#neural-forecast
Title
# neural-forecast
j
jan rathfelder
10/26/2023, 12:56 PMHi, i am a bit confused about the hist_exog and futr_exog features. How can i use totally different future features, that my model has not seen during training? I hve never seen such a case. I am looking at this code block: horizon = 24 # day-ahead daily forecast
models = [NHITS(h = horizon,
input_size = 5*horizon,
futr_exog_list = ['gen_forecast', 'week_day'], # <- Future exogenous variables
hist_exog_list = ['system_load'], # <- Historical exogenous variables
stat_exog_list = ['market_0', 'market_1'], # <- Static exogenous variables
scaler_type = 'robust')] from here: https://nixtla.github.io/neuralforecast/examples/exogenous_variables.html
c
Chris Gervais
10/26/2023, 12:59 PMfuture exogenous = features available in the future at time of prediction ie if you have the gen forecast for tomorrow (often available in ISOs) you can make a forecast at the current hour for all of tomorrow, ie “day-ahead” forecast
j
jan rathfelder
10/26/2023, 1:04 PMfirst of all, i guess it is a capability of the neuralfc algorithms, which i need to read up on. but lets take the case where i only have 'normal' external regressors, so i dont make a difference between historic and future. i just have regressors with my time-series, e.g.: sales = f(price, marketing). now i want to train using also price and marketing, but when making forecasts i want to use the same regressors (with varying values probably). how would i feed this into the model? would the historic and future regressors be the same in this case?
also it seems that the Auto-versions of the algorithms cant handle exogenous regressors? does this mean the whole ts-cv-tuning is only working without regressors?
@Chris Gervais, to put it simple: i want to use regressors like in statsforecast, but using DL algorithms
@José Morales, can you tell me if this makes sense? I define total calls to be my exogenous features in the past and also for future forecasts. can i define it like this in my config using ts-vc? # Use your own config or AutoNHITS.default_config
nhits_config = dict(
learning_rate = tune.loguniform(1e-4, 1e-2), # loguniform samples over log-space, which is common for learning rates.
max_steps = tune.randint(500, 2000), # Random integer between 500 and 2000.
input_size = tune.choice([horizon*2, horizon*3]), # if horizon is a variable and you want to just multiply it.
batch_size = tune.randint(1, 20),
windows_batch_size = tune.randint(100, 500),
n_pool_kernel_size = tune.choice([[2, 2, 2], [16, 8, 1]]),
n_freq_downsample = tune.choice([[168, 24, 1], [24, 12, 1], [1, 1, 1]]),
activation = 'ReLU',
n_blocks = [1, 1, 1],
mlp_units = [[512, 512], [512, 512], [512, 512]],
interpolation_mode = "linear",
val_check_steps = 100,
hist_exog_list = ['total_calls'],
futr_exog_list = ['total_calls']
)
horizon=6
model = [AutoNHITS(h=horizon,
config=nhits_config,
loss = MQLoss(),
num_samples=15, # number of configurations explored --> ideally above 25,
search_alg=HyperOptSearch()) # number of configurations explored --> ideally above 20!!
]
j
José Morales
10/26/2023, 4:04 PMYes. If you have those features both when training and at inference you have to provide them through
hist_exog_listfutr_exog_list👍 2
c
Chris Gervais
10/26/2023, 4:06 PMand for the sake of clarity, if you have 'normal' regressors that you expect to be available for the full horizon, they would be classified as future regressors
👍 1
j
jan rathfelder
10/27/2023, 9:21 AMthanks so much for your answers! amazing
l
lobbie lobbie
11/04/2023, 12:13 PMHi @Chris Gervais,
Can you elaborate on @jan rathfelder's question on why the features in futr_exog_list and hist_exog_list can be different? Shouldn't the features in historical df be the same as in the future df? How do the nfc models use features to forecast that they were not trained on?
futr_exog_list = ['gen_forecast', 'week_day'], # <- Future exogenous variableshist_exog_list = ['system_load'], # <- Historical exogenous variablesstat_exog_list = ['market_0', 'market_1'], # <- Static exogenous variablesc
Chris Gervais
11/04/2023, 12:25 PMjust to be clear, nfc models are trained on both future and historical features. there isn’t a “mapping” between future and historical features, they’re entirely separate columns, with the difference being historical features only have data in the past where as future regressors have data in the future. in the example above, system load represents what the actual demand on the grid is at any given time. you can imagine in production this data not being available for future timestamps (ie the forecast horizon), but you can also imagine that data containing some helpful information about timestamps you do care about. NF and other newer libraries allow you to leverage both types of regressors.
If it helps conceptually, I find it helpful to build a dataframe manually with both types of features by taking the historical features and taking lagged versions of them. Ie system load becomes system load at t-1, t-2 etc. so that for any t+1 timestamp youll notice you have all the data available to make the prediction. this is a simplified version (I think, @Nixtla Team please confirm) of what happens under the hood of NFC
j
José Morales
11/16/2023, 3:54 PMYes. If you have those features both when training and at inference you have to provide them throughHey folks, just wanted to correct this statement. If you have a feature available both when training and at inference it should be specified only inandhist_exog_list.futr_exog_list
futr_exog_listinput_sizeinput_size + h