Familiarity-dependent computational modelling of indoor landmark selection for route communication: a ranking approach

These codes and data are aimed at computing suitable indoor landmarks for users of different familiarity. The descriptions of files are as follows:rel_ranking_familiarity.py: the source code to train models;hyperparams: this fold includes lgbrank_familiar_best_params.csv and lgbrank_unfamiliar_best_params.csv files, which store the hyperparameters for 17 fold cross_validation in the familiar datase and in the unfamiliar dataset, respectively;17_fold_dataset: this fold includes all the dataset for 1-_fold_cross_validation, in each fold familiar_rank.train.query and familiar_rank.train are for training in the familiar dataset, unfamiliar_rank.train.query and unfamiliar_rank.train are for training in the unfamiliar dataset, familiar_rank.test.query and familiar_rank.test are for testing in the familiar dataset, unfamiliar_rank.test.query and unfamiliar_rank.test are for testing in the unfamiliar dataset.