# =============================================================================
# HSCI 841 Qualitative Research Methods and Analysis in Public Health  -  Lesson 1:
#   Foundations of Qualitative Data Analysis
# Answer key for the in-lesson R activities
# Data file(s): term projects/HSCI_841/transcripts/P01_Maya.txt  (all 20 transcripts are in
#   HSCI_841_loneliness_data.zip; unzip it inside the course repository)
# Packages: tidyverse, quanteda, tidytext  (install once with the block below)
# Reproduces every code block in the lesson.
#
# Paths are relative to the course repository root. Set your working directory there
# (Session > Set Working Directory > Choose Directory, or open the course .Rproj) before running.
# =============================================================================

# ==== Section 4: The Course R Toolchain / Install the course toolchain ====

# NOTE (answer key): the install block is commented out so the script can be sourced or run with
# Rscript without reinstalling packages. Run it once, by hand, the first time you set the course up.
# install.packages(c(
#   "tidyverse",          # general data wrangling and plotting
#   "tidytext",           # text-as-data verbs in the tidyverse idiom
#   "quanteda",           # industrial-strength text analysis (later modules)
#   "quanteda.textstats", # keyness, readability, lexical diversity
#   "quanteda.textplots", # keyness plots, word clouds, network plots
#   "stringr",            # text manipulation
#   "readtext",           # reading text corpora into R
#   "igraph",             # network analysis (a later module)
#   "topicmodels",        # LDA topic modelling (a later module)
#   "irr"                 # intercoder reliability stats (a later module)
# ))

# Verify the install by loading the core stack
library(tidyverse)
library(quanteda)
library(tidytext)

# Smoke test: read one transcript into R
# NOTE (answer key): the lesson page used "../term projects/...", which only works from inside
# the modules/ folder. Every HSCI 841 path is now relative to the repository root.
loneliness_dir <- "term projects/HSCI_841/transcripts"
p01 <- readLines(file.path(loneliness_dir, "P01_Maya.txt"))
length(p01)  # number of lines
head(p01, 12)  # first 12 lines: metadata header

# What success looks like: the object p01 exists, length(p01) is 65, and the first 12 lines are
# the metadata header (Participant ID through Location).
cat("Lines in P01_Maya.txt:", length(p01), "\n")
cat("Header fields:", paste(sub(":.*$", "", head(p01, 11)), collapse = ", "), "\n")

# The same check across the whole corpus: 20 transcripts, one file per participant.
all_files <- list.files(loneliness_dir, pattern = "\\.txt$", full.names = TRUE)
cat("Transcripts found:", length(all_files), "\n")
cat("Participant turns in P01:", sum(grepl("^P:", p01)),
    " interviewer turns:", sum(grepl("^I:", p01)), "\n")