Comparing Automated Subject Indexing Methods in R
Helper function for document-wise computation of ranked retrieval scor...
Declaration of options to be used as identical function arguments
casimir Options
Postprocessing of pr curve data
Process cost for false positives
Check for inconsistent relevance values
Filter predictions based on score and rank
Compute bootstrap replica of pr auc
casimir: Comparing Automated Subject Indexing Methods in R
Coerce column to character
Coerce id columns to character
Check for inconsistent relevance values
Compute intermediate ranked retrieval results per group
Compute intermediate set retrieval results per group
Compute area under precision-recall curve
Compute area under precision-recall curve
Compute precision-recall curve
Compute inverse propensity scores
Compute ranked retrieval scores
Compute multi-label metrics
Join gold standard and predicted results
Create a rank column
Helper function for document-wise computation of ranked retrieval scor...
Compute the denominator for R-precision
Helper function for document-wise computation of ranked retrieval scor...
Compute bootstrap replica of pr auc
Compute bootstrapping results
Calculate bootstrapping results for one sample
Calculate bootstrapping results for one sample
Join propensity scores
Rename metrics
Set grouping variables
Set flags for propensity scores
Compute the mean of intermediate results
Compute the mean of intermediate results
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.