{"Package":"banter","Type":"Package","Title":"BioAcoustic eveNT classifiER","Description":"Create a hierarchical acoustic event species classifier out of\nmultiple call type detectors as described in\nRankin et al (2017) .","Version":"0.9.6","Authors@R":"c(\nEA = person(\"Eric\", \"Archer\", email = \"eric.archer@noaa.gov\", role = c(\"aut\", \"cre\")),\nTS = person(\"Taiki\", \"Sakai\", email = \"taiki.sakai@noaa.gov\", role = c(\"aut\")))","Depends":"R (>= 4.1.0), magrittr","Imports":"dplyr (>= 1.0.6), ggplot2 (>= 3.3.3), gridExtra (>= 2.3),\nmethods, parallel, randomForest (>= 4.6), rfPermute (>= 2.5.1),\nrlang, stats, swfscMisc (>= 1.5), tibble (>= 3.1.2), tidyr (>=\n1.1.1)","Suggests":"testthat","License":"GNU General Public License","RoxygenNote":"7.2.3","Encoding":"UTF-8","NeedsCompilation":"no","Packaged":"2023-02-12 17:04:57 UTC; ericarcher","Author":"Eric Archer [aut, cre],\nTaiki Sakai [aut]","Maintainer":"Eric Archer ","Repository":"CRAN","Date/Publication":"2023-02-12 21:32:29 UTC","repoType":"cran","tarballUrl":"ftp://cran.r-project.org/pub/R/src/contrib/banter_0.9.6.tar.gz","jsonAuthors":{"EA":{"name":"Eric Archer","email":"eric.archer@noaa.gov","maintainer":true},"TS":{"name":"Taiki Sakai","email":"taiki.sakai@noaa.gov","maintainer":false}},"readme":"[![CRAN version](http://www.r-pkg.org/badges/version/banter?color=red)](https://cran.r-project.org/package=banter)\n[![CRAN last day downloads](http://cranlogs.r-pkg.org/badges/last-day/banter?color=red)](https://cran.r-project.org/package=banter)\n[![CRAN last week downloads](http://cranlogs.r-pkg.org/badges/last-week/banter?color=red)](https://cran.r-project.org/package=banter)\n[![CRAN last month downloads](http://cranlogs.r-pkg.org/badges/banter?color=red)](https://cran.r-project.org/package=banter)\n[![CRAN total downloads](http://cranlogs.r-pkg.org/badges/grand-total/banter?color=red)](https://cran.r-project.org/package=banter) \n[![R-CMD-check](https://github.com/EricArcher/banter/workflows/R-CMD-check/badge.svg)](https://github.com/EricArcher/banter/actions) \n\n# banter\n\n### Description\n\n*banter* is a package for creating hierarchical acoustic event classifiers out of multiple call type detectors.\n\n### Installation\n\nTo install the latest version from GitHub:\n\n```r\n# make sure you have devtools installed\nif(!require('devtools')) install.packages('devtools')\n\n# install package from GitHub\ndevtools::install_github('ericarcher/banter')\n```\n\n### For a complete tutorial, run `banterGuide()`.\n\n### Quick Tutorial\n\nThe BANTER (Bio-Acoustic eveNT classifiER) model is initialized with a data frame of events. There is one row per event and it must have a column called `event.id` which is a unique id for each event, and a column called `species` which assigns each event to a given species. Every other column in the data.frame will be used as a predictor variable for the events. \nIn the package, an example data.frame is in the `train.data` example data list as the `$events` element.\n```r\ndata(train.data)\nbant.mdl <- initBanterModel(train.data$events)\n```\n\nNext, detector data is added to the initialized BANTER model object. Each detector is a data.frame with a column called `event.id` that associates the detected call with an event that the model was initialized with, and a `call.id` column that provides a unique identifier for each call. Every other column will be used as a predictor variable for the calls. \nIn the package, example data.frames for three detectors are provided in the `$detectors` element of the `train.data` example data list. Here is an example of adding the burst pulse (`bp`) detector.\n\n```r\nbant.mdl <- addBanterDetector(\n bant.mdl, \n data = train.data$detectors$bp, \n name = \"bp\",\n ntree = 10, \n sampsize = 1\n)\n```\n\nThe `addBanterDetector` function can be called repeatedly to add additional detectors. Alternatively, if the detectors are all in a named list, they can be added at once:\n\n```r\nbant.mdl <- addBanterDetector(\n bant.mdl, \n data = train.data$detectors, \n ntree = 10, \n sampsize = 1\n)\n```\n\nOnce all of the detectors have been added, then the full BANTER model is run:\n```r\nbant.mdl <- runBanterModel(bant.mdl, ntree = 5000, sampsize = 3)\n```\n\nThe model can be easily summarized:\n```r\nsummary(bant.mdl)\n```\n\nThe actual `randomForest` model can be extracted for the event or detector models:\n```r\n# extract event Random Forest model\nevent.rf <- getBanterModel(bant.mdl, \"event\")\n\n# extract burst pulse (bp) Random Forest model\nbp.rf <- getBanterModel(bant.mdl, \"bp\")\n```\n\nThese can then be visualized using other tools, such as those in the `rfPermute` package:\n```r\nlibrary(rfPermute)\nplotVotes(event.rf)\n```\n\nTo predict novel data, it must be in a list with the event data in the `$events` element, and the detector data in a named list called `$detectors`:\n```r\ndata(test.data)\npredict(bant.mdl, test.data)\n```\n\n### Contact\n\n* submit suggestions and bug-reports: \n* send a pull request: \n* e-mail: \n\n### Reference\nRankin, S., Archer, F., Keating, J. L., Oswald, J. N., Oswald, M., Curtis, A. and Barlow, J. (2017) Acoustic classification of dolphins in the California Current using whistles, echolocation clicks, and burst pulses. Mar Mam Sci, 33: 520-540. [doi:10.1111/mms.12381](https://onlinelibrary.wiley.com/doi/abs/10.1111/mms.12381)\n\n### version 0.9.6 (devel)\n\n* changed behavior of `addBanterDetector()` to provide a warning instead of an error if a detector didn't have enough detections of a species and add all detectors that were valid. \n\n### version 0.9.5 (on CRAN)\n\n* add `subsampleDetections()` to draw a random number of detections per event\n* fixed `predict()` so that species names in `new.data` are modified using `make.names()` like they are in constructing the initial banter model.\n* added run timestamps to all models and changed `summary()` to display a matrix of all.\n* fixed trace and inbag plots in `summary()` and `plotDetectorTrace()`.\n\n### version 0.9.4\n\n* Detector names and detector predictor column names submitted to `addBanterDetector()` are now first checked to make sure they are syntactically valid and unique by comparing them with the results from `make.names()`.\n* Detector names and detector predictor column names in `new.data` submitted to `predict()` are first checked to make sure at least one detector from model is present.\n* Detectors missing in `new.data` for `predict()` will automatically have all species detector probabilities and detector proportions set to 0.\n* Added validation option to `predict()` if `species` column exists in `new.data`\n* Default value for num.cores has been set to 1.\n* Added `banterGuide()`\n\n### version 0.9.3\n\n* Initial CRAN release","jobInfo":{"package":"banter","version":"0.9.6","parsingStatus":"success","parserVersion":2,"parsedAt":"2023-02-12T23:30:51+0000"}}

Description

Usage

Arguments

Format