library(tidyverse)

# CSV (most common)
df <- read_csv("data/raw/dataset.csv")

# Excel
df <- readxl::read_excel("data/raw/dataset.xlsx", sheet = "Sheet1")

# Clean column names immediately
df <- df |> janitor::clean_names()

analysis_data <- raw_data |>
  # Clean and filter
  filter(!is.na(key_variable)) |>
  
  # Transform variables
  mutate(
    date = as.Date(date_string, format = "%Y-%m-%d"),
    age_group = cut(age, breaks = c(0, 18, 45, 65, Inf),
                    labels = c("0-17", "18-44", "45-64", "65+"))
  ) |>
  
  # Summarize
  group_by(region, age_group) |>
  summarize(
    n = n(),
    mean_value = mean(outcome, na.rm = TRUE),
    .groups = "drop"
  )

ggplot(df, aes(x = date, y = count, color = category)) +
  geom_line(linewidth = 1) +
  scale_color_brewer(palette = "Set2") +
  labs(
    title = "Trend Over Time",
    subtitle = "By category",
    x = "Date",
    y = "Count",
    color = "Category",
    caption = "Source: Dataset Name"
  ) +
  theme_minimal(base_size = 12) +
  theme(
    legend.position = "bottom",
    plot.title = element_text(face = "bold")
  )

# Good
result <- data |>
  filter(year >= 2020) |>
  group_by(county) |>
  summarize(total = sum(cases))

# Bad
result<-data|>filter(year>=2020)|>group_by(county)|>summarize(total=sum(cases))

# Load and clean surveillance data ------------------------------------------

# Calculate age-adjusted rates
# Using direct standardization method per CDC guidelines
adjusted_rate <- calculate_adjusted_rate(df, standard_pop)

library(tidyverse)  # Loads: ggplot2, dplyr, tidyr, readr, purrr, tibble, stringr, forcats

project/
├── project.Rproj
├── renv.lock
├── CLAUDE.md              # Claude Code configuration
├── README.md
├── data/
│   ├── raw/               # Never modify
│   └── processed/         # Analysis-ready
├── R/                     # Custom functions
├── scripts/               # Pipeline scripts
├── analysis/              # Quarto documents
└── output/
    ├── figures/
    └── tables/

---
title: "Analysis Title"
author: "Your Name"
date: today
format:
  html:
    toc: true
    code-fold: true
    embed-resources: true
execute:
  warning: false
  message: false
---

# Initialize (once per project)
renv::init()

# Snapshot dependencies after installing packages
renv::snapshot()

# Restore environment (for collaborators)
renv::restore()

# ============================================================================
# Title: Analysis of [Subject]
# Author: [Name]
# Date: [Date]
# Purpose: [One-sentence description]
# Input: data/processed/clean_data.csv
# Output: output/figures/trend_plot.png
# ============================================================================

df |>
  group_by(category) |>
  summarize(
    n = n(),
    mean = mean(value, na.rm = TRUE),
    sd = sd(value, na.rm = TRUE),
    median = median(value, na.rm = TRUE),
    q25 = quantile(value, 0.25, na.rm = TRUE),
    q75 = quantile(value, 0.75, na.rm = TRUE)
  ) |>
  gt::gt() |>
  gt::fmt_number(columns = where(is.numeric), decimals = 2)

model <- glm(outcome ~ exposure + age + sex, data = df, family = binomial)

# Tidy coefficients
tidy_results <- broom::tidy(model, conf.int = TRUE, exponentiate = TRUE) |>
  select(term, estimate, conf.low, conf.high, p.value)

# Model diagnostics
glance_results <- broom::glance(model)

library(incidence2)

# Create incidence object
inc <- incidence(
  df,
  date_index = "onset_date",
  interval = "week",
  groups = "outcome_category"
)

# Plot
plot(inc) +
  labs(
    title = "Epidemic Curve",
    x = "Week of Onset",
    y = "Number of Cases"
  ) +
  theme_minimal()

# Age-adjusted rates using direct standardization
library(epitools)

# Stratum-specific counts and populations
result <- ageadjust.direct(
  count = df$cases,
  pop = df$population,
  stdpop = standard_population$pop  # e.g., US 2000 standard
)

# Validate data before analysis
stopifnot(
  "Data frame is empty" = nrow(df) > 0,
  "Missing required columns" = all(c("id", "date", "value") %in% names(df)),
  "Duplicate IDs found" = !any(duplicated(df$id))
)

# Informative warnings for data quality issues
if (sum(is.na(df$key_var)) > 0) {
  warning(sprintf("%d missing values in key_var (%.1f%%)",
                  sum(is.na(df$key_var)),
                  100 * mean(is.na(df$key_var))))
}

# Check file exists before reading
if (!file.exists(filepath)) {
  stop(sprintf("File not found: %s", filepath))
}

# Create directories if needed
dir.create("output/figures", recursive = TRUE, showWarnings = FALSE)

# Use data.table for >1M rows
library(data.table)
dt <- fread("large_file.csv")

# Or use arrow for very large/parquet files
library(arrow)
df <- read_parquet("data.parquet")

# Lazy evaluation with duckdb
library(duckdb)
con <- dbConnect(duckdb())
df_lazy <- tbl(con, "data.csv")

# Good: vectorized
df$rate <- df$cases / df$population * 100000

# Avoid: row-by-row loop
for (i in 1:nrow(df)) {
  df$rate[i] <- df$cases[i] / df$population[i] * 100000
}