It would seem that I have far too much time on my hands. After the post about a Star Trek “test”, I started wondering if there could be any data to back it up and… well here we go:

The Next Generation

DS9

Voyager

Enterprise

Discovery

Note: This is a limited dataset, as the source site only has transcripts for seasons 1, 2, and 4

If anyone is interested, here’s the (rather hurried) Python used:

#!/usr/bin/env python

#
# This script assumes that you've already downloaded all the episode lines from
# the fantastic chakoteya.net:
#
# wget --accept=html,htm --relative --wait=2 --include-directories=/STDisco17/ http://www.chakoteya.net/STDisco17/episodes.html -m
# wget --accept=html,htm --relative --wait=2 --include-directories=/Enterprise/ http://www.chakoteya.net/Enterprise/episodes.htm -m
# wget --accept=html,htm --relative --wait=2 --include-directories=/Voyager/ http://www.chakoteya.net/Voyager/episode_listing.htm -m
# wget --accept=html,htm --relative --wait=2 --include-directories=/DS9/ http://www.chakoteya.net/DS9/episodes.htm -m
# wget --accept=html,htm --relative --wait=2 --include-directories=/NextGen/ http://www.chakoteya.net/NextGen/episodes.htm -m
#
# Then you'll probably have to convert the following files to UTF-8 as they
# differ from the rest:
#
# * Voyager/709.htm
# * Voyager/515.htm
# * Voyager/416.htm
# * Enterprise/41.htm
#

import re
from collections import defaultdict
from pathlib import Path

EPISODE_REGEX = re.compile(r"^\d+\.html?$")
LINE_REGEX = re.compile(r"^(?P<name>[A-Z']+): ")

EPISODES = Path("www.chakoteya.net")
DISCO = EPISODES / "STDisco17"
ENT = EPISODES / "Enterprise"
TNG = EPISODES / "NextGen"
DS9 = EPISODES / "DS9"
VOY = EPISODES / "Voyager"


class CharacterLines:
    def __init__(self, path: Path) -> None:
        self.path = path
        self.line_count = defaultdict(int)

    def collect(self) -> None:
        for episode in self.path.glob("*.htm*"):
            if EPISODE_REGEX.match(episode.name):
                for line in episode.read_text().split("\n"):
                    if m := LINE_REGEX.match(line):
                        self.line_count[m.group("name")] += 1

    @property
    def as_percentages(self) -> dict[str, float]:
        total = sum(self.line_count.values())
        r = {}
        for k, v in self.line_count.items():
            percentage = round(v * 100 / total, 2)
            if percentage > 1:
                r[k] = percentage
        return {k: v for k, v in reversed(sorted(r.items(), key=lambda _: _[1]))}

    def render(self) -> None:
        print(self.path.name)
        print("| Name             | Percentage of Lines |")
        print("| ---------------- | ------------------- |")
        for character, pct in self.as_percentages.items():
            print(f"| {character:16} | {pct} |")


if __name__ == "__main__":
    for series in (TNG, DS9, VOY, ENT, DISCO):
        counter = CharacterLines(series)
        counter.collect()
        counter.render()