(v2.1.1.9244) automated GPT training data

.github/prehooks/pre-commit

@@ -111,8 +111,6 @@ echo ""
 # Save the version number for use in the commit-msg hook
 echo "${currentversion}" > .git/commit_version.tmp
 
-# Generate GPT knowledge info for our Assistant (https://chat.amr-for-r.org)
-bash data-raw/_generate_GPT_knowledge_input.sh "${currentversion}"
 git add data-raw/*
 git add -u
 

.github/workflows/publish-to-pypi.yml

@@ -93,5 +93,4 @@ jobs:
           git rm -rf . || true
           git add .
           git commit -m "Python wrapper update"
-          # git push origin python-wrapper --force
           git push https://$PYPI_PAT@github.com/msberends/AMR.git python-wrapper --force

.github/workflows/renew-gpt-training-data.yml

@@ -0,0 +1,67 @@
+# ==================================================================== #
+# TITLE:                                                               #
+# AMR: An R Package for Working with Antimicrobial Resistance Data     #
+#                                                                      #
+# SOURCE CODE:                                                         #
+# https://github.com/msberends/AMR                                     #
+#                                                                      #
+# PLEASE CITE THIS SOFTWARE AS:                                        #
+# Berends MS, Luz CF, Friedrich AW, et al. (2022).                     #
+# AMR: An R Package for Working with Antimicrobial Resistance Data.    #
+# Journal of Statistical Software, 104(3), 1-31.                       #
+# https://doi.org/10.18637/jss.v104.i03                                #
+#                                                                      #
+# Developed at the University of Groningen and the University Medical  #
+# Center Groningen in The Netherlands, in collaboration with many      #
+# colleagues from around the world, see our website.                   # 
+#                                                                      #
+# This R package is free software; you can freely use and distribute   #
+# it for both personal and commercial purposes under the terms of the  #
+# GNU General Public License version 2.0 (GNU GPL-2), as published by  #
+# the Free Software Foundation.                                        #
+# We created this package for both routine data analysis and academic  #
+# research and it was publicly released in the hope that it will be    #
+# useful, but it comes WITHOUT ANY WARRANTY OR LIABILITY.              #
+#                                                                      #
+# Visit our website for the full manual and a complete tutorial about  #
+# how to conduct AMR data analysis: https://amr-for-r.org              #
+# ==================================================================== #
+
+on:
+  push:
+    # only on main
+    branches: "main"
+
+name: Publish GPT Training Data to GitHub
+
+jobs:
+  update-pypi:
+    runs-on: ubuntu-latest
+    
+    env:
+      PYPI_PAT: ${{ secrets.PYPI_PAT }}
+    
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      
+      - name: Build the training data
+        run: |
+          cd data-raw/
+          bash _generate_GPT_knowledge_input.sh
+
+      - name: Git push to amr-for-r-assistant repo
+        run: |
+          mkdir ~/other
+          # to also mv hidden files:
+          shopt -s dotglob
+          mv ./* ~/other/
+          git clone https://github.com/msberends/amr-for-r-assistant
+          cd amr-for-r-assistant
+          mv ~/other/data-raw/latest_training_data.txt ./
+          
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git add latest_training_data.txt
+          git commit -m "GPT training data update"
+          git push https://$PYPI_PAT@github.com/msberends/amr-for-r-assistant.git main --force

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: AMR
-Version: 2.1.1.9243
-Date: 2025-04-18
+Version: 2.1.1.9244
+Date: 2025-04-19
 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

NEWS.md

@@ -1,4 +1,4 @@
-# AMR 2.1.1.9243
+# AMR 2.1.1.9244
 
 *(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://amr-for-r.org/#get-this-package).)*
 

data-raw/_generate_GPT_knowledge_input.sh

@@ -6,11 +6,11 @@ if [ "$(basename "$PWD")" != "AMR" ]; then
   exit 1
 fi
 
-rm -rf data-raw/gpt_training_text_v*
+rm data-raw/latest_training_data.txt
 
 # Define the output file, located in ./data-raw
 version="$1"
-output_file="data-raw/gpt_training_text_v${version}.txt"
+output_file="data-raw/latest_training_data.txt"
 
 # Clear the output file if it exists
 echo "This knowledge base contains all context you must know about the AMR package for R. You are a GPT trained to be an assistant for the AMR package in R. You are an incredible R specialist, especially trained in this package and in the tidyverse." > "$output_file"

tests/testthat/test-sir.R

@@ -75,7 +75,7 @@ test_that("test-sir.R", {
   )
   expect_error(as.sir.mic(as.mic(16)))
   expect_error(as.sir.disk(as.disk(16)))
-  expect_error(get_guideline("this one does not exist"))
+  expect_error(AMR:::get_guideline("this one does not exist"))
 
   if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0", also_load = TRUE)) {
     # 40 sir columns
@@ -128,7 +128,7 @@ test_that("test-sir.R", {
 
   # allow for guideline length > 1
   expect_equal(
-    get_guideline(c("CLSI", "CLSI", "CLSI2023", "EUCAST", "EUCAST2020"), AMR::clinical_breakpoints),
+    AMR:::get_guideline(c("CLSI", "CLSI", "CLSI2023", "EUCAST", "EUCAST2020"), AMR::clinical_breakpoints),
     c("CLSI 2024", "CLSI 2024", "CLSI 2023", "EUCAST 2024", "EUCAST 2020")
   )