(v2.1.1.9107) new pkg knowledge for AMR

DESCRIPTION

@@ -1,5 +1,5 @@
 Package: AMR
-Version: 2.1.1.9106
+Version: 2.1.1.9107
 Date: 2024-11-21
 Title: Antimicrobial Resistance Data Analysis
 Description: Functions to simplify and standardise antimicrobial resistance (AMR)

NEWS.md

@@ -1,4 +1,4 @@
-# AMR 2.1.1.9106
+# AMR 2.1.1.9107
 
 *(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/_generate_GPT_knowledge_input.sh

@@ -6,13 +6,17 @@ if [ "$(basename "$PWD")" != "AMR" ]; then
   exit 1
 fi
 
+rm -rf data-raw/gpt_training_text_v*
+
 # Define the output file, located in ./data-raw
 version="$1"
 output_file="data-raw/gpt_training_text_v${version}.txt"
 
 # Clear the output file if it exists
 echo "This files contains all context you must know about the AMR package for R." > "$output_file"
-echo -e "\n\n\n\n" >> "$output_file"
+echo "First and foremost, you are trained on version ${version}. Remember this whenever someone asks which AMR package version you’re at." >> "$output_file"
+echo "--------------------------------" >> "$output_file"
+echo "" >> "$output_file"
 
 # Function to remove header block (delimited by # ======)
 remove_header() {
@@ -20,43 +24,51 @@ remove_header() {
 }
 
 # Process all .R files in the 'R' folder
-for file in R/*.R; do
-  echo "THE PART HEREAFTER CONTAINS CONTENTS FROM FILE $file" >> "$output_file"
-  echo -e "\n\n" >> "$output_file"
+# for file in R/*.R; do
+#   echo "THE PART HEREAFTER CONTAINS CONTENTS FROM FILE '$file':" >> "$output_file"
+#   echo -e "\n" >> "$output_file"
+#   remove_header "$file" >> "$output_file"
+#   echo -e "\n\n" >> "$output_file"
+# done
+
+# Process important metadata files (DESCRIPTION, NAMESPACE, index.md)
+for file in NAMESPACE index.md; do
+  if [[ -f $file ]]; then
+    echo "THE PART HEREAFTER CONTAINS CONTENTS FROM FILE '$file':" >> "$output_file"
+    echo -e "\n" >> "$output_file"
+    cat "$file" >> "$output_file"
+    echo -e "\n\n" >> "$output_file"
+  fi
+done
+
+# Process all .Rd files from the 'man' folder
+for file in man/*.Rd; do
+  echo "THE PART HEREAFTER CONTAINS CONTENTS FROM FILE '$file':" >> "$output_file"
+  echo -e "\n" >> "$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
-  echo "THE PART HEREAFTER CONTAINS CONTENTS FROM FILE $file" >> "$output_file"
-  echo -e "\n\n" >> "$output_file"
+  echo "THE PART HEREAFTER CONTAINS CONTENTS FROM FILE '$file':" >> "$output_file"
+  echo -e "\n" >> "$output_file"
   remove_header "$file" >> "$output_file"
   echo -e "\n\n" >> "$output_file"
 done
 
-# Process important metadata files (DESCRIPTION, NAMESPACE, index.md)
-for file in DESCRIPTION NAMESPACE index.md; do
-  if [[ -f $file ]]; then
-    echo "THE PART HEREAFTER CONTAINS CONTENTS FROM FILE $file" >> "$output_file"
-    echo -e "\n\n" >> "$output_file"
-    cat "$file" >> "$output_file"
-    echo -e "\n\n" >> "$output_file"
-  fi
+# Process all .Rmd files in the 'vignettes' folder
+echo "THE PART HEREAFTER CONTAINS THE README OF OUR PYTHON PACKAGE" >> "$output_file"
+echo -e "\n" >> "$output_file"
+for file in PythonPackage/AMR/README.md; do
+  remove_header "$file" >> "$output_file"
+  echo -e "\n\n" >> "$output_file"
 done
 
 # Process test files (if available) in the 'tests' folder
-for file in tests/*.R; do
-  echo "THE PART HEREAFTER 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
-  echo "THE PART HEREAFTER 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
+# for file in tests/*.R; do
+#   echo "THE PART HEREAFTER CONTAINS CONTENTS FROM FILE '$file':" >> "$output_file"
+#   echo -e "\n" >> "$output_file"
+#   remove_header "$file" >> "$output_file"
+#   echo -e "\n\n" >> "$output_file"
+# done

data-raw/_generate_python_wrapper.sh

@@ -46,9 +46,6 @@ BLUE = '\033[94m'
 GREEN = '\033[32m'
 RESET = '\033[0m'
 
-print(f"{BLUE}AMR:{RESET} Setting up R environment and AMR datasets...", flush=True)
-
-
 import os
 from rpy2 import robjects
 from rpy2.robjects import pandas2ri
@@ -58,8 +55,6 @@ import importlib.metadata as metadata
 
 # Get the path to the virtual environment
 venv_path = os.getenv('VIRTUAL_ENV')  # Path to the active virtual environment
-if not venv_path:
-    raise EnvironmentError("No virtual environment detected. Please activate your Python virtual environment.")
 
 # Define R library path within the venv
 r_lib_path = os.path.join(venv_path, "R_libs")
@@ -86,11 +81,14 @@ r_amr_version = robjects.r(f'as.character(packageVersion("AMR", lib.loc = "{r_li
 # Compare R and Python package versions
 if python_amr_version and r_amr_version != python_amr_version:
     try:
+        print(f"{BLUE}AMR:{RESET} Updating package version{RESET}", flush=True)
         utils = importr('utils')
         utils.install_packages('AMR', repos='https://msberends.r-universe.dev', quiet=True)
     except Exception as e:
         print(f"{BLUE}AMR:{RESET} Could not update: {e}{RESET}", flush=True)
 
+print(f"{BLUE}AMR:{RESET} Setting up R environment and AMR datasets...", flush=True)
+
 # Activate the automatic conversion between R and pandas DataFrames
 pandas2ri.activate()