Package: casimir 0.3.3

Maximilian Kähler

casimir: Comparing Automated Subject Indexing Methods in R

Perform evaluation of automatic subject indexing methods. The main focus of the package is to enable efficient computation of set retrieval and ranked retrieval metrics across multiple dimensions of a dataset, e.g. document strata or subsets of the label set. The package also provides the possibility of computing bootstrap confidence intervals for all major metrics, with seamless integration of parallel computation and propensity scored variants of standard metrics.

Authors:Maximilian Kähler [aut, cre], Markus Schumacher [aut], Deutsche Nationalbibliothek [cph]

casimir_0.3.3.tar.gz
casimir_0.3.3.zip(r-4.7-any)casimir_0.3.3.zip(r-4.6-any)casimir_0.3.3.zip(r-4.5-any)
casimir_0.3.3.tgz(r-4.6-any)casimir_0.3.3.tgz(r-4.5-any)
casimir_0.3.3.tar.gz(r-4.7-any)casimir_0.3.3.tar.gz(r-4.6-any)
casimir_0.3.3.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION
card.svg |card.png
casimir/json (API)

# Install 'casimir' in R:

install.packages('casimir', repos = c('https://deutsche-nationalbibliothek.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/deutsche-nationalbibliothek/casimir/issues

Pkgdown/docs site:https://deutsche-nationalbibliothek.github.io

Datasets:

dnb_gold_standard - DNB gold standard data for computing evaluation metrics
dnb_label_distribution - DNB label distribution for computing propensity scored metrics
dnb_test_predictions - DNB test predictions for computing evaluation metrics

On CRAN:

code4lib glam information-retrieval metrics multilabel-classification subject-indexing xmlc

3.82 score 1 stars 22 scripts 279 downloads 13 exports 33 dependencies

Last updated from:49ff488089. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel	OK	185
source / vignettes	OK	165
linux-release	OK	181
macos-release	OK	181
macos-oldrel	OK	232
windows-devel	OK	144
windows-release	OK	134
windows-oldrel	OK	138
wasm-release	OK	129

Exports:apply_threshold compute_intermediate_results compute_intermediate_results_rr compute_pr_auc compute_pr_auc_from_curve compute_pr_curve compute_propensity_scores compute_ranked_retrieval_scores compute_set_retrieval_scores create_comparison create_rank_col join_propensity_scores summarise_intermediate_results

Dependencies:cli codetools collapse cpp11 digest dplyr furrr future generics globals glue lifecycle listenv magrittr options parallelly pillar pkgconfig purrr R6 Rcpp rlang rsample slider stringi stringr tibble tidyr tidyselect utf8 vctrs warp withr

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Filter predictions based on score and rank	apply_threshold
Compute bootstrap replica of pr auc	boot_worker_fn
Coerce id columns to character	check_id_vars
Coerce column to character	check_id_vars_col
Check for inconsistent relevance values	check_repair_relevance_compare
Check for inconsistent relevance values	check_repair_relevance_pred
Compute intermediate set retrieval results per group	compute_intermediate_results compute_intermediate_results_dplyr
Compute intermediate ranked retrieval results per group	compute_intermediate_results_rr
Compute area under precision-recall curve	compute_pr_auc
Compute area under precision-recall curve	compute_pr_auc_from_curve
Compute precision-recall curve	compute_pr_curve
Compute inverse propensity scores	compute_propensity_scores
Compute ranked retrieval scores	compute_ranked_retrieval_scores
Compute multi-label metrics	compute_set_retrieval_scores compute_set_retrieval_scores_dplyr
Join gold standard and predicted results	create_comparison
Create a rank column	create_rank_col create_rank_col_dplyr
Helper function for document-wise computation of ranked retrieval scores	dcg_score
DNB gold standard data for computing evaluation metrics	dnb_gold_standard
DNB label distribution for computing propensity scored metrics	dnb_label_distribution
DNB test predictions for computing evaluation metrics	dnb_test_predictions
Compute the denominator for R-precision	find_ps_rprec_deno find_ps_rprec_deno_dplyr
Compute bootstrap replica of pr auc	generate_pr_auc_replica
Compute bootstrapping results	generate_replicate_results generate_replicate_results_dplyr
Calculate bootstrapping results for one sample	helper_f
Calculate bootstrapping results for one sample	helper_f_dplyr
Join propensity scores	join_propensity_scores join_propensity_scores_dplyr
Helper function for document-wise computation of ranked retrieval scores	lrap_score
Helper function for document-wise computation of ranked retrieval scores	ndcg_score
Declaration of options to be used as identical function arguments	option_params
casimir Options	options
Postprocessing of pr curve data	pr_curve_post_processing
Process cost for false positives	process_cost_fp
Rename metrics	rename_metrics
Set grouping variables	set_grouping_var
Set flags for propensity scores	set_ps_flags
Compute the mean of intermediate results	summarise_intermediate_results
Compute the mean of intermediate results	summarise_intermediate_results_dplyr