deep_state() is a way to generate a specification of a DeepState Estimator before fitting and allows the model to be created using different packages. Currently the only package is gluonts.

deep_state(
  mode = "regression",
  id,
  freq,
  prediction_length,
  lookback_length = NULL,
  add_trend = NULL,
  cell_type = NULL,
  num_layers = NULL,
  num_cells = NULL,
  dropout = NULL,
  epochs = NULL,
  batch_size = NULL,
  num_batches_per_epoch = NULL,
  learn_rate = NULL,
  learn_rate_decay_factor = NULL,
  learn_rate_min = NULL,
  patience = NULL,
  clip_gradient = NULL,
  penalty = NULL,
  scale = NULL
)

Arguments

mode

A single character string for the type of model. The only possible value for this model is "regression".

id

A quoted column name that tracks the GluonTS FieldName "item_id"

freq

A pandas timeseries frequency such as "5min" for 5-minutes or "D" for daily. Refer to Pandas Offset Aliases.

prediction_length

Numeric value indicating the length of the prediction horizon

lookback_length

Number of steps to unroll the RNN for before computing predictions (default: NULL, in which case past_length = prediction_length)

add_trend

Flag to indicate whether to include trend component in the state-space model. Default: FALSE.

cell_type

Type of recurrent cells to use (available: 'lstm' or 'gru'; default: 'lstm')

num_layers

Number of RNN layers (default: 2)

num_cells

Number of RNN cells for each layer (default: 40)

dropout

Dropout regularization parameter (default: 0.1)

epochs

Number of epochs that the network will train (default: 5).

batch_size

Number of examples in each batch (default: 32).

num_batches_per_epoch

Number of batches at each epoch (default: 50).

learn_rate

Initial learning rate (default: 10-3).

learn_rate_decay_factor

Factor (between 0 and 1) by which to decrease the learning rate (default: 0.5).

learn_rate_min

Lower bound for the learning rate (default: 5x10-5 ).

patience

The patience to observe before reducing the learning rate, nonnegative integer (default: 10).

clip_gradient

Maximum value of gradient. The gradient is clipped if it is too large (default: 10).

penalty

The weight decay (or L2 regularization) coefficient. Modifies objective by adding a penalty for having large weights (default 10-8 ).

scale

Scales numeric data by id group using mean = 0, standard deviation = 1 transformation. (default: FALSE)

Details

These arguments are converted to their specific names at the time that the model is fit. Other options and arguments can be set using set_engine(). If left to their defaults here (see above), the values are taken from the underlying model functions. If parameters need to be modified, update() can be used in lieu of recreating the object from scratch.

The model can be created using the fit() function using the following engines:

  • GluonTS DeepStateEstimator: "gluonts_deepstate" (the default)

Engine Details

The standardized parameter names in modeltime can be mapped to their original names in each engine:

modeltimeDeepStateEstimator
idNA
freqfreq
prediction_lengthprediction_length
lookback_lengthpast_length (= prediction_length)
epochsepochs (5)
batch_sizebatch_size (32)
num_batches_per_epochnum_batches_per_epoch (50)
learn_ratelearning_rate (0.001)
learn_rate_decay_factorlearning_rate_decay_factor (0.5)
learn_rate_minminimum_learning_rate (5e-5)
patiencepatience (10)
clip_gradientclip_gradient (10)
penaltyweight_decay (1e-8)
scalescale_by_id (FALSE)

Other options can be set using set_engine().

Engine

gluonts_deepstate

The engine uses gluonts.model.deep_state.DeepStateEstimator(). Default values that have been changed to prevent long-running computations:

  • epochs = 5: GluonTS uses 100 by default.

  • cardinality = 1: GluonTS requires user to provide. You can change this via set_engine()

Required Parameters

The gluonts implementation has several Required Parameters, which are user-defined.

1. ID Variable (Required):

An important difference between other parsnip models is that each time series (even single time series) must be uniquely identified by an ID variable.

  • The ID feature must be of class character or factor.

  • This ID feature is provided as a quoted expression during the model specification process (e.g. deep_state(id = "ID") assuming you have a column in your data named "ID").

2. Frequency (Required):

The GluonTS models use a Pandas Timestamp Frequency freq to generate features internally. Examples:

  • freq = "5min" for timestamps that are 5-minutes apart

  • freq = "D" for Daily Timestamps

The Pandas Timestamps are quite flexible. Refer to Pandas Offset Aliases.

3. Prediction Length (Required):

Unlike other parsnip models, a prediction_length is required during the model specification and fitting process.

Fit Details

The following features are REQUIRED to be available in the incoming data for the fitting process.

  • Fit: fit(y ~ date + id, data): Includes a target feature that is a function of a "date" and "id" feature. The ID feature must be pre-specified in the model_specification.

  • Predict: predict(model, new_data) where new_data contains both a column named "date" and "id".

ID Variable

An ID feature must be included in the recipe or formula fitting process. This assists with cataloging the time series inside GluonTS ListDataset. The column name must match the quoted feature name specified in the deep_state(id = "id") expects a column inside your data named "id".

Date and Date-Time Variable

It's a requirement to have a date or date-time variable as a predictor. The fit() interface accepts date and date-time features and handles them internally.

References

  1. Rangapuram, Syama Sundar, et al. "Deep state space models for time series forecasting." Advances in Neural Information Processing Systems. 2018.

See also

fit.model_spec(), set_engine()

Examples

# \donttest{ library(tidymodels) library(tidyverse) library(timetk) # ---- MODEL SPEC ---- # - Important: Make sure *required* parameters are provided model_spec <- deep_state( # User Defined (Required) Parameters id = "id", freq = "M", prediction_length = 24, # Hyper Parameters epochs = 1, num_batches_per_epoch = 4 ) %>% set_engine("gluonts_deepstate") model_spec
#> Deep State Model Specification (regression) #> #> Main Arguments: #> id = id #> freq = M #> prediction_length = 24 #> epochs = 1 #> num_batches_per_epoch = 4 #> #> Computational engine: gluonts_deepstate #>
# ---- TRAINING ---- # Important: Make sure the date and id features are included as regressors # and do NOT dummy the id feature. model_fitted <- model_spec %>% fit(value ~ date + id, m750) model_fitted
#> parsnip model object #> #> Fit time: 1.4s #> DeepState #> -------- #> Model: <gluonts.mx.model.predictor.RepresentableBlockPredictor> #> #> gluonts.model.deepstate._network.DeepStatePredictionNetwork(cardinality=[1], cell_type="lstm", dropout_rate=0.1, embedding_dimension=[1], innovation_bounds=gluonts.mx.distribution.lds.ParameterBounds(lower=1e-06, upper=0.01), issm=gluonts.model.deepstate.issm.CompositeISSM(add_trend=False, seasonal_issms=[gluonts.model.deepstate.issm.SeasonalityISSM(num_seasons=12, time_feature=gluonts.time_feature._base.MonthOfYearIndex())]), noise_std_bounds=gluonts.mx.distribution.lds.ParameterBounds(lower=1e-06, upper=1.0), num_cells=40, num_layers=2, num_parallel_samples=100, past_length=48, prediction_length=24, prior_cov_bounds=gluonts.mx.distribution.lds.ParameterBounds(lower=1e-06, upper=1.0), scaling=True)
# ---- PREDICT ---- # - IMPORTANT: New Data must have id and date features new_data <- tibble( id = factor("M750"), date = as.Date("2015-07-01") ) predict(model_fitted, new_data)
#> # A tibble: 1 x 1 #> .pred #> <dbl> #> 1 8867.
# }