tempor.models.clairvoyance2.prediction package¶

Submodules¶

class tempor.models.clairvoyance2.prediction.Seq2SeqClassifier(params: dict[str, Any] | None = None)[source]¶

requirements : Requirements = Requirements(dataset_requirements=DatasetRequirements(requires_static_covariates_present=False, requires_no_missing_data=True, static_covariates_value_type=<DataValueOpts.NUMERIC: 2>, temporal_covariates_value_type=<DataValueOpts.NUMERIC: 2>, temporal_targets_value_type=<DataValueOpts.NUMERIC_CATEGORICAL: 3>, temporal_treatments_value_type=<DataValueOpts.ANY: 1>, event_covariates_value_type=<DataValueOpts.ANY: 1>, event_targets_value_type=<DataValueOpts.ANY: 1>, event_treatments_value_type=<DataValueOpts.ANY: 1>, requires_all_temporal_data_samples_aligned=False, requires_all_temporal_data_regular=False, requires_all_temporal_data_index_numeric=False, requires_all_temporal_containers_shares_index=True), prediction_requirements=PredictionRequirements(target_data_structure=<DataStructureOpts.TIME_SERIES: 1>, horizon_type=<HorizonOpts.TIME_INDEX: 2>, min_timesteps_target_when_fit=3, min_timesteps_target_when_predict=1), treatment_effects_requirements=None)¶

DEFAULT_PARAMS : dict[str, Any] | NamedTuple = _DefaultParams(encoder_rnn_type='LSTM', encoder_hidden_size=100, encoder_num_layers=1, encoder_bias=True, encoder_dropout=0.0, encoder_bidirectional=False, encoder_nonlinearity=None, encoder_proj_size=None, decoder_rnn_type='LSTM', decoder_hidden_size=100, decoder_num_layers=1, decoder_bias=True, decoder_dropout=0.0, decoder_bidirectional=False, decoder_nonlinearity=None, decoder_proj_size=None, adapter_hidden_dims=[50], adapter_out_activation='Tanh', predictor_hidden_dims=[], predictor_out_activation=None, max_len=None, optimizer_str='Adam', optimizer_kwargs={'lr': 0.01, 'weight_decay': 1e-05}, batch_size=32, epochs=100, padding_indicator=-999.0)¶

class tempor.models.clairvoyance2.prediction.Seq2SeqRegressor(params: dict[str, Any] | None = None)[source]¶

requirements : Requirements = Requirements(dataset_requirements=DatasetRequirements(requires_static_covariates_present=False, requires_no_missing_data=True, static_covariates_value_type=<DataValueOpts.NUMERIC: 2>, temporal_covariates_value_type=<DataValueOpts.NUMERIC: 2>, temporal_targets_value_type=<DataValueOpts.NUMERIC: 2>, temporal_treatments_value_type=<DataValueOpts.ANY: 1>, event_covariates_value_type=<DataValueOpts.ANY: 1>, event_targets_value_type=<DataValueOpts.ANY: 1>, event_treatments_value_type=<DataValueOpts.ANY: 1>, requires_all_temporal_data_samples_aligned=False, requires_all_temporal_data_regular=False, requires_all_temporal_data_index_numeric=False, requires_all_temporal_containers_shares_index=True), prediction_requirements=PredictionRequirements(target_data_structure=<DataStructureOpts.TIME_SERIES: 1>, horizon_type=<HorizonOpts.TIME_INDEX: 2>, min_timesteps_target_when_fit=3, min_timesteps_target_when_predict=1), treatment_effects_requirements=None)¶

DEFAULT_PARAMS : dict[str, Any] | NamedTuple = _DefaultParams(encoder_rnn_type='LSTM', encoder_hidden_size=100, encoder_num_layers=1, encoder_bias=True, encoder_dropout=0.0, encoder_bidirectional=False, encoder_nonlinearity=None, encoder_proj_size=None, decoder_rnn_type='LSTM', decoder_hidden_size=100, decoder_num_layers=1, decoder_bias=True, decoder_dropout=0.0, decoder_bidirectional=False, decoder_nonlinearity=None, decoder_proj_size=None, adapter_hidden_dims=[50], adapter_out_activation='Tanh', predictor_hidden_dims=[], predictor_out_activation=None, max_len=None, optimizer_str='Adam', optimizer_kwargs={'lr': 0.01, 'weight_decay': 1e-05}, batch_size=32, epochs=100, padding_indicator=-999.0)¶