From cfd31f0f0ce5c1f15d342145cc0f31d053d68632 Mon Sep 17 00:00:00 2001 From: Matthijs Berends Date: Thu, 17 Oct 2024 11:55:23 +0200 Subject: [PATCH] (v2.1.1.9099) fix generating GPT training test --- DESCRIPTION | 2 +- NEWS.md | 2 +- data-raw/AMRforRGPT.sh | 26 ++- data-raw/gpt_training_text.txt | 349 ++++++++++++++++----------------- 4 files changed, 189 insertions(+), 190 deletions(-) diff --git a/DESCRIPTION b/DESCRIPTION index ddb77e99..57bc83c9 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,5 +1,5 @@ Package: AMR -Version: 2.1.1.9098 +Version: 2.1.1.9099 Date: 2024-10-17 Title: Antimicrobial Resistance Data Analysis Description: Functions to simplify and standardise antimicrobial resistance (AMR) diff --git a/NEWS.md b/NEWS.md index 71f429c5..5d7b052e 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,4 +1,4 @@ -# AMR 2.1.1.9098 +# AMR 2.1.1.9099 *(this beta version will eventually become v3.0. We're happy to reach a new major milestone soon, which will be all about the new One Health support! Install this beta using [the instructions here](https://msberends.github.io/AMR/#latest-development-version).)* diff --git a/data-raw/AMRforRGPT.sh b/data-raw/AMRforRGPT.sh index 7bf9a565..99bca848 100644 --- a/data-raw/AMRforRGPT.sh +++ b/data-raw/AMRforRGPT.sh @@ -1,7 +1,13 @@ #!/bin/bash +# Check if the current directory is named 'AMR' +if [ "$(basename "$PWD")" != "AMR" ]; then + echo "Error: The script must be run from the 'AMR' directory." + exit 1 +fi + # Define the output file, located in ./data-raw -output_file="gpt_training_text.txt" +output_file="data-raw/gpt_training_text.txt" # Clear the output file if it exists echo "This files contains all context you must know about the AMR package for R."> "$output_file" @@ -12,16 +18,16 @@ remove_header() { sed '/# =\{6,\}/,/# =\{6,\}/d' "$1" } -# Process all .R files in the '../R' folder -for file in ../R/*.R; do +# Process all .R files in the 'R' folder +for file in R/*.R; do echo "THE NEXT PART CONTAINS CONTENTS FROM FILE $file" >> "$output_file" echo -e "\n\n" >> "$output_file" remove_header "$file" >> "$output_file" echo -e "\n\n" >> "$output_file" done -# Process all .Rmd files in the '../vignettes' folder -for file in ../vignettes/*.Rmd; do +# Process all .Rmd files in the 'vignettes' folder +for file in vignettes/*.Rmd; do echo "THE NEXT PART CONTAINS CONTENTS FROM FILE $file" >> "$output_file" echo -e "\n\n" >> "$output_file" remove_header "$file" >> "$output_file" @@ -29,7 +35,7 @@ for file in ../vignettes/*.Rmd; do done # Process important metadata files (DESCRIPTION, NAMESPACE, index.md) -for file in ../DESCRIPTION ../NAMESPACE ../index.md; do +for file in DESCRIPTION NAMESPACE index.md; do if [[ -f $file ]]; then echo "THE NEXT PART CONTAINS CONTENTS FROM FILE $file" >> "$output_file" echo -e "\n\n" >> "$output_file" @@ -38,16 +44,16 @@ for file in ../DESCRIPTION ../NAMESPACE ../index.md; do fi done -# Process test files (if available) in the '../tests' folder -for file in ../tests/*.R; do +# Process test files (if available) in the 'tests' folder +for file in tests/*.R; do echo "THE NEXT PART CONTAINS CONTENTS FROM FILE $file" >> "$output_file" echo -e "\n\n" >> "$output_file" remove_header "$file" >> "$output_file" echo -e "\n\n" >> "$output_file" done -# Process all .Rd files from the '../man' folder -for file in ../man/*.Rd; do +# Process all .Rd files from the 'man' folder +for file in man/*.Rd; do echo "THE NEXT PART CONTAINS CONTENTS FROM FILE $file" >> "$output_file" echo -e "\n\n" >> "$output_file" remove_header "$file" >> "$output_file" diff --git a/data-raw/gpt_training_text.txt b/data-raw/gpt_training_text.txt index dab2aabf..928967b1 100644 --- a/data-raw/gpt_training_text.txt +++ b/data-raw/gpt_training_text.txt @@ -4,7 +4,7 @@ This files contains all context you must know about the AMR package for R. -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/aa_amr-package.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/aa_amr-package.R @@ -40,7 +40,7 @@ THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/aa_amr-package.R -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/aa_globals.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/aa_globals.R @@ -228,7 +228,7 @@ globalVariables(c( -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/aa_helper_functions.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/aa_helper_functions.R @@ -1952,7 +1952,7 @@ if (getRversion() < "4.0.0") { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/aa_helper_pm_functions.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/aa_helper_pm_functions.R @@ -3091,7 +3091,7 @@ pm_row_number <- function(x) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/aa_options.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/aa_options.R @@ -3151,7 +3151,7 @@ NULL -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/ab.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/ab.R @@ -3819,7 +3819,7 @@ get_translate_ab <- function(translate_ab) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/ab_from_text.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/ab_from_text.R @@ -4028,7 +4028,7 @@ ab_from_text <- function(text, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/ab_property.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/ab_property.R @@ -4478,7 +4478,7 @@ ab_validate <- function(x, property, ...) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/ab_selectors.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/ab_selectors.R @@ -5394,7 +5394,7 @@ message_agent_names <- function(function_name, agents, ab_group = NULL, examples -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/age.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/age.R @@ -5605,7 +5605,7 @@ age_groups <- function(x, split_at = c(12, 25, 55, 75), na.rm = FALSE) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/antibiogram.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/antibiogram.R @@ -6292,7 +6292,7 @@ knit_print.antibiogram <- function(x, italicise = TRUE, na = getOption("knitr.ka -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/atc_online.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/atc_online.R @@ -6503,7 +6503,7 @@ atc_online_ddd_units <- function(atc_code, ...) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/av.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/av.R @@ -7099,7 +7099,7 @@ get_translate_av <- function(translate_av) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/av_from_text.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/av_from_text.R @@ -7264,7 +7264,7 @@ av_from_text <- function(text, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/av_property.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/av_property.R @@ -7533,7 +7533,7 @@ av_validate <- function(x, property, ...) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/availability.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/availability.R @@ -7614,7 +7614,7 @@ availability <- function(tbl, width = NULL) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/bug_drug_combinations.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/bug_drug_combinations.R @@ -7956,7 +7956,7 @@ print.bug_drug_combinations <- function(x, ...) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/count.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/count.R @@ -8192,7 +8192,7 @@ count_df <- function(data, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/custom_antimicrobials.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/custom_antimicrobials.R @@ -8343,7 +8343,7 @@ clear_custom_antimicrobials <- function() { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/custom_eucast_rules.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/custom_eucast_rules.R @@ -8631,7 +8631,7 @@ format_custom_query_rule <- function(query, colours = has_colour()) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/custom_microorganisms.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/custom_microorganisms.R @@ -8937,7 +8937,7 @@ abbreviate_mo <- function(x, minlength = 5, prefix = "", hyphen_as_space = FALSE -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/data.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/data.R @@ -9271,7 +9271,7 @@ THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/data.R -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/disk.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/disk.R @@ -9495,7 +9495,7 @@ get_skimmers.disk <- function(column) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/eucast_rules.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/eucast_rules.R @@ -10703,7 +10703,7 @@ eucast_dosage <- function(ab, administration = "iv", version_breakpoints = 12.0) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/export_biosample.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/export_biosample.R @@ -10739,7 +10739,7 @@ export_ncbi_biosample <- function(x, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/first_isolate.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/first_isolate.R @@ -11433,7 +11433,7 @@ duplicated_antibiogram <- function(antibiogram, points_threshold, ignore_I, type -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/g.test.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/g.test.R @@ -11638,7 +11638,7 @@ g.test <- function(x, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/get_episode.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/get_episode.R @@ -11885,7 +11885,7 @@ exec_episode <- function(x, episode_days, case_free_days, ...) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/ggplot_pca.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/ggplot_pca.R @@ -12312,7 +12312,7 @@ pca_calculations <- function(pca_model, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/ggplot_sir.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/ggplot_sir.R @@ -12821,7 +12821,7 @@ labels_sir_count <- function(position = NULL, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/guess_ab_col.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/guess_ab_col.R @@ -13169,7 +13169,7 @@ generate_warning_abs_missing <- function(missing, any = FALSE) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/italicise_taxonomy.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/italicise_taxonomy.R @@ -13293,7 +13293,7 @@ italicize_taxonomy <- function(string, type = c("markdown", "ansi", "html")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/join_microorganisms.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/join_microorganisms.R @@ -13464,7 +13464,7 @@ join_microorganisms <- function(type, x, by, suffix, ...) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/key_antimicrobials.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/key_antimicrobials.R @@ -13812,7 +13812,7 @@ antimicrobials_equal <- function(y, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/kurtosis.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/kurtosis.R @@ -13871,7 +13871,7 @@ kurtosis.data.frame <- function(x, na.rm = FALSE, excess = FALSE) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/like.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/like.R @@ -13997,7 +13997,7 @@ like <- function(x, pattern, ignore.case = TRUE) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/mdro.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/mdro.R @@ -15892,7 +15892,7 @@ eucast_exceptional_phenotypes <- function(x = NULL, only_sir_columns = FALSE, .. -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/mean_amr_distance.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/mean_amr_distance.R @@ -16055,7 +16055,7 @@ amr_distance_from_row <- function(amr_distance, row) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/mic.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/mic.R @@ -16650,7 +16650,7 @@ Summary.mic <- function(..., na.rm = FALSE) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/mo.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/mo.R @@ -17957,7 +17957,7 @@ synonym_mo_to_accepted_mo <- function(x, fill_in_accepted = FALSE, dataset = AMR -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/mo_matching_score.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/mo_matching_score.R @@ -18068,7 +18068,7 @@ mo_matching_score <- function(x, n) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/mo_property.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/mo_property.R @@ -19093,7 +19093,7 @@ find_mo_col <- function(fn) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/mo_source.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/mo_source.R @@ -19402,7 +19402,7 @@ check_validity_mo_source <- function(x, refer_to_name = "`reference_df`", stop_o -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/pca.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/pca.R @@ -19563,7 +19563,7 @@ print_pca_group <- function(a) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/plotting.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/plotting.R @@ -20459,7 +20459,7 @@ plot_colours_subtitle_guideline <- function(x, mo, ab, guideline, colours_SIR, f -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/proportion.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/proportion.R @@ -20893,7 +20893,7 @@ proportion_df <- function(data, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/random.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/random.R @@ -21039,7 +21039,7 @@ random_exec <- function(method_type, size, mo = NULL, ab = NULL) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/resistance_predict.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/resistance_predict.R @@ -21431,7 +21431,7 @@ fortify.resistance_predict <- function(model, data, ...) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/sir.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/sir.R @@ -23160,7 +23160,7 @@ check_reference_data <- function(reference_data, .call_depth) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/sir_calc.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/sir_calc.R @@ -23529,7 +23529,7 @@ sir_calc_df <- function(type, # "proportion", "count" or "both" -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/sir_df.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/sir_df.R @@ -23560,7 +23560,7 @@ sir_df <- function(data, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/skewness.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/skewness.R @@ -23613,7 +23613,7 @@ skewness.data.frame <- function(x, na.rm = FALSE) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/translate.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/translate.R @@ -23865,7 +23865,7 @@ translate_into_language <- function(from, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/vctrs.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/vctrs.R @@ -24046,7 +24046,7 @@ vec_cast.sir.character <- function(x, to, ...) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/whocc.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/whocc.R @@ -24074,7 +24074,7 @@ NULL -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/zz_deprecated.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/zz_deprecated.R @@ -24123,7 +24123,7 @@ deprecation_warning <- function(old = NULL, new = NULL, extra_msg = NULL, is_fun -THE NEXT PART CONTAINS CONTENTS FROM FILE ../R/zzz.R +THE NEXT PART CONTAINS CONTENTS FROM FILE R/zzz.R @@ -24345,7 +24345,7 @@ AMR_env$cli_abort <- import_fn("cli_abort", "cli", error_on_fail = FALSE) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../vignettes/AMR.Rmd +THE NEXT PART CONTAINS CONTENTS FROM FILE vignettes/AMR.Rmd @@ -24704,7 +24704,7 @@ our_data_1st %>% -THE NEXT PART CONTAINS CONTENTS FROM FILE ../vignettes/AMR_for_Python.Rmd +THE NEXT PART CONTAINS CONTENTS FROM FILE vignettes/AMR_for_Python.Rmd @@ -24734,17 +24734,42 @@ knitr::opts_chunk$set( # Introduction -The `AMR` package for R is a powerful tool for antimicrobial resistance (AMR) analysis. It provides extensive features for handling microbial and antimicrobial data. However, for those who work primarily in Python, we now have a more intuitive option available: the `AMR` Python package, which uses `rpy2` internally. This package allows Python users to access all the functions from the R `AMR` package without the need to set up `rpy2` themselves. Since this Python package is not a true 'port' (which would require all R functions to be rewritten into Python), R and the AMR R package are still required to be installed. Yet, Python users can now easily work with AMR data directly through Python code. +The `AMR` package for R is a powerful tool for antimicrobial resistance (AMR) analysis. It provides extensive features for handling microbial and antimicrobial data. However, for those who work primarily in Python, we now have a more intuitive option available: the [`AMR` Python Package Index](https://pypi.org/project/AMR/). -In this document, we explain how this works and provide simple examples of using the `AMR` Python package. +This Python package is a wrapper round the `AMR` R package. It uses the `rpy2` package internally. Despite the need to have R installed, Python users can now easily work with AMR data directly through Python code. -## How It Works +# Install -The `AMR` Python package acts as a wrapper around the functions in the `AMR` R package. The package simplifies the process of calling R functions in Python, eliminating the need to manually manage the `rpy2` setup, which Python uses internally to be able to work with the R package. By just using `import AMR`, Python users can directly use the functions from the `AMR` R package as if they were native Python functions. +1. First make sure you have R installed. There is **no need to install the `AMR` R package**, as it will be installed automatically. -Internally, `rpy2` is still being used, but all complexity is hidden from the user. This approach keeps the Python code clean and Pythonic, while still leveraging the full power of the R `AMR` package. + For Linux: -## Example of Usage + ```bash + # Ubuntu / Debian + sudo apt install r-base + # Fedora: + sudo dnf install R + # CentOS/RHEL + sudo yum install R + ``` + + For macOS (using [Homebrew](https://brew.sh)): + + ```bash + brew install r + ``` + + For Windows, visit the [CRAN download page](https://cran.r-project.org) to download and install R. + +2. Since the Python package is available on the official [Python Package Index](https://pypi.org/project/AMR/), you can just run: + + ```bash + pip install AMR + ``` + +# Examples of Usage + +## Cleaning Taxonomy Here’s an example that demonstrates how to clean microorganism and drug names using the `AMR` Python package: @@ -24780,7 +24805,8 @@ print(df) * **ab_name**: Similarly, this function standardises antimicrobial names. The different representations of ciprofloxacin (e.g., "Cipro", "CIP", "J01MA02", and "Ciproxin") are all converted to the standard name, "Ciprofloxacin". -### Taxonomic Data Sets Now in Python! + +## Taxonomic Data Sets Now in Python! As a Python user, you might like that the most important data sets of the `AMR` R package, `microorganisms`, `antibiotics`, `clinical_breakpoints`, and `example_isolates`, are now available as regular Python data frames: @@ -24821,42 +24847,7 @@ AMR.antibiotics | ZFD | NaN | Zoliflodacin | None | NaN | None | NaN | None | -# Installation - -To be able to use the `AMR` Python package, it is required to install both R and the `AMR` R package. - -### Preparation: Install R and `AMR` R package - -For Linux and macOS, this is just: - -```bash -# Ubuntu / Debian -sudo apt install r-base && Rscript -e 'install.packages("AMR")' -# Fedora: -sudo dnf install R && Rscript -e 'install.packages("AMR")' -# CentOS/RHEL -sudo yum install R && Rscript -e 'install.packages("AMR")' -# Arch Linux -sudo pacman -S r && Rscript -e 'install.packages("AMR")' -# macOS -brew install r && Rscript -e 'install.packages("AMR")' -``` - -For Windows, visit the [CRAN download page](https://cran.r-project.org) in install R, then afterwards install the 'AMR' package manually. - -### Install `AMR` Python Package - -Since the Python package is available on the official [Python Package Index](https://pypi.org/project/AMR/), you can just run: - -```bash -pip install AMR -``` - -# Working with `AMR` in Python - -Now that we have everything set up, let’s walk through some practical examples of using the `AMR` package within Python. - -## Example 1: Calculating AMR +## Calculating AMR ```python import AMR @@ -24871,7 +24862,7 @@ print(result) [0.59555556] ``` -## Example 2: Generating Antibiograms +## Generating Antibiograms One of the core functions of the `AMR` package is generating an antibiogram, a table that summarises the antimicrobial susceptibility of bacterial isolates. Here’s how you can generate an antibiogram from Python: @@ -24910,11 +24901,13 @@ In this example, we generate an antibiogram by selecting various antibiotics. With the `AMR` Python package, Python users can now effortlessly call R functions from the `AMR` R package. This eliminates the need for complex `rpy2` configurations and provides a clean, easy-to-use interface for antimicrobial resistance analysis. The examples provided above demonstrate how this can be applied to typical workflows, such as standardising microorganism and antimicrobial names or calculating resistance. -By using `import AMR`, you can seamlessly integrate the robust features of the R `AMR` package into your Python workflows. Whether you're cleaning data or analysing resistance patterns, the `AMR` Python package makes it easy to work with AMR data in Python. +By just running `import AMR`, users can seamlessly integrate the robust features of the R `AMR` package into Python workflows. + +Whether you're cleaning data or analysing resistance patterns, the `AMR` Python package makes it easy to work with AMR data in Python. -THE NEXT PART CONTAINS CONTENTS FROM FILE ../vignettes/EUCAST.Rmd +THE NEXT PART CONTAINS CONTENTS FROM FILE vignettes/EUCAST.Rmd @@ -25021,7 +25014,7 @@ knitr::kable(eucast_rules(data), align = "lccccccc") -THE NEXT PART CONTAINS CONTENTS FROM FILE ../vignettes/MDR.Rmd +THE NEXT PART CONTAINS CONTENTS FROM FILE vignettes/MDR.Rmd @@ -25191,7 +25184,7 @@ freq(my_TB_data$mdr) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../vignettes/PCA.Rmd +THE NEXT PART CONTAINS CONTENTS FROM FILE vignettes/PCA.Rmd @@ -25291,7 +25284,7 @@ ggplot_pca(pca_result, ellipse = TRUE) + -THE NEXT PART CONTAINS CONTENTS FROM FILE ../vignettes/WHONET.Rmd +THE NEXT PART CONTAINS CONTENTS FROM FILE vignettes/WHONET.Rmd @@ -25397,7 +25390,7 @@ tryCatch( -THE NEXT PART CONTAINS CONTENTS FROM FILE ../vignettes/datasets.Rmd +THE NEXT PART CONTAINS CONTENTS FROM FILE vignettes/datasets.Rmd @@ -25773,7 +25766,7 @@ microorganisms.codes %>% -THE NEXT PART CONTAINS CONTENTS FROM FILE ../vignettes/resistance_predict.Rmd +THE NEXT PART CONTAINS CONTENTS FROM FILE vignettes/resistance_predict.Rmd @@ -25911,7 +25904,7 @@ summary(model)$coefficients -THE NEXT PART CONTAINS CONTENTS FROM FILE ../vignettes/welcome_to_AMR.Rmd +THE NEXT PART CONTAINS CONTENTS FROM FILE vignettes/welcome_to_AMR.Rmd @@ -25984,13 +25977,13 @@ This AMR package for R is free, open-source software and licensed under the [GNU -THE NEXT PART CONTAINS CONTENTS FROM FILE ../DESCRIPTION +THE NEXT PART CONTAINS CONTENTS FROM FILE DESCRIPTION Package: AMR -Version: 2.1.1.9094 -Date: 2024-10-10 +Version: 2.1.1.9098 +Date: 2024-10-17 Title: Antimicrobial Resistance Data Analysis Description: Functions to simplify and standardise antimicrobial resistance (AMR) data analysis and to work with microbial and antimicrobial properties by @@ -26052,7 +26045,7 @@ Roxygen: list(markdown = TRUE) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../NAMESPACE +THE NEXT PART CONTAINS CONTENTS FROM FILE NAMESPACE @@ -26414,7 +26407,7 @@ importFrom(stats,var) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../index.md +THE NEXT PART CONTAINS CONTENTS FROM FILE index.md @@ -26732,7 +26725,7 @@ This R package is free, open-source software and licensed under the [GNU General -THE NEXT PART CONTAINS CONTENTS FROM FILE ../tests/tinytest.R +THE NEXT PART CONTAINS CONTENTS FROM FILE tests/tinytest.R @@ -26793,7 +26786,7 @@ if (tryCatch(isTRUE(AMR:::import_fn("isJob", "rstudioapi")()), error = function( -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/AMR-options.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/AMR-options.Rd @@ -26858,7 +26851,7 @@ Now the team settings are configured in only one place, and can be maintained th -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/AMR.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/AMR.Rd @@ -26955,7 +26948,7 @@ Other contributors: -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/WHOCC.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/WHOCC.Rd @@ -26987,7 +26980,7 @@ ab_tradenames("flucloxacillin") -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/WHONET.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/WHONET.Rd @@ -27044,7 +27037,7 @@ WHONET -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/ab_from_text.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/ab_from_text.Rd @@ -27151,7 +27144,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/ab_property.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/ab_property.Rd @@ -27335,7 +27328,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/add_custom_antimicrobials.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/add_custom_antimicrobials.Rd @@ -27446,7 +27439,7 @@ x[, betalactams()] -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/add_custom_microorganisms.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/add_custom_microorganisms.Rd @@ -27566,7 +27559,7 @@ mo_gramstain(c("C. freundii complex", "C. braakii complex")) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/age.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/age.Rd @@ -27621,7 +27614,7 @@ To split ages into groups, use the \code{\link[=age_groups]{age_groups()}} funct -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/age_groups.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/age_groups.Rd @@ -27704,7 +27697,7 @@ To determine ages, based on one or more reference dates, use the \code{\link[=ag -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/antibiogram.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/antibiogram.Rd @@ -28045,7 +28038,7 @@ plot(ab2) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/antibiotic_class_selectors.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/antibiotic_class_selectors.Rd @@ -28413,7 +28406,7 @@ if (require("data.table")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/antibiotics.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/antibiotics.Rd @@ -28508,7 +28501,7 @@ antivirals -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/as.ab.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/as.ab.Rd @@ -28620,7 +28613,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/as.av.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/as.av.Rd @@ -28717,7 +28710,7 @@ av_name("acicl") -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/as.disk.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/as.disk.Rd @@ -28749,12 +28742,12 @@ is.disk(x) An \link{integer} with additional class \code{\link{disk}} } \description{ -This transforms a vector to a new class \code{\link{disk}}, which is a disk diffusion growth zone size (around an antibiotic disk) in millimetres between 6 and 50. +This transforms a vector to a new class \code{\link{disk}}, which is a disk diffusion growth zone size (around an antibiotic disk) in millimetres between 0 and 50. } \details{ Interpret disk values as SIR values with \code{\link[=as.sir]{as.sir()}}. It supports guidelines from EUCAST and CLSI. -Disk diffusion growth zone sizes must be between 6 and 50 millimetres. Values higher than 50 but lower than 100 will be maximised to 50. All others input values outside the 6-50 range will return \code{NA}. +Disk diffusion growth zone sizes must be between 0 and 50 millimetres. Values higher than 50 but lower than 100 will be maximised to 50. All others input values outside the 0-50 range will return \code{NA}. \code{NA_disk_} is a missing value of the new \code{disk} class. } @@ -28795,7 +28788,7 @@ as.sir(df, uti = TRUE) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/as.mic.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/as.mic.Rd @@ -28937,7 +28930,7 @@ if (require("ggplot2")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/as.mo.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/as.mo.Rd @@ -29210,7 +29203,7 @@ The \code{\link[=mo_property]{mo_*}} functions (such as \code{\link[=mo_genus]{m -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/as.sir.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/as.sir.Rd @@ -29635,7 +29628,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/atc_online.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/atc_online.Rd @@ -29727,7 +29720,7 @@ if (requireNamespace("curl") && requireNamespace("rvest") && requireNamespace("x -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/av_from_text.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/av_from_text.Rd @@ -29797,7 +29790,7 @@ av_from_text("28/03/2020 valaciclovir po tid", type = "admin") -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/av_property.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/av_property.Rd @@ -29921,7 +29914,7 @@ av_name("J05AB01") -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/availability.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/availability.Rd @@ -29961,7 +29954,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/bug_drug_combinations.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/bug_drug_combinations.Rd @@ -30052,7 +30045,7 @@ bug_drug_combinations(example_isolates, -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/clinical_breakpoints.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/clinical_breakpoints.Rd @@ -30131,7 +30124,7 @@ clinical_breakpoints -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/count.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/count.Rd @@ -30339,7 +30332,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/custom_eucast_rules.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/custom_eucast_rules.Rd @@ -30492,7 +30485,7 @@ x2 -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/dosage.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/dosage.Rd @@ -30532,7 +30525,7 @@ dosage -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/eucast_rules.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/eucast_rules.Rd @@ -30695,7 +30688,7 @@ eucast_dosage(c("tobra", "genta", "cipro"), "iv", version_breakpoints = 10) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/example_isolates.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/example_isolates.Rd @@ -30733,7 +30726,7 @@ example_isolates -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/example_isolates_unclean.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/example_isolates_unclean.Rd @@ -30769,7 +30762,7 @@ example_isolates_unclean -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/export_ncbi_biosample.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/export_ncbi_biosample.Rd @@ -30801,7 +30794,7 @@ Export Data Set as NCBI BioSample Antibiogram -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/first_isolate.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/first_isolate.Rd @@ -31005,7 +30998,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/g.test.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/g.test.Rd @@ -31153,7 +31146,7 @@ g.test(x) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/get_episode.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/get_episode.Rd @@ -31353,7 +31346,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/ggplot_pca.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/ggplot_pca.Rd @@ -31508,7 +31501,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/ggplot_sir.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/ggplot_sir.Rd @@ -31748,7 +31741,7 @@ if (require("ggplot2") && require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/guess_ab_col.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/guess_ab_col.Rd @@ -31807,7 +31800,7 @@ guess_ab_col(df, as.ab("augmentin")) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/intrinsic_resistant.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/intrinsic_resistant.Rd @@ -31846,7 +31839,7 @@ intrinsic_resistant -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/italicise_taxonomy.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/italicise_taxonomy.Rd @@ -31885,7 +31878,7 @@ cat(italicise_taxonomy("An overview of S. aureus isolates", type = "ansi")) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/join.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/join.Rd @@ -31966,7 +31959,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/key_antimicrobials.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/key_antimicrobials.Rd @@ -32118,7 +32111,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/kurtosis.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/kurtosis.Rd @@ -32159,7 +32152,7 @@ kurtosis(rnorm(10000), excess = TRUE) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/like.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/like.Rd @@ -32244,7 +32237,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/mdro.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/mdro.Rd @@ -32470,7 +32463,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/mean_amr_distance.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/mean_amr_distance.Rd @@ -32569,7 +32562,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/microorganisms.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/microorganisms.Rd @@ -32680,7 +32673,7 @@ microorganisms -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/microorganisms.codes.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/microorganisms.codes.Rd @@ -32725,7 +32718,7 @@ mo_is_intrinsic_resistant("eco", ab = "vancomycin") -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/microorganisms.groups.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/microorganisms.groups.Rd @@ -32766,7 +32759,7 @@ microorganisms.groups[microorganisms.groups$mo_group == "B_BCTRD_FRGL-C", ] -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/mo_matching_score.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/mo_matching_score.Rd @@ -32849,7 +32842,7 @@ mo_matching_score( -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/mo_property.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/mo_property.Rd @@ -33363,7 +33356,7 @@ Data set \link{microorganisms} -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/mo_source.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/mo_source.Rd @@ -33479,7 +33472,7 @@ If the original file (in the previous case an Excel file) is moved or deleted, t -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/pca.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/pca.Rd @@ -33582,7 +33575,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/plot.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/plot.Rd @@ -33810,7 +33803,7 @@ if (require("ggplot2")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/proportion.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/proportion.Rd @@ -34108,7 +34101,7 @@ if (require("dplyr")) { -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/random.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/random.Rd @@ -34168,7 +34161,7 @@ random_disk(25, "Streptococcus pneumoniae", "ampicillin") # range 12-27 -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/resistance_predict.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/resistance_predict.Rd @@ -34351,7 +34344,7 @@ Models: \code{\link[=lm]{lm()}} \code{\link[=glm]{glm()}} -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/skewness.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/skewness.Rd @@ -34391,7 +34384,7 @@ skewness(runif(1000)) -THE NEXT PART CONTAINS CONTENTS FROM FILE ../man/translate.Rd +THE NEXT PART CONTAINS CONTENTS FROM FILE man/translate.Rd