Modified gantt plot to visualize the appearances of characters in the manga 'Kanojo, Okarishimasu'

appearances.py

# Given a one-hot encoded csv file with character names as the columns and each row representing a chapter/episode, 
# this script generates a gantt chart timeline for the appearances of each character. 
# Created by Anthony Teo

# Example: mainapps.csv
# Kazuya,Ruka,Mami
# 1,0,0
# 0,1,1
# 1,1,1
# 1,0,0

import plotly.figure_factory as ff
import plotly.express as px
from datetime import datetime
import numpy as np
import sys
import os
import pandas as pd


def convert_to_datetime(x):
    return datetime.fromtimestamp(31536000+x*24*3600).strftime("%Y-%m-%d")


data = pd.read_csv(os.path.join(sys.path[0], 'mainapps.csv'))
chapters = 0

df = []
for col in data.columns:
    start = -1
    if chapters != len(data[col]):
        chapters = len(data[col])
    for i in range(len(data[col])):
        val = data[col][i]
        if val == 1:
            if start == -1:
                start = i
        else:
            if start != -1:
                df.append(dict(Task="Appearance", Start=convert_to_datetime(
                    start), Finish=convert_to_datetime(i), Character=col))
                start = -1
    if start != -1:
        df.append(dict(Task="Appearance", Start=convert_to_datetime(
            start), Finish=convert_to_datetime(i + 1), Character=col))
        start = -1


num_tick_labels = np.linspace(
    start=0, stop=chapters, num=chapters + 1, dtype=int)
date_ticks = [convert_to_datetime(x) for x in num_tick_labels]

fig = px.timeline(df, x_start="Start", x_end="Finish",
                  y="Character", color="Character")
fig.update_layout({
    "plot_bgcolor": 'rgba(0,0,0,0.0)',
    "paper_bgcolor": 'rgba(0,0,0,0.0)'
})
fig.layout.xaxis.update({
    'tickvals': date_ticks,
    'ticktext': num_tick_labels
})
fig.show()

mainapps.csv

scraping.py

# This script scrapes the 'Characters' field in the KanoKari wiki and exports it as a one-hot encoded csv file. 

import requests
from bs4 import BeautifulSoup
import pandas as pd


chapters = 165
charApps = []
charMap = {
    "Kazuya Kinoshita": 1,
    "Chizuru Ichinose": 2,
    "Ruka Sarashina": 3,
    "Mami Nanami": 4,
    "Sumi Sakurasawa": 5,
    "Mini Yaemori": 6
}

for i in range(1, chapters):
    URL = 'https://kanojo-okarishimasu.fandom.com/wiki/Chapter_' + str(i)
    page = requests.get(URL)
    soup = BeautifulSoup(page.content, 'html.parser')

    ul = soup.find(id='Characters').findNext('ul')
    oneHot = [0] * len(charMap)
    for li in ul.findAll('li'):
      charName = li.text
      if charName in charMap:
        oneHot[charMap[charName] - 1] = 1
    charApps.append(oneHot)


# create df from columns
df_chars = pd.DataFrame(
    charApps, columns=charMap.keys())
print(df_chars.head(10))

df_chars.to_csv('apps.csv', index=False)