R code base analysis

coding_trends.R

# this code analyzes all of the R scripts in a specified folder and then creates charts summarizing your coding trends over time #
# Load necessary libraries
library(tidyverse)
library(fs)
library(ggplot2)
library(lubridate)
library(dplyr)
library(scales)

# Specify your folder path - replace with your actual path
folder_path <- "~/"  # Update this!
cutoff_date<-"2012-01-01" # update this for the cutoff date to start anayzing your R code

# Function to analyze R files
analyze_r_files <- function(folder_path) {
  # Find all .R files in the folder and subfolders
  r_files <- fs::dir_ls(path = folder_path, 
                        recurse = TRUE, 
                        glob = "*.R")
  
  # Initialize a dataframe to store results
  results <- data.frame(
    file_name = character(),
    file_path = character(),
    last_modified = as.POSIXct(character()),
    size_bytes = numeric(),
    num_lines = numeric(),
    num_chars = numeric(),
    num_dollar_signs = numeric(),
    num_functions = numeric(),
    num_comments = numeric(),
    num_pipes = numeric(),        # Added for %>% count
    num_libraries = numeric(),    # Added for library() count
    stringsAsFactors = FALSE
  )
  
  # Process each file
  for (file in r_files) {
    tryCatch({
      # Get file info
      file_info <- fs::file_info(file)
      file_name <- basename(file)
      
      # Read file content
      content <- readLines(file, warn = FALSE)
      
      # Calculate metrics
      num_lines <- length(content)
      content_text <- paste(content, collapse = "\n")
      num_chars <- nchar(content_text)
      num_dollar_signs <- stringr::str_count(content_text, "\\$")
      num_functions <- stringr::str_count(content_text, "function\\s*\\(")
      num_comments <- sum(stringr::str_detect(content, "^\\s*#"))
      num_pipes <- stringr::str_count(content_text, "%>%")         # Count pipes
      num_libraries <- stringr::str_count(content_text, "library\\(") # Count library calls
      
      # Add to results
      results <- rbind(results, data.frame(
        file_name = file_name,
        file_path = as.character(file),
        last_modified = file_info$modification_time,
        size_bytes = file_info$size,
        num_lines = num_lines,
        num_chars = num_chars,
        num_dollar_signs = num_dollar_signs,
        num_functions = num_functions,
        num_comments = num_comments,
        num_pipes = num_pipes,                 # Added pipe count
        num_libraries = num_libraries,         # Added library count
        stringsAsFactors = FALSE
      ))
    }, error = function(e) {
      warning("Error processing file: ", file, "\n", e$message)
    })
  }
  
  return(results)
}

# Run the analysis
results <- analyze_r_files(folder_path)

# summarize by date ----
date_summ <- results %>%
  mutate(date_floor=floor_date(last_modified,unit="months")) %>%
  group_by(date_floor) %>%
  summarise(scripts=n(),lines=sum(num_lines),
            characters=sum(num_chars),dollars=sum(num_dollar_signs),
            pipes=sum(num_pipes),libraries=sum(num_libraries),
            lines=sum(num_lines),comments=sum(num_comments)) %>%
  mutate(dollar_pct=dollars/characters,
         pipe_pct=pipes/characters,
         packages_per_script=libraries/scripts,
         lines_per_script=lines/scripts,
         comments_per_line=comments/lines) %>%
  mutate(date_floor = as_date(date_floor))

# Ensure date is a proper Date object
date_summ <- date_summ %>%
  mutate(date_floor = as_date(date_floor))

# Create improved plot
ggplot(
  subset(date_summ, date_floor >= as_date(cutoff_date)),
  aes(x = date_floor, y = pipe_pct)
) +
  geom_point(size = 2, alpha = 0.6, color = "#478873") +
  geom_smooth(color = "#2F4F4F", size = 1.2, se=F)  + # A darker gray-green for contrast
  labs(
    title = "R Pipe Operator Usage Over Time",
    subtitle = "Frequency of `%>%` by last modified date (2012–2025)",
    x = "Last modified date",
    y = "Frequency of Pipe Operator",
    caption = "Source: My R code repository"
  ) +
  scale_x_date(
    date_breaks = "1 year",
    date_labels = "%Y",
    limits = c(as_date("2012-01-01"), NA),
    expand = c(0.01, 0.01)
  ) +
  scale_y_continuous(
    labels = label_percent(accuracy = 0.1)
  ) +
  theme_minimal(base_size = 16) +
  theme(
    plot.background = element_rect(fill = "#F7FBF9", color = NA),
    panel.background = element_rect(fill = "#F7FBF9", color = NA),
    panel.grid.major = element_line(color = "grey90"),
    panel.grid.minor = element_blank(),
    axis.text.x = element_text(angle = 45, hjust = 1),
    plot.title = element_text(face = "bold", size = 20),
    plot.subtitle = element_text(size = 14, margin = margin(b = 10)),
    plot.caption = element_text(size = 10, face = "italic", hjust = 1),
    axis.title.x = element_text(margin = margin(t = 10)),
    axis.title.y = element_text(margin = margin(r = 10))
  )
ggsave(
  filename = paste0(folder_path,"pipe_operator_usage.png"),
  width = 10,
  height = 6,
  dpi = 300,
  bg = "#F7FBF9"
)

# Create improved plot
ggplot(
  subset(date_summ, date_floor >= as_date(cutoff_date)),
  aes(x = date_floor, y = dollar_pct)
) +
  geom_point(size = 2, alpha = 0.6, color = "#478873") +
  geom_smooth(color = "#2F4F4F", size = 1.2, se=F)  + # A darker gray-green for contrast
  labs(
    title = "Dollar Sign Usage in R Code Over Time",
    subtitle = "Frequency of '$' usage by last modified date (2012–2025)",
    x = "Last modified date",
    y = "Frequency of '$' Usage",
    caption = "Source: Mike Beuoy's R code repository"
  ) +
  scale_x_date(
    date_breaks = "1 year",
    date_labels = "%Y",
    limits = c(as_date("2012-01-01"), NA),
    expand = c(0.01, 0.01)
  ) +
  scale_y_continuous(
    labels = label_percent(accuracy = 0.1)
  ) +
  theme_minimal(base_size = 16) +
  theme(
    plot.background = element_rect(fill = "#F7FBF9", color = NA),
    panel.background = element_rect(fill = "#F7FBF9", color = NA),
    panel.grid.major = element_line(color = "grey90"),
    panel.grid.minor = element_blank(),
    axis.text.x = element_text(angle = 45, hjust = 1),
    plot.title = element_text(face = "bold", size = 20),
    plot.subtitle = element_text(size = 14, margin = margin(b = 10)),
    plot.caption = element_text(size = 10, face = "italic", hjust = 1),
    axis.title.x = element_text(margin = margin(t = 10)),
    axis.title.y = element_text(margin = margin(r = 10))
  )
ggsave(
  filename = paste0(folder_path,"dollar_sign.png"),
  width = 10,
  height = 6,
  dpi = 300,
  bg = "#F7FBF9"
)

# packages per script ----
ggplot(
  subset(date_summ, date_floor >= as_date(cutoff_date)),
  aes(x = date_floor, y = packages_per_script)
) +
  geom_point(size = 2, alpha = 0.6, color = "#478873") +
  geom_smooth(color = "#2F4F4F", size = 1.2, se=F)  + # A darker gray-green for contrast
  labs(
    title = "Number of Packages Loaded Per R Script Over Time",
    subtitle = "Frequency of 'library' statement by last modified date (2012–2025)",
    x = "Last modified date",
    y = "Avg # of packages loaded",
    caption = "Source: My R code repository"
  ) +
  scale_x_date(
    date_breaks = "1 year",
    date_labels = "%Y",
    limits = c(as_date("2012-01-01"), NA),
    expand = c(0.01, 0.01)
  ) +
  theme_minimal(base_size = 16) +
  theme(
    plot.background = element_rect(fill = "#F7FBF9", color = NA),
    panel.background = element_rect(fill = "#F7FBF9", color = NA),
    panel.grid.major = element_line(color = "grey90"),
    panel.grid.minor = element_blank(),
    axis.text.x = element_text(angle = 45, hjust = 1),
    plot.title = element_text(face = "bold", size = 20),
    plot.subtitle = element_text(size = 14, margin = margin(b = 10)),
    plot.caption = element_text(size = 10, face = "italic", hjust = 1),
    axis.title.x = element_text(margin = margin(t = 10)),
    axis.title.y = element_text(margin = margin(r = 10))
  )
ggsave(
  filename = paste0(folder_path,"packages_loaded.png"),
  width = 10,
  height = 6,
  dpi = 300,
  bg = "#F7FBF9"
)

# lines per script ----
ggplot(
  subset(date_summ, date_floor >= as_date(cutoff_date)),
  aes(x = date_floor, y = lines_per_script)
) +
  geom_point(size = 2, alpha = 0.6, color = "#478873") +
  geom_smooth(color = "#2F4F4F", size = 1.2, se=F)  + # A darker gray-green for contrast
  labs(
    title = "Number of Lines Per R Script Over Time",
    subtitle = "Number of lines in each R script by last modified date (2012–2025)",
    x = "Last modified date",
    y = "Avg # of lines",
    caption = "Source: My R code repository"
  ) +
  scale_x_date(
    date_breaks = "1 year",
    date_labels = "%Y",
    limits = c(as_date("2012-01-01"), NA),
    expand = c(0.01, 0.01)
  ) +
  theme_minimal(base_size = 16) +
  theme(
    plot.background = element_rect(fill = "#F7FBF9", color = NA),
    panel.background = element_rect(fill = "#F7FBF9", color = NA),
    panel.grid.major = element_line(color = "grey90"),
    panel.grid.minor = element_blank(),
    axis.text.x = element_text(angle = 45, hjust = 1),
    plot.title = element_text(face = "bold", size = 20),
    plot.subtitle = element_text(size = 14, margin = margin(b = 10)),
    plot.caption = element_text(size = 10, face = "italic", hjust = 1),
    axis.title.x = element_text(margin = margin(t = 10)),
    axis.title.y = element_text(margin = margin(r = 10))
  )
ggsave(
  filename = paste0(folder_path,"lines_per_script.png"),
  width = 10,
  height = 6,
  dpi = 300,
  bg = "#F7FBF9"
)

# comments per line ----
ggplot(
  subset(date_summ, date_floor >= as_date(cutoff_date)),
  aes(x = date_floor, y = comments_per_line)
) +
  geom_point(size = 2, alpha = 0.6, color = "#478873") +
  geom_smooth(color = "#2F4F4F", size = 1.2, se=F)  + # A darker gray-green for contrast
  labs(
    title = "Number of Comments Per Line Over Time",
    subtitle = "Number of comments per line in each R script by last modified date (2012–2025)",
    x = "Last modified date",
    y = "Comments Per Line",
    caption = "Source: My R code repository"
  ) +
  scale_x_date(
    date_breaks = "1 year",
    date_labels = "%Y",
    limits = c(as_date("2012-01-01"), NA),
    expand = c(0.01, 0.01)
  ) +
  theme_minimal(base_size = 16) +
  theme(
    plot.background = element_rect(fill = "#F7FBF9", color = NA),
    panel.background = element_rect(fill = "#F7FBF9", color = NA),
    panel.grid.major = element_line(color = "grey90"),
    panel.grid.minor = element_blank(),
    axis.text.x = element_text(angle = 45, hjust = 1),
    plot.title = element_text(face = "bold", size = 20),
    plot.subtitle = element_text(size = 14, margin = margin(b = 10)),
    plot.caption = element_text(size = 10, face = "italic", hjust = 1),
    axis.title.x = element_text(margin = margin(t = 10)),
    axis.title.y = element_text(margin = margin(r = 10))
  )
ggsave(
  filename = paste0(folder_path,"comments_per_line.png"),
  width = 10,
  height = 6,
  dpi = 300,
  bg = "#F7FBF9"
)