to add the LLM scores to the dataset, I used the file:
ai_survey_3.py, which calls ai_backbone_1.py, and references data in allScriptures.csv adn Gospel Principles.csv
this produced nextLLMScoreDF.csv
the main analysis of this is in simply_showing_bom_is_true.py
which makes the nextLLMScoreDF.csv more readable by converting it to wide format in wideWithScriptures_1.csv
this also adds in bom_chapter_dates_v2.csv to have rough estimates for dates of each verse.
this produced in result the p_vals.csv and the p_vals_noEther.csv
for the cluster analysis, i used clustering.py, which produced book_averages.csv, as well as the figure field_clusters_interactive_2.html