View source on GitHub
|
Framework for Bayesian structural time series models.
See the blog post for an introductory example.
Classes
class AdditiveStateSpaceModel: A state space model representing a sum of component state space models.
class Autoregressive: Formal representation of an autoregressive model.
class AutoregressiveIntegratedMovingAverage: Represents an autoregressive integrated moving-average (ARIMA) model.
class AutoregressiveMovingAverageStateSpaceModel: State space model for an autoregressive moving average process.
class AutoregressiveStateSpaceModel: State space model for an autoregressive process.
class ConstrainedSeasonalStateSpaceModel: Seasonal state space model with effects constrained to sum to zero.
class DynamicLinearRegression: Formal representation of a dynamic linear regresson model.
class DynamicLinearRegressionStateSpaceModel: State space model for a dynamic linear regression from provided covariates.
class IntegratedStateSpaceModel: Integrates (/cumsums) a noise-free state space model.
class LinearRegression: Formal representation of a linear regression from provided covariates.
class LocalLevel: Formal representation of a local level model.
class LocalLevelStateSpaceModel: State space model for a local level.
class LocalLinearTrend: Formal representation of a local linear trend model.
class LocalLinearTrendStateSpaceModel: State space model for a local linear trend.
class MaskedTimeSeries: Named tuple encoding a time series Tensor and optional missingness mask.
class MissingValuesTolerance: MissingValuesTolerance(overall_fraction, fraction_low_missing_number, fraction_high_missing_number, low_missing_number, high_missing_number)
class Seasonal: Formal representation of a seasonal effect model.
class SeasonalStateSpaceModel: State space model for a seasonal effect.
class SemiLocalLinearTrend: Formal representation of a semi-local linear trend model.
class SemiLocalLinearTrendStateSpaceModel: State space model for a semi-local linear trend.
class SmoothSeasonal: Formal representation of a smooth seasonal effect model.
class SmoothSeasonalStateSpaceModel: State space model for a smooth seasonal effect.
class SparseLinearRegression: Formal representation of a sparse linear regression.
class StructuralTimeSeries: Base class for structural time series models.
class Sum: Sum of structural time series components.
Functions
build_factored_surrogate_posterior(...): Build a variational posterior that factors over model parameters.
build_factored_surrogate_posterior_stateless(...): Returns stateless functions for building a variational posterior.
decompose_by_component(...): Decompose an observed time series into contributions from each component.
decompose_forecast_by_component(...): Decompose a forecast distribution into contributions from each component.
fit_with_hmc(...): Draw posterior samples using Hamiltonian Monte Carlo (HMC).
forecast(...): Construct predictive distribution over future observations.
impute_missing_values(...): Runs posterior inference to impute the missing values in a time series.
moments_of_masked_time_series(...): Compute mean and variance, accounting for a mask.
one_step_predictive(...): Compute one-step-ahead predictive distributions for all timesteps.
regularize_series(...): Infers frequency and makes an irregular time series regular.
sample_uniform_initial_state(...): Initialize from a uniform [-2, 2] distribution in unconstrained space.