Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/Dingdong-Inc/frn-50k-baseline
/ functions
Functions
842 in github.com/Dingdong-Inc/frn-50k-baseline
⨍
Functions
842
◇
Types & classes
203
Method
forward
(self, x)
latent_demand_recovery/pypots/nn/modules/timesnet/layers.py:70
Method
forward
(self, X)
latent_demand_recovery/pypots/nn/modules/timesnet/backbone.py:39
Method
forward
Forward processing of the position-wise feed forward network. Parameters ---------- x: Input tensor. Ret
latent_demand_recovery/pypots/nn/modules/transformer/layers.py:40
Method
forward
Forward processing of the encoder layer. Parameters ---------- enc_input: Input tensor. src_mask:
latent_demand_recovery/pypots/nn/modules/transformer/layers.py:112
Method
forward
Forward processing of the decoder layer. Parameters ---------- dec_input: Input tensor. enc_output:
latent_demand_recovery/pypots/nn/modules/transformer/layers.py:203
Method
forward
Forward processing of the encoder. Parameters ---------- x: Input tensor. src_mask: Masking
latent_demand_recovery/pypots/nn/modules/transformer/auto_encoder.py:78
Method
forward
Forward processing of the decoder. Parameters ---------- trg_seq: Input tensor. enc_output:
latent_demand_recovery/pypots/nn/modules/transformer/auto_encoder.py:183
Method
forward
( self, q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, attn_mask:
latent_demand_recovery/pypots/nn/modules/transformer/attention.py:31
Method
forward
Forward processing of the scaled dot-product attention. Parameters ---------- q: Query tensor. k:
latent_demand_recovery/pypots/nn/modules/transformer/attention.py:63
Method
forward
Forward processing of the multi-head attention module. Parameters ---------- q: Query tensor. k:
latent_demand_recovery/pypots/nn/modules/transformer/attention.py:172
Method
forward
Forward processing of the positional encoding module. Parameters ---------- x: Input tensor. return_only
latent_demand_recovery/pypots/nn/modules/transformer/embedding.py:47
Method
forward
(self, x)
latent_demand_recovery/pypots/nn/modules/transformer/embedding.py:94
Method
forward
(self, x)
latent_demand_recovery/pypots/nn/modules/transformer/embedding.py:117
Method
forward
(self, x)
latent_demand_recovery/pypots/nn/modules/transformer/embedding.py:139
Method
forward
(self, x)
latent_demand_recovery/pypots/nn/modules/transformer/embedding.py:160
Method
forward
(self, x, x_timestamp=None)
latent_demand_recovery/pypots/nn/modules/transformer/embedding.py:188
Method
forward
(self, x, missing_mask, target)
latent_demand_recovery/pypots/nn/modules/mrnn/layers.py:39
Method
forward
(self, inputs: dict)
latent_demand_recovery/pypots/nn/modules/mrnn/backbone.py:59
Method
forward
(self, reconstruction, X_ori, missing_mask, indicating_mask, norm_val)
latent_demand_recovery/pypots/nn/modules/saits/loss.py:27
Method
forward
( self, X, missing_mask, attn_mask: Optional = None )
latent_demand_recovery/pypots/nn/modules/saits/backbone.py:87
Method
forward
(self, X, missing_mask=None)
latent_demand_recovery/pypots/nn/modules/saits/embedding.py:55
Method
forward
(self, x)
latent_demand_recovery/pypots/nn/modules/gpvae/layers.py:100
Method
forward
(self, x)
latent_demand_recovery/pypots/nn/modules/gpvae/layers.py:181
Method
forward
(self, x)
latent_demand_recovery/pypots/nn/modules/gpvae/layers.py:253
Method
forward
(self, X, missing_mask)
latent_demand_recovery/pypots/nn/modules/gpvae/backbone.py:166
Method
from_dataset
Create model from dataset and set parameters related to covariates. Args: dataset: timeseries dataset allowe
demand_forecasting/TFT/models/base_model.py:1424
Method
from_dataset
Create model from dataset. Args: dataset: timeseries dataset **kwargs: additional arguments such as hyperpar
demand_forecasting/TFT/models/base_model.py:1783
Method
from_dataset
Create model from dataset. Args: dataset: timeseries dataset allowed_encoder_known_variable_names: List of k
demand_forecasting/TFT/models/tft/model.py:334
Function
gene_complete_random_walk_for_anomaly_detection
Generate random walk time-series data for the anomaly-detection task. Parameters ---------- n_samples : int, default=1000 The num
latent_demand_recovery/pypots/data/generating.py:138
Function
gene_physionet2012
Generate a fully-prepared PhysioNet-2012 dataset for model testing. Parameters ---------- artificially_missing_rate : float, default=0.1
latent_demand_recovery/pypots/data/generating.py:324
Function
gene_random_walk
Generate a random-walk data. Parameters ---------- n_steps : int, default=24 Number of time steps in each sample. n_features
latent_demand_recovery/pypots/data/generating.py:229
Function
get_cluster_means
Get time series variables' mean values and 95% confidence intervals at each time point per cluster. Parameters __________ dict_to_pl
latent_demand_recovery/pypots/utils/visual/clustering.py:136
Function
get_cluster_members
Subset time series array using predicted cluster membership. Parameters __________ test_data : Time series array that cluste
latent_demand_recovery/pypots/utils/visual/clustering.py:17
Method
get_last_lr
Return last computed learning rate by current scheduler.
latent_demand_recovery/pypots/optim/lr_scheduler/base.py:105
Method
get_lr
(self)
latent_demand_recovery/pypots/optim/lr_scheduler/constant_lrs.py:60
Method
get_lr
(self)
latent_demand_recovery/pypots/optim/lr_scheduler/lambda_lrs.py:69
Method
get_lr
(self)
latent_demand_recovery/pypots/optim/lr_scheduler/multiplicative_lrs.py:64
Method
get_lr
(self)
latent_demand_recovery/pypots/optim/lr_scheduler/linear_lrs.py:77
Method
get_lr
(self)
latent_demand_recovery/pypots/optim/lr_scheduler/exponential_lrs.py:43
Method
get_lr
(self)
latent_demand_recovery/pypots/optim/lr_scheduler/step_lrs.py:55
Method
get_lr
(self)
latent_demand_recovery/pypots/optim/lr_scheduler/multistep_lrs.py:56
Method
get_output_size
(normalizer, loss)
demand_forecasting/TFT/models/base_model.py:371
Function
get_random_seed
Get the random seed used in PyPOTS. Returns ------- random_seed : The random seed used in PyPOTS.
latent_demand_recovery/pypots/utils/random.py:31
Method
impute
Impute missing values in the given data with the trained model. Parameters ---------- X : The data samples for te
latent_demand_recovery/pypots/imputation/base.py:109
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/base.py:431
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/informer/model.py:308
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/median/model.py:115
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/fedformer/model.py:327
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/mean/model.py:114
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/brits/model.py:272
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/etsformer/model.py:313
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/csdi/model.py:444
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/imputeformer/model.py:285
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/autoformer/model.py:313
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/crossformer/model.py:320
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/dlinear/model.py:291
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/patchtst/model.py:341
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/usgan/model.py:442
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/locf/model.py:128
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/timesnet/model.py:303
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/transformer/model.py:311
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/mrnn/model.py:261
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/saits/model.py:386
Method
impute
Impute missing values in the given data with the trained model. Warnings -------- The method impute is deprecated. Please use
latent_demand_recovery/pypots/imputation/itransformer/model.py:306
Method
impute
(self, X, missing_mask, n_sampling_times=1)
latent_demand_recovery/pypots/nn/modules/gpvae/backbone.py:155
Method
init_optimizer
Initialize the torch optimizer wrapped by this class. Parameters ---------- params : An iterable of ``torch.Tenso
latent_demand_recovery/pypots/optim/adadelta.py:52
Method
init_optimizer
Initialize the torch optimizer wrapped by this class. Parameters ---------- params : An iterable of ``torch.Tenso
latent_demand_recovery/pypots/optim/radam.py:56
Method
init_optimizer
Initialize the torch optimizer wrapped by this class. Parameters ---------- params : An iterable of ``torch.Tenso
latent_demand_recovery/pypots/optim/base.py:49
Method
init_optimizer
Initialize the torch optimizer wrapped by this class. Parameters ---------- params : An iterable of ``torch.Tenso
latent_demand_recovery/pypots/optim/adamw.py:57
Method
init_optimizer
Initialize the torch optimizer wrapped by this class. Parameters ---------- params : An iterable of ``torch.Tenso
latent_demand_recovery/pypots/optim/adagrad.py:57
Method
init_optimizer
Initialize the torch optimizer wrapped by this class. Parameters ---------- params : An iterable of ``torch.Tenso
latent_demand_recovery/pypots/optim/rmsprop.py:62
Method
init_optimizer
Initialize the torch optimizer wrapped by this class. Parameters ---------- params : An iterable of ``torch.Tenso
latent_demand_recovery/pypots/optim/adam.py:56
Method
init_scheduler
(self, optimizer)
latent_demand_recovery/pypots/optim/lr_scheduler/lambda_lrs.py:53
Method
init_scheduler
(self, optimizer)
latent_demand_recovery/pypots/optim/lr_scheduler/multiplicative_lrs.py:48
Method
inverse_transform
(self, data)
demand_forecasting/DLinear/data_provider/data_loader.py:115
Method
lagged_target_positions
Positions of lagged target variable(s) in covariates. Returns: Dict[int, torch.LongTensor]: dictionary mapping integer l
demand_forecasting/TFT/models/base_model.py:2073
Method
lagged_target_positions
Positions of lagged target variable(s) in covariates. Returns: Dict[int, torch.LongTensor]: dictionary mapping integer l
demand_forecasting/TFT/models/base_model.py:2118
Method
lagged_targets
Subset of `lagged_variables` but only includes variables that are lagged targets.
demand_forecasting/TFT/data/timeseries.py:525
Method
lagged_variables
Lagged variables. Returns: Dict[str, str]: dictionary of variable names corresponding to lagged variables
demand_forecasting/TFT/data/timeseries.py:510
Function
list_supported_datasets
Return the datasets natively supported by PyPOTS so far. Returns ------- SUPPORTED_DATASETS : A list including all supported data
latent_demand_recovery/pypots/data/load_specific_datasets.py:25
Function
load_data
(path)
demand_forecasting/SSA/ssa_forecasting.py:86
Function
load_dict_from_h5
Load the data from the given h5 file and return as a Python dictionary. Notes ----- This implementation was inspired by https://github.co
latent_demand_recovery/pypots/data/saving/h5.py:90
Method
log_interval
Log interval depending if training or validating
demand_forecasting/TFT/models/base_model.py:687
Method
make_selection_plot
(title, values, labels)
demand_forecasting/TFT/models/tft/model.py:773
Method
mask
(self)
latent_demand_recovery/pypots/nn/modules/informer/layers.py:30
Method
max_lag
Maximum number of time steps variables are lagged. Returns: int: maximum lag
demand_forecasting/TFT/data/timeseries.py:548
Method
message
( self, x_i: Tensor, x_j: Tensor, edge_weights: Tensor, edge_attr: Opt
latent_demand_recovery/pypots/nn/modules/raindrop/layers.py:247
Method
message_selfattention
( self, x_i: Tensor, x_j: Tensor, edge_weights: Tensor, edge_attr: Opt
latent_demand_recovery/pypots/nn/modules/raindrop/layers.py:217
Method
min_lag
Minimum number of time steps variables are lagged. Returns: int: minimum lag
demand_forecasting/TFT/data/timeseries.py:534
Method
multi_target
If dataset encodes one or multiple targets. Returns: bool: true if multiple targets
demand_forecasting/TFT/data/timeseries.py:1097
Method
n_targets
Number of targets to forecast. Based on loss function. Returns: int: number of targets
demand_forecasting/TFT/models/base_model.py:309
Method
on_after_backward
Log gradient flow for debugging.
demand_forecasting/TFT/models/base_model.py:888
Method
on_fit_end
(self)
demand_forecasting/TFT/models/tft/model.py:522
Method
on_load_checkpoint
(self, checkpoint: Dict[str, Any])
demand_forecasting/TFT/models/base_model.py:1031
Method
on_save_checkpoint
(self, checkpoint: Dict[str, Any])
demand_forecasting/TFT/models/base_model.py:1007
Function
parse_delta
Generate the time-gap matrix (i.e. the delta metrix) from the missing mask. Please refer to :cite:`che2018GRUD` for its math definition. Para
latent_demand_recovery/pypots/data/utils.py:136
Function
phi_
(phi_c, x, lb=0, ub=1)
latent_demand_recovery/pypots/nn/modules/fedformer/layers.py:31
Function
pickle_dump
Pickle the given object. Parameters ---------- data: The object to be pickled. path: Saving path. Returns -
latent_demand_recovery/pypots/data/saving/pickle.py:15
Function
pickle_load
Load pickled object from file. Parameters ---------- path : Local path of the pickled object. Returns ------- Object
latent_demand_recovery/pypots/data/saving/pickle.py:45
Function
plot_cluster_means
Generate line plots of cluster means and 95% confidence intervals for each time series variable. Parameters __________ cluster_means
latent_demand_recovery/pypots/utils/visual/clustering.py:218
← previous
next →
701–800 of 842, ranked by callers