Extract Text

import seaborn as sns

import matplotlib.pyplot as plt

from cycler import cycler

import os

import pandas as pd

import statistics

import re

from nltk.probability import FreqDist

#file header: 

# work_id,title,author,rating,category,fandom,relationship,character,additional tags,language,published,status,status date,words,chapters,comments,kudos,bookmarks,hits,all_kudos,all_bookmarks,body

# 27852922,Dealing with Our Demons,['ravenyenn19'],Mature,F/M,"Six of Crows Series",Kaz Brekker/Inej Ghafa,"Kaz B","Romance,Kanej - Freeform, Eventual Smut",English,2020-12-03,Updated,2023-03-16,747673,162/?,8573,12204,1373,709212,"['ud4m', 'book_addict_1228', 'ephemeraldelights', 'bluedelilah25', 'sunshinecorsets', 'I_do_not_like_purple_glasses', 'beep_boop_00', 'schleswigholstein', 'moonandstars75', 'ewerythingoes', 'mindfighters', 'rosibunnis', 'Lizie06', 'ghostlatte', 'aguswolman', 'QueenofEnglan', 'JenBoyette04', 'gnitneb_reads', 'gloomysunshine', 'v1ofvs', 'BazzaKrekker', 'BookGeek', 'poppyflower19', 'Cassanibal', 'vanilla_chai_tea', 'Honorthyword', 'mariaarmengol', 'luc1inda', 'zarawrites', 'monmough', 'Guilty__Pleasures', 'Ilyann', 'folieadeux_0_0', 'dragonguard', 'Emeliemarx', 'angrydabee', 'slythxrclaw', 'samaram0215', 'letsgetthisbread69', 'Mintmew', 'biblichour', 'Katloupet', 'Miss_ginger', 'inejsquake', 'Arabella_7833', 'flossy_flo99', 'a_k123', 'hushedwanderer', 'siriuslymichele', 'AnnaAvinaVTDX']",[],"Dear Kaz,

grisha_fanfics = pd.read_csv("grishaverse/data/fanfics/grishaverse_fics.csv")

tog_fanfics = pd.read_csv("throne_of_glass/data/fanfics/throne_of_glass_fics.csv")

"""

grisha_kudos = grisha_fanfics["kudos"].values.tolist()

grisha_kudos_freq_dist = FreqDist(grisha_kudos)

# convert to FreqDist object to a pandas series for easier processing

dist_panda = pd.Series(dict(grisha_kudos_freq_dist))

#print(dist_panda)

# plot using matplotlib and seaborn 

# set figure, ax into variables

fig, ax = plt.subplots(figsize=(10,10))

# call function for bar (value) labels 

#addlabels(x=new_sent_len_dist.index, y=new_sent_len_dist.values)

plt.title("Grishaverse Frequency Distribution of All Kudos")

ax.set_xlabel("Number of Kudos")

ax.set_ylabel("Percentage of Occurence")

sns.lineplot(x=dist_panda.index, y=dist_panda.values, ax=ax, palette="flare")

#plt.xticks(rotation=30) !!! very useful for words

plt.savefig(f"grishaverse/freq_distribution/fanfic_kudo_freq_dist.png") # "throne_of_glass/freq_distribution/all_canon_sent_len.png"

"""

def preprocess_data(df, series):

    good_fics = []

    medium_fics = []

    bad_fics = []

    few_kudos = 100

    medium_kudos = 1500

    for index, row in df.iterrows():

        published = pd.to_datetime(row["published"])

        if published.year != 2023:

            if not pd.isna(row["kudos"]):

                kudos = pd.to_numeric(row["kudos"], errors="coerce")

                if kudos <= few_kudos:

                    bad_fics.append(row["body"])

                elif kudos <= medium_kudos:

                    medium_fics.append(row["body"])

                elif kudos > medium_kudos:

                    good_fics.append(row["body"])

            else:

                print(f"Missing kudos value for row {index}")

    bad_fics_joined = ''.join(map(str, bad_fics))

    good_fics_joined = ''.join(map(str, good_fics))

    medium_fics_joined = ''.join(map(str, medium_fics))

    with open(f"{series}/data/split_txt_fanfics/good_fics.txt", "w") as f:

        f.write(good_fics_joined)

    with open(f"{series}/data/split_txt_fanfics/bad_fics.txt", "w") as f:

        f.write(bad_fics_joined)

    with open(f"{series}/data/split_txt_fanfics/medium_fics.txt", "w") as f:

        f.write(medium_fics_joined)

preprocess_data(grisha_fanfics, "grishaverse")

preprocess_data(tog_fanfics, "throne_of_glass")