Add wordcounts plot script

2026-09-12 14:05:28 +02:00
parent 86fab09dfe
commit f52ab00652
3 changed files with 195 additions and 0 deletions
@@ -0,0 +1,84 @@
+#!/usr/bin/env Rscript
+# Usage: Rscript plot_wordcounts.R [tick_days] [input.csv] [output.svg]
+# By default, label every seven days, independently of the data points.
+
+library(ggplot2)
+
+args <- commandArgs(trailingOnly = TRUE)
+if (length(args) > 3L) {
+  stop("Usage: Rscript plot_wordcounts.R [tick_days] [input.csv] [output.svg]")
+}
+tick_days <- if (length(args) >= 1L) {
+  as.numeric(args[1])
+} else {
+  7
+}
+
+script_arg <- grep("^--file=", commandArgs(), value = TRUE)[1]
+script_dir <- dirname(normalizePath(sub("^--file=", "", script_arg)))
+input <- if (length(args) >= 2L) {
+  args[2]
+} else {
+  file.path(script_dir, "wordcounts.csv")
+}
+output <- if (length(args) >= 3L) {
+  args[3]
+} else {
+  file.path(script_dir, "wordcounts.svg")
+}
+
+counts <- read.csv(input, colClasses = "character")
+
+timezone <- Sys.getenv("TZ", unset = "Europe/Berlin")
+if (!nzchar(timezone)) {
+  timezone <- "Europe/Berlin"
+}
+normalized <- sub("([+-][0-9]{2}):([0-9]{2})$", "\\1\\2", counts$date)
+counts$timestamp <- as.POSIXct(
+  normalized,
+  format = "%Y-%m-%dT%H:%M:%S%z",
+  tz = timezone
+)
+date_only <- grepl("^[0-9]{4}-[0-9]{2}-[0-9]{2}$", counts$date)
+counts$timestamp[date_only] <- as.POSIXct(
+  counts$date[date_only],
+  format = "%Y-%m-%d",
+  tz = timezone
+)
+counts$wordcount <- as.numeric(counts$wordcount)
+counts <- counts[order(counts$timestamp), ]
+
+# Fixed time intervals
+start <- as.POSIXct(
+  format(min(counts$timestamp), "%Y-%m-%d", tz = timezone),
+  tz = timezone
+)
+interval <- tick_days * 86400
+span <- as.numeric(difftime(max(counts$timestamp), start, units = "secs"))
+ticks <- start + seq(0, max(1, ceiling(span / interval))) * interval
+
+plot <- ggplot(counts, aes(x = timestamp, y = wordcount)) +
+  scale_x_datetime(
+    breaks = ticks,
+    limits = range(ticks),
+    date_labels = "%Y-%m-%d",
+    timezone = timezone,
+    minor_breaks = NULL
+  ) +
+  scale_y_continuous(labels = scales::label_comma()) +
+  labs(
+    title = "Thesis Word Count",
+    x = "Date",
+    y = "Words"
+  ) +
+  theme_minimal(base_size = 12) +
+  theme(
+    axis.text.x = element_text(angle = 45, hjust = 1),
+    panel.grid.minor = element_blank()
+  )
+if (nrow(counts) > 1L) {
+  plot <- plot + geom_line(linewidth = 0.5)
+}
+
+ggsave(output, plot, width = 10, height = 5, dpi = 180, bg = "white")
+message("Saved ", output)