(v2.1.1.9099) fix generating GPT training test

.github/prehooks/pre-commit

@@ -49,6 +49,7 @@ if command -v Rscript > /dev/null; then
   if [ "$(Rscript -e 'cat(all(c('"'pkgload'"', '"'devtools'"', '"'dplyr'"') %in% rownames(installed.packages())))')" = "TRUE" ]; then
     Rscript -e "source('data-raw/_pre_commit_checks.R')"
     currentpkg=$(Rscript -e "cat(pkgload::pkg_name())")
+    bash data-raw/AMRforRGPT.sh
     echo "- Adding changed files in ./data-raw and ./man to this commit"
     git add data-raw/*
     git add man/*

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: AMR
-Version: 2.1.1.9095
+Version: 2.1.1.9099
-Date: 2024-10-15
+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

NEWS.md

@@ -1,4 +1,4 @@
-# AMR 2.1.1.9095
+# 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).)*
 

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
+# Process all .R files in the 'R' folder
-for file in ../R/*.R; do
+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
+# Process all .Rmd files in the 'vignettes' folder
-for file in ../vignettes/*.Rmd; do
+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
+# Process test files (if available) in the 'tests' folder
-for file in ../tests/*.R; do
+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
+# Process all .Rd files from the 'man' folder
-for file in ../man/*.Rd; do
+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"

data-raw/_generate_python_wrapper.sh

@@ -50,14 +50,31 @@ from rpy2 import robjects
 from rpy2.robjects import pandas2ri
 from rpy2.robjects.packages import importr, isinstalled
 import pandas as pd
+# import importlib.metadata as metadata
 
-# Check if the R package is installed
+# Check if AMR package is installed in R
 if not isinstalled('AMR'):
     utils = importr('utils')
-    utils.install_packages('AMR')
+    utils.install_packages('AMR', repos='https://msberends.r-universe.dev')
+
+# Python package version of AMR
+python_amr_version = metadata.version('AMR')
+# R package version of AMR
+# r_amr_version = robjects.r('packageVersion("AMR")')[0]
+
+# Compare R and Python package versions
+# if r_amr_version != python_amr_version:
+#     print(f"{BLUE}AMR:{RESET} Version mismatch detected. Updating AMR R package version to {python_amr_version}...", flush=True)
+#     try:
+#         # Re-install the specific version of AMR in R
+#         utils = importr('utils')
+#         utils.install_packages('AMR', repos='https://msberends.r-universe.dev')
+#     except Exception as e:
+#         print(f"{BLUE}AMR:{RESET} Could not update: {e}{RESET}", flush=True)
 
 # Activate the automatic conversion between R and pandas DataFrames
 pandas2ri.activate()
+
 # example_isolates
 example_isolates = pandas2ri.rpy2py(robjects.r('''
 df <- AMR::example_isolates
@@ -68,6 +85,7 @@ df[] <- lapply(df, function(x) {
         x
     }
 })
+df <- df[, !sapply(df, is.list)]
 df
 '''))
 example_isolates['date'] = pd.to_datetime(example_isolates['date'])
@@ -75,7 +93,7 @@ example_isolates['date'] = pd.to_datetime(example_isolates['date'])
 # microorganisms
 microorganisms = pandas2ri.rpy2py(robjects.r('AMR::microorganisms[, !sapply(AMR::microorganisms, is.list)]'))
 antibiotics = pandas2ri.rpy2py(robjects.r('AMR::antibiotics[, !sapply(AMR::antibiotics, is.list)]'))
-clinical_breakpoints = pandas2ri.rpy2py(robjects.r('AMR::clinical_breakpoints'))
+clinical_breakpoints = pandas2ri.rpy2py(robjects.r('AMR::clinical_breakpoints[, !sapply(AMR::clinical_breakpoints, is.list)]'))
 
 print(f"{BLUE}AMR:{RESET} {GREEN}Done.{RESET}", flush=True)
 EOL
@@ -220,6 +238,7 @@ echo "Python wrapper functions generated in $functions_file."
 echo "Python wrapper functions listed in $init_file."
 
 cp ../vignettes/AMR_for_Python.Rmd python_wrapper/AMR/README.md
+sed -i '1,/^# Introduction$/d' python_wrapper/AMR/README.md
 echo "README copied"
 
 

vignettes/AMR_for_Python.Rmd

@@ -24,17 +24,42 @@ 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:
 
@@ -70,7 +95,8 @@ 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:
 
@@ -111,42 +137,7 @@ AMR.antibiotics
 | ZFD | NaN         | Zoliflodacin         | None                       | NaN      | None       | NaN    | None     |
 
 
-# Installation
+## Calculating AMR
-
-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
 
 ```python
 import AMR
@@ -161,7 +152,7 @@ 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:
 
@@ -200,4 +191,6 @@ 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.