From 25d9e4aaadb5b4b2000b684d2945faa8065964f1 Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Wed, 4 Sep 2024 17:12:54 -0500
Subject: [PATCH] feat: Add question-by-question theme analysis

---
 main.jl | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/main.jl b/main.jl
index fb1146d..46eceec 100755
--- a/main.jl
+++ b/main.jl
@@ -41,7 +41,10 @@ function logged_prompt(prompt)
     return response
 end #function
 
+question_dict = Dict()
+
 for q in questions
+    # Summarize the major themes among all answers
     analysis_prompt = """
     The following is a list of answers to a survey with one response per paragraph:
 
@@ -63,9 +66,61 @@ for q in questions
 
     analysis_response = logged_prompt(analysis_prompt)
 
+
+    # Compile all themes that Llama3 identified.
+    # Llama3 tends to summarize each theme with a bolded statement.
+    # We will extract the bolded statements to compile themes
+    themes = String[]
+    for l in eachline(IOBuffer(analysis_response))
+        m = match(r"^[1-9]+\. \*\*(.+)\*\*:", l)
+        isnothing(m) || push!(themes, first(m))
+    end #for
+    @info "Found themes $themes"
+
+    answer_dict = Dict()
+
+    # Now go back through each answer and check if it is addressing the theme noted
+    for (i, a) in enumerate(skipmissing(survey_data[!, q]))
+        i == 1 && continue #first "answer" is the question
+
+        theme_dict = Dict{String,Union{Bool,Missing}}()
+
+        for t in themes
+            theme_prompt = """
+            The following was answered as a free-response answer on a survey:
+
+            $a
+
+            ---
+
+            Does this answer deal with the theme of $t? Answer yes or no.
+            """
+
+            theme_response = logged_prompt(theme_prompt)
+
+            if startswith(lowercase(theme_response), "yes")
+                theme_dict[t] = true
+            elseif startswith(lowercase(theme_response), "no")
+                theme_dict[t] = false
+            else
+                theme_dict[t] = missing
+            end #if
+        end #for
+
+        answer_dict[a] = theme_dict
+
+    end #for
+
+    question_dict[q] = answer_dict
+
 end #for
 
 
+open("results.json", "w") do io
+    JSON3.write(io, question_dict)
+end
+
+
 # Compile comments from all requested questions
 for q in questions
     open("$q.md", "w") do f