Functions — github.com/Wang-Shuo/Neural-Attentive-Session-Based-Recommendation-PyTorch

CodeHub MCPcopy Create free account

hub / github.com/Wang-Shuo/Neural-Attentive-Session-Based-Recommendation-PyTorch / functions

Functions18 in github.com/Wang-Shuo/Neural-Attentive-Session-Based-Recommendation-PyTorch

⨍ Functions 18 ◇ Types & classes 2

↓ 2 callersFunctionlen_argsort

↓ 2 callersFunctionprocess_seqs

(iseqs, idates)

datasets/preprocess.py:194

↓ 2 callersFunctionvalidate

(valid_loader, model)

↓ 1 callersFunctionget_mrr

Calculates the MRR score for the given predictions and targets Args: indices (Bxk): torch.LongTensor. top-k indices predicted by the

↓ 1 callersFunctionget_recall

Calculates the recall score for the given predictions and targets Args: indices (Bxk): torch.LongTensor. top-k indices predicted by

↓ 1 callersMethodinit_hidden

(self, batch_size)

↓ 1 callersFunctionload_data

Loads the dataset :type path: String :param path: The path to the dataset (here RSC2015) :type n_items: int :param n_items: The numbe

↓ 1 callersFunctionmain

↓ 1 callersFunctionobtian_tes

datasets/preprocess.py:172

↓ 1 callersFunctionobtian_tra

datasets/preprocess.py:147

↓ 1 callersFunctiontrainForEpoch

(train_loader, model, optimizer, epoch, num_epochs, criterion, log_aggr=1)

Method__getitem__

(self, n_items, hidden_size, embedding_dim, batch_size, n_layers = 1)

Functioncollate_fn

This function will be used to pad the sessions to max length in the batch and transpose the batch from batch_size x max_seq_len to max_

Functionevaluate

Evaluates the model using Recall@K, MRR@K scores. Args: logits (B,C): torch.LongTensor. The predicted logit for the next items.

(self, seq, lengths)