if use_feat_static_cat == True (default: None)
embedding_dimension = embedding_dimension, # – Dimension of the embeddings for categorical features (default: [min(50, (cat+1)//2) for cat in cardinality])
# distr_output = StudentTOutput(), # – Distribution to use to evaluate observations and sample predictions (default: StudentTOutput())
# scaling = True, # – Whether to automatically scale the target values (default: true)
# lags_seq = None, # – Indices of the lagged target values to use as inputs of the RNN (default: None, in which case these are automatically determined based on freq)
# time_features = None, # – Time features to use as inputs of the RNN (default: None, in which case these are automatically determined based on freq)
# num_parallel_samples = 100, # – Number of evaluation samples per time series to increase parallelism during inference. This is a model optimization that does not affect the accuracy (default: 100)
# imputation_method = None, # – One of the methods from ImputationStrategy
# train_sampler = None, # – Controls the sampling of windows during training.
# validation_sampler = None, # – Controls the sampling of windows during validation.
# alpha = None, # – The scaling coefficient of the activation regularization
# beta = None, # – The scaling coefficient of the temporal activation regularization
batch_size = batch_size, # – The size of the batches to be used training and prediction.
# minimum_scale = None, # – The minimum scale that is returned by the MeanScaler
# default_scale = None, # – Default scale that is applied if the context length window is completely unobserved. If not set, the scale in this case will be the mean scale in the batch.
# impute_missing_values = None, # – Whether to impute the missing values during training by using the current model parameters. Recommended if the dataset contains many missing values. However, this is a lot slower than the default mode.
# num_imputation_samples = None, # – How many samples to use to impute values when impute_missing_values=True
)
elif algo_name == 'DeepState':
estimator = DeepStateEstimator(
freq=freq,
prediction_length=prediction_length,
trainer=trainer,
batch_size=batch_size,
use_feat_dynamic_real=use_feat_dynamic_real,
use_feat_static_cat=use_feat_static_cat,
cardinality=cardinality,
)
elif algo_name == 'DeepVAR':
estimator = DeepVAREstimator( # use multi
freq=freq,
prediction_length=prediction_length,
context_length=context_length,
trainer=trainer,
batch_size=batch_size,
target_dim=96,
)
elif algo_name == 'GaussianProcess':
# # TODO
# estimator = GaussianProcessEstimator(
# freq=freq,
# prediction_length=prediction_length,
# context_length=context_length,
# trainer=trainer,
# batch_size=batch_size,
# cardinality=num_timeseries,
# )
pass
elif algo_name == 'GPVAR':
estimator = GPVAREstimator( # use multi
freq=freq,
prediction_length=prediction_length,
context_length=context_length,
trainer=trainer,
batch_size=batch_size,
target_dim=96,
)
elif algo_name == 'LSTNet':
estimator = LSTNetEstimator( # use multi
freq=freq,
prediction_length=prediction_length,
context_length=context_length,
num_series=96,
skip_size=4,
ar_window=4,
channels=72,
trainer=trainer,
batch_size=batch_size,
)
elif algo_name == 'NBEATS':
estimator = NBEATSEstimator(
freq=freq,
prediction_length=prediction_length,
context_length=context_length,
trainer=trainer,
batch_size=batch_size,
)
elif algo_name == 'DeepRenewalProcess':
estimator = DeepRenewalProcessEstimator(
freq=freq,
prediction_length=prediction_length,
context_length=context_length,
trainer=trainer,
batch_size=batch_size,
num_cells=40,
num_layers=2,
)
elif algo_name == 'Tree':
estimator = TreePredictor(
freq = freq,
prediction_length = prediction_length,
context_length = context_length,
n_ignore_last = 0,
lead_time = 0,
max_n_datapts = 1000000,
min_bin_size = 100, # Used only for "QRX" method.
use_feat_static_real = False,
use_feat_dynamic_cat = False,
use_feat_dynamic_real = use_feat_dynamic_real,
cardinality = cardinality,
one_hot_encode = False,
model_params = {'eta': 0.1, 'max_depth': 6, 'silent': 0, 'nthread': -1, 'n_jobs': -1, 'gamma': 1, 'subsample': 0.9, 'min_child_weight': 1, 'colsample_bytree': 0.9, 'lambda': 1, 'booster': 'gbtree'},
max_workers = 4, # default: None
method = "QRX", # "QRX", "QuantileRegression", "QRF"
quantiles=None, # Used only for "QuantileRegression" method.
model=None,
seed=None,
)
elif algo_name == 'SelfAttention':
# # TODO
# estimator = SelfAttentionEstimator(
# freq=freq,
# prediction_length=prediction_length,
# context_length=context_length,
# trainer=trainer,
# batch_size=batch_size,
# )
pass
elif algo_name == 'MQCNN':
estimator = MQCNNEstimator(
freq=freq,
prediction_length=prediction_length,
context_length=context_length,
trainer=trainer,
batch_size=batch_size,
use_past_feat_dynamic_real=use_past_feat_dynamic_real,
use_feat_dynamic_real=use_feat_dynamic_real,
use_feat_static_cat=use_feat_static_cat,
cardinality=cardinality,
embedding_dimension=embedding_dimension,
add_time_feature=True,
add_age_feature=False,
enable_encoder_dynamic_feature=True,
enable_decoder_dynamic_feature=True,
seed=None,
decoder_mlp_dim_seq=None,
channels_seq=None,
dilation_seq=None,
kernel_size_seq=None,
use_residual=True,
quantiles=None,
distr_output=None,
scaling=None,
scaling_decoder_dynamic_feature=False,
num_forking=None,
max_ts_len=None,
)
elif algo_name == 'MQRNN':
estimator = MQRNNEstimator(
freq=freq,
prediction_length=prediction_length,
context_length=context_length,
trainer=trainer,
batch_size=batch_size,
)
elif algo_name == 'Seq2Seq':
# # TODO
# estimator = Seq2SeqEstimator(
# freq=freq,
# prediction_length=prediction_length,
# context_length=context_length,
# trainer=trainer,
# cardinality=cardinality,
# embedding_dimension=4,
# encoder=Seq2SeqEncoder(),
# decoder_mlp_layer=[4],
# decoder_mlp_static_dim=4
# )
pass
elif algo_name == 'SimpleFeedForward':
estimator = SimpleFeedForwardEstimator(
num_hidden_dimensions=[40, 40],
prediction_length=prediction_length,
context_length=context_length,
freq=freq,
trainer=trainer,
batch_size=batch_size,
)
elif algo_name == 'TemporalFusionTransformer':
estimator = TemporalFusionTransformerEstimator(
prediction_length=prediction_length,
context_length=context_length,
freq=freq,
trainer=trainer,
batch_size=batch_size,
hidden_dim = 32,
variable_dim = None,
num_heads = 4,
num_outputs = 3,
num_instance_per_series = 100,
dropout_rate = 0.1,
# time_features = [],
# static_cardinalities = {},
# dynamic_cardinalities = {},
# static_feature_dims = {},
# dynamic_feature_dims = {},
# past_dynamic_features = []
)
elif algo_name == 'DeepTPP':
# # TODO
# estimator = DeepTPPEstimator(
# prediction_interval_length=prediction_length,
# context_interval_length=context_length,
# freq=freq,
# trainer=trainer,
# batch_size=batch_size,
# num_marks=len(cardinality) if cardinality is not None else 0,
# )
pass
elif algo_name == 'Transformer':
estimator = TransformerEstimator(
freq=freq,
prediction_length=prediction_length,
trainer=trainer,
batch_size=batch_size,
cardinality=cardinality,
)
elif algo_name == 'WaveNet':
estimator = WaveNetEstimator(
freq=freq,
prediction_length=prediction_length,
trainer=trainer,
batch_size=batch_size,
cardinality=cardinality,
)
elif algo_name == 'Naive2':
# TODO Multiplicative seasonality is not appropriate for zero and negative values
predictor = Naive2Predictor(freq=freq, prediction_length=prediction_length, season_length=context_length)
elif algo_name == 'NPTS':
predictor = NPTSPredictor(freq=freq, prediction_length=prediction_length, context_length=context_length)
elif algo_name == 'Prophet':
def configure_model(model):
model.add_seasonality(
name='weekly', period=7, fourier_order=3, prior_scale=0.1
)
return model
predictor = ProphetPredictor(freq=freq, prediction_length=prediction_length, init_model=configure_model)
elif algo_name == 'ARIMA':
predictor = RForecastPredictor(freq=freq,
prediction_length=prediction_length,
method_name='arima',
period=context_length,
trunc_length=len(train[0]['target']))
elif algo_name == 'ETS':
predictor = RForecastPredictor(freq=freq,
prediction_length=prediction_length,
method_name='ets',
period=context_length,
trunc_length=len(train[0]['target']))
elif algo_name == 'TBATS':
predictor = RForecastPredictor(freq=freq,
prediction_length=prediction_length,
method_name='tbats',
period=context_length,
trunc_length=len(train[0]['target']))
elif algo_name == 'CROSTON':
predictor = RForecastPredictor(freq=freq,
prediction_length=prediction_length,
method_name='croston',
period=context_length,
trunc_length=len(train[0]['target']))
elif algo_name == 'MLP':
predictor = RForecastPredictor(freq=freq,
prediction_length=prediction_length,
method_name='mlp',
period=context_length,
trunc_length=len(train[0]['target']))
elif algo_name == 'SeasonalNaive':
predictor = SeasonalNaivePredictor(freq=freq, prediction_length=prediction_length)
else:
print('[ERROR]:', algo_name, 'not supported')
return
if predictor is None:
try:
predictor = estimator.train(train_ds, test_ds)
except Exception as e:
print(e)
try:
grouper_train = MultivariateGrouper(max_target_dim=num_timeseries)
train_ds_multi = grouper_train(train_ds)
test_ds_multi = grouper_train(test_ds)
predictor = estimator.train(train_ds_multi, test_ds_multi)
except Exception as e:
print(e)
forecast_it, ts_it = make_evaluation_predictions(
dataset=test_ds, # test dataset
predictor=predictor, # predictor
num_samples=100, # number of sample paths we want for evaluation
)
forecasts = list(forecast_it)
tss = list(ts_it)
# print(len(forecasts), len(tss))
evaluator = Evaluator(quantiles=[0.1, 0.5, 0.9])
agg_metrics, item_metrics = evaluator(iter(tss), iter(forecasts), num_series=len(test_ds))
print(json.dumps(agg_metrics, indent=4))
model_dir = os.path.join(args.model_dir, algo_name)
if not os.path.exists(model_dir):
os.makedirs(model_dir)
predictor.serialize(Path(model_dir))
def test_r_predictor_serialization():
predictor = RForecastPredictor(freq="1D", prediction_length=3)
assert predictor == serde.decode(serde.encode(predictor))
# lectura del dataset
dataset = get_dataset(args.datasource, regenerate=False)
# metadata del dataset
prediction_length = dataset.metadata.prediction_length
freq = dataset.metadata.freq
cardinality = ast.literal_eval(
dataset.metadata.feat_static_cat[0].cardinality)
# sacar conjuntos de entrenamiento
train_ds = dataset.train
test_ds = dataset.test
# predictor ets
ets_predictor = RForecastPredictor(freq=freq,
prediction_length=prediction_length,
method_name='ets')
ets_forecast = list(ets_predictor.predict(train_ds))
# arima predictor
arima_predictor = RForecastPredictor(freq=freq,
prediction_length=prediction_length,
method_name='arima')
arima_forecast = list(arima_predictor.predict(train_ds))
# predictor croston
croston_predictor = CrostonForecastPredictor(
freq=freq, prediction_length=prediction_length,
variant='original',
no_of_params=2)
paths=target_path, start=start, past_length=past
, pred_length=pred, slice=slice
, timestep=timestep, freq=freq
)
if not os.path.exists(forecast_result_saved_path):
sample_forecasts = []
for target_name in target_path:
target = target_path[target_name]
with open(target, 'rb') as fp:
target_ds = pickle.load(fp)
print('导入原始数据成功~~~')
assert target_ds.metadata['dim'] == 1, 'target 序列的维度都应该为1'
target_data = target_ds
prophet_predictor = RForecastPredictor(freq=freq, prediction_length=pred
,method_name='arima' ,trunc_length=past)
generators = prophet_predictor.predict(target_data.train)
forecast_samples = list(generators)
sorted_samples = np.concatenate([np.expand_dims(sample._sorted_samples, 0) for sample in forecast_samples], axis=0)
sorted_samples = np.expand_dims(sorted_samples, axis=0)
sample_forecasts.append(sorted_samples)
sample_forecasts = np.concatenate(sample_forecasts, axis=0)
print('把预测结果保存在-->', forecast_result_saved_path)
with open(forecast_result_saved_path , 'wb') as fp:
pickle.dump(sample_forecasts , fp)