def train_models(
train,
models,
forecast_len,
full_df=None,
seasonality="infer_from_data",
in_sample=None,
freq=None,
GPU=None,
):
seasons = select_seasonality(train, seasonality)
periods = select_seasonality(train, "periodocity")
models_dict = {}
for m in models:
if in_sample:
print(
"Model {} is being trained for in sample prediction".format(m))
else:
print("Model {} is being trained for out of sample prediction".
format(m))
if m == "ARIMA":
models_dict[m] = pm.auto_arima(train, seasonal=True, m=seasons)
if m == "Prophet":
if freq == "D":
model = Prophet(daily_seasonality=True)
else:
model = Prophet()
models_dict[m] = model.fit(prophet_dataframe(train))
if m == "HWAAS":
try:
models_dict[m] = ExponentialSmoothing(
train,
seasonal_periods=seasons,
trend="add",
seasonal="add",
damped=True,
).fit(use_boxcox=True)
except:
models_dict[m] = ExponentialSmoothing(
train,
seasonal_periods=seasons,
trend="add",
seasonal="add",
damped=True,
).fit(use_boxcox=False)
if m == "HWAMS":
try:
models_dict[m] = ExponentialSmoothing(
train,
seasonal_periods=seasons,
trend="add",
seasonal="mul",
damped=True,
).fit(use_boxcox=True)
except:
try:
models_dict[m] = ExponentialSmoothing(
train,
seasonal_periods=seasons,
trend="add",
seasonal="mul",
damped=True,
).fit(use_boxcox=False)
except:
models_dict[m] = ExponentialSmoothing(
train,
seasonal_periods=seasons,
trend=None,
seasonal="add").fit(use_boxcox=False)
# if m=="HOLT":
# models_dict["HOLT"] = Holt(train,exponential=True).fit()
if m == "PYAF":
model = autof()
model.train(
iInputDS=train.reset_index(),
iTime="Date",
iSignal="Target",
iHorizon=len(train),
) # bad coding to have horison here
models_dict[m] = model.forecast(iInputDS=train.reset_index(),
iHorizon=forecast_len)
if m == "Gluonts":
freqed = pd.infer_freq(train.index)
if freqed == "MS":
freq = "M"
else:
freq = freqed
estimator = DeepAREstimator(
freq=freq,
prediction_length=forecast_len,
trainer=Trainer(epochs=6, ctx="gpu"),
) # use_feat_dynamic_real=True
if GPU:
models_dict[m] = estimator.train(
training_data=gluonts_dataframe(train))
else:
models_dict[m] = estimator.train(
training_data=gluonts_dataframe(train))
if m == "NBEATS":
if GPU:
device = torch.device("cuda")
else:
device = torch.device("cpu")
if os.path.isfile(CHECKPOINT_NAME):
os.remove(CHECKPOINT_NAME)
stepped = 35
batch_size = 10
if in_sample:
x_train, y_train, x_test, y_test, net, norm_constant = nbeats_dataframe(
full_df, forecast_len, in_sample=True, device=device)
optimiser = optim.Adam(net.parameters())
data = data_generator(x_train, y_train, batch_size)
# test_losses = []
for r in range(stepped):
train_100_grad_steps(data, device, net,
optimiser) # test_losses
models_dict[m] = {}
models_dict[m]["model"] = net
models_dict[m]["x_test"] = x_test
models_dict[m]["y_test"] = y_test
models_dict[m]["constant"] = norm_constant
else: # if out_sample train is df
x_train, y_train, net, norm_constant = nbeats_dataframe(
full_df, forecast_len, in_sample=False, device=device)
batch_size = 10 # greater than 4 for viz
optimiser = optim.Adam(net.parameters())
data = data_generator(x_train, y_train, batch_size)
stepped = 5
# test_losses = []
for r in range(stepped):
# _, forecast = net(torch.tensor(x_train, dtype=torch.float)) ### Not Used
# if GPU:
# p = forecast.detach().numpy() ### Not Used
# else:
# p = forecast.detach().numpy() ### Not Used
train_100_grad_steps(data, device, net,
optimiser) # test_losses
models_dict[m] = {}
models_dict[m]["model"] = net
models_dict[m]["tuple"] = (x_train, y_train, net,
norm_constant)
# if m=="TBA":
# bat = TBATS(use_arma_errors=False,use_box_cox=True)
# models_dict[m] = bat.fit(train)
if m == "TATS":
bat = TBATS(
seasonal_periods=list(get_unique_N(season_list(train), 1)),
use_arma_errors=False,
use_trend=True,
)
models_dict[m] = bat.fit(train)
if m == "TBAT":
bat = TBATS(use_arma_errors=False,
use_box_cox=True,
use_trend=True)
models_dict[m] = bat.fit(train)
if m == "TBATS1":
bat = TBATS(
seasonal_periods=[seasons],
use_arma_errors=False,
use_box_cox=True,
use_trend=True,
)
models_dict[m] = bat.fit(train)
if m == "TBATP1":
bat = TBATS(
seasonal_periods=[periods],
use_arma_errors=False,
use_box_cox=True,
use_trend=True,
)
models_dict[m] = bat.fit(train)
if m == "TBATS2":
bat = TBATS(
seasonal_periods=list(get_unique_N(season_list(train), 2)),
use_arma_errors=False,
use_box_cox=True,
use_trend=True,
)
models_dict[m] = bat.fit(train)
# if m=="ProphetGluonts":
# freqed = pd.infer_freq(train.index)
# if freqed=="MS":
# freq= "M"
# else:
# freq= freqed
# models_dict["ProphetGluonts"] = ProphetPredictor(freq=freq, prediction_length=forecast_len) #use_feat_dynamic_real=True
# models_dict["ProphetGluonts"] = list(models_dict["ProphetGluonts"])
return models_dict, seasons
def train_models(train,
models,
forecast_len,
full_df=None,
seasonality="infer_from_data",
in_sample=None):
seasons = select_seasonality(train, seasonality)
models_dict = {}
for m in models:
if m == "ARIMA":
models_dict["ARIMA"] = pm.auto_arima(train,
seasonal=True,
m=seasons)
if m == "Prophet":
model = Prophet()
models_dict["Prophet"] = model.fit(prophet_dataframe(train))
if m == "HWAAS":
models_dict["HWAAS"] = ExponentialSmoothing(
train,
seasonal_periods=seasons,
trend='add',
seasonal='add',
damped=True).fit(use_boxcox=True)
if m == "HWAMS":
models_dict["HWAMS"] = ExponentialSmoothing(
train,
seasonal_periods=seasons,
trend='add',
seasonal='mul',
damped=True).fit(use_boxcox=True)
# if m=="HOLT":
# models_dict["HOLT"] = Holt(train,exponential=True).fit()
if m == "PYAF":
model = autof.cForecastEngine()
model.train(iInputDS=train.reset_index(),
iTime='Date',
iSignal='Target',
iHorizon=len(train)) # bad coding to have horison here
models_dict["PYAF"] = model.forecast(iInputDS=train.reset_index(),
iHorizon=forecast_len)
if m == "Gluonts":
freqed = pd.infer_freq(train.index)
if freqed == "MS":
freq = "M"
else:
freq = freqed
estimator = DeepAREstimator(
freq=freq,
prediction_length=forecast_len,
trainer=Trainer(epochs=2)) #use_feat_dynamic_real=True
print(train)
print(type(train))
print(gluonts_dataframe(train))
models_dict["Gluonts"] = estimator.train(
training_data=gluonts_dataframe(train))
if m == "NBEATS":
device = torch.device('cpu')
seasons = select_seasonality(train, seasonality)
if os.path.isfile(CHECKPOINT_NAME):
os.remove(CHECKPOINT_NAME)
stepped = 5
batch_size = 10
if in_sample:
x_train, y_train, x_test, y_test, net, norm_constant = nbeats_dataframe(
full_df, forecast_len, in_sample=True)
optimiser = optim.Adam(net.parameters())
data = data_generator(x_train, y_train, batch_size)
#test_losses = []
for r in range(stepped):
train_100_grad_steps(data, device, net,
optimiser) #test_losses
models_dict["NBEATS"] = {}
models_dict["NBEATS"]["model"] = net
models_dict["NBEATS"]["x_test"] = x_test
models_dict["NBEATS"]["y_test"] = y_test
models_dict["NBEATS"]["constant"] = norm_constant
else: # if out_sample train is df
x_train, y_train, net, norm_constant = nbeats_dataframe(
full_df, forecast_len, in_sample=False)
batch_size = 10 # greater than 4 for viz
optimiser = optim.Adam(net.parameters())
data = data_generator(x_train, y_train, batch_size)
stepped = 5
#test_losses = []
for r in range(stepped):
_, forecast = net(torch.tensor(
x_train, dtype=torch.float)) ### Not Used
p = forecast.detach().numpy() ### Not Used
train_100_grad_steps(data, device, net,
optimiser) #test_losses
models_dict["NBEATS"] = {}
models_dict["NBEATS"]["model"] = net
models_dict["NBEATS"]["tuple"] = (x_train, y_train, net,
norm_constant)
# if m=="ProphetGluonts":
# freqed = pd.infer_freq(train.index)
# if freqed=="MS":
# freq= "M"
# else:
# freq= freqed
# models_dict["ProphetGluonts"] = ProphetPredictor(freq=freq, prediction_length=forecast_len) #use_feat_dynamic_real=True
# models_dict["ProphetGluonts"] = list(models_dict["ProphetGluonts"])
# create a forecast engine. This is the main object handling all the operations
# We use the test-dataset as the last step of our training to generate the evaluation-metrics and do not use the test-dataset during prediction.
# get the best time series model for predicting one week
return models_dict
