# ferdo R Lab | Lesson 6 | Independent TODO analysis template
# Synthetic data. The original CSV must stay unchanged.
stopifnot(file.exists("data/class_synthetic.csv"))
d <- read.csv("data/class_synthetic.csv",na.strings=c("","NA"),
              stringsAsFactors=FALSE)
d$group <- factor(d$group,levels=c("A","B"))

# TODO 1: Check dimensions, column types and missing scores/hours.
# Explain why 0 differs from NA.

# TODO 2: Count complete study_hours / quiz_score pairs.

# TODO 3: Safely filter quiz_score >= 70, excluding missing score rows.

# TODO 4: Construct a 3-column summary data.frame:
# group, valid_n, mean_score. Explain valid_n vs total group size.

# TODO 5: Labelled boxplot comparing quiz_score across groups.

# TODO 6: Labelled scatterplot (study_hours, quiz_score).
# Use a single common complete.cases mask for both axes.

# OPTIONAL if your UCL module requires correlation:
# TODO 7: cor() and/or lm(), with a noncausal interpretation.

# TODO 8: Explain two results and two limitations in the report template.