Add new configuration file

2024-08-22 04:20:40 -04:00
parent a300484ceb
commit bcc8dba3e4
8 changed files with 1824 additions and 1016 deletions
--- a/workflow/.old/apps/shell/submodules/parse_study_info
+++ b/workflow/.old/apps/shell/submodules/parse_study_info
@@ -0,0 +1,121 @@
+#!/usr/bin/env/bash
+# @description Creates, modifies, and parses the study info file
+#
+# TODO
+#
+# * Needs refactoring
+# * Ended up combining a few functions into one
+#
+#
+# @exitcode 0 If one or more studies found
+# @exitcode 1 If no studies found
+# @set STUDIES array contains array of "exp# sd ExpDir"
+parse_study_info() {
+  debug "Running: ${FUNCNAME[0]}"
+
+  # Only run this once per project
+  # in case we run multiple modules
+  (( SET_STUDIES )) && return 0
+  declare -g SET_STUDIES=1
+  
+  # Use initials from project or whoami?
+  # Best I can do is first two letters of username
+  # See TODO in markdown
+  initials="${USER:0:2}"
+  INITIALS=${initials^^}
+
+  empty_study=1
+  # Find an Exp directory that does not exist
+  while [[ -d $STUDY_RESULTS_DIR/exp$empty_study ]]; do
+    (( empty_study++ ))
+  done
+
+  next_study_entry="$empty_study,$PROJECT_NAME,NA,NA,$INITIALS"
+
+  echo "${underline}Study Info File${nounderline}"
+
+  if [[ -f $STUDY_INFO_FILE ]]; then
+    # Get latest entry
+    while IFS=',' read -r col1 _; do # split on comma, get Exp # from 1st column
+      studies_nums+=("$col1")
+    done < <(tail -n +2 "$STUDY_INFO_FILE")
+    largest=${studies_nums[0]}
+    for i in "${studies_nums[@]}"; do
+      if ((i > largest)); then
+        largest=$i
+      fi
+    done
+    empty_study=$((largest+1))
+    next_study_entry="$((empty_study)),$PROJECT_NAME,NA,NA,$INITIALS"
+  else # create a default study info file
+    echo "ExpNumb,ExpLabel,BackgroundSD,ZscoreJoinSD,AnalysisBy" > "$STUDY_INFO_FILE"
+    echo "$next_study_entry" >> "$STUDY_INFO_FILE"
+    next_study_entry="$((empty_study+1)),$PROJECT_NAME,NA,NA,$INITIALS"
+  fi
+
+  # Print current studies
+  cat <<-EOF 
+		* Give each experiment labels to be used for the plots and specific files. 
+		* Enter the desired experiment names in the order they should appear in the REMc heatmaps
+
+		Current study info file contents:
+
+		${underline}$STUDY_INFO_FILE${nounderline}
+		$(cat "$STUDY_INFO_FILE")
+	
+	EOF
+
+  # Allow user to add/edit the study info file
+  if ! ((YES)); then
+    for ((i=1; i<2; i++)); do
+      cat <<-EOF
+				Next entry suggestion: "$next_study_entry"
+
+				Would you like to: 
+				* (a)dd the suggested entry
+				* (e)dit the study info file manually
+				* (c)ontinue (default)
+			EOF
+      read -r -p "(c): " response
+      echo ""
+      [[ -z $response ]] && break
+      case $response in
+        a)
+          echo "Adding auto-entry suggestion to $STUDY_INFO_FILE"
+          echo "$next_study_entry" >> "$STUDY_INFO_FILE"
+          next_study_entry="$((empty_study+1)),$PROJECT_NAME,NA,NA,$INITIALS"
+          i=0
+          ;;
+        e)
+          debug "$EDITOR $STUDY_INFO_FILE"
+          "$EDITOR" "$STUDY_INFO_FILE"
+          ;;
+        c)
+          break
+          ;;
+        *)
+          err "Invalid response, please try again"
+          i=0
+          ;;
+      esac
+      break
+    done
+  fi
+
+  # Read study info file
+  declare -ga STUDIES
+  while IFS=',' read -r num _ sd _; do
+    STUDIES+=("$num $sd $STUDY_RESULTS_DIR/exp$num")
+  done < <(tail -n +2 "$STUDY_INFO_FILE") # skip header
+
+  # Initialize missing Exp dirs
+  for study in "${STUDIES[@]}"; do
+    read -r _ _ dir <<< "$study"
+    [[ -d $dir ]] || execute mkdir "$dir"
+  done
+
+  ((DEBUG)) && declare -p STUDIES
+
+  # Return true if at least one study was found
+  [[ ${#STUDIES[@]} -gt 0 ]]
+}