import csv
import json
import re
import matplotlib.pyplot as plt
import numpy as np
from collections import Counter
from pprint import pprint

stop_words = [
    "(review)",
    "of",
    "and",
    "the",
    "we",
    "in",
    "to",
    "what",
    "a",
    "on",
    "an",
    "do",
    "for",
    "with",
    "is",
    "it",
    "that",
    "this",
    "as",
    "by",
    "are",
    "using",
    "from",
    "how",
    "has",
    "be",
    "or",
    "can",
    "our",
    "at",
    "why",
    "when",
    "introduction",
    "your",
    "through",
    "et",
    "al.",
    "&",
    "",
]
file_path = "data.csv"
data = []


def parse_csv(file_path):
    with open(file_path, "r") as file:
        reader = csv.reader(file)
        for row in reader:
            data.append(row)


def extract_journal_titles(data):
    journal_titles = []
    for row in data:
        if "(edited volume)" not in row[3]:
            journal_titles.append(row[3])
    count_journal_titles = Counter(journal_titles).most_common(30)
    pprint(count_journal_titles)
    print("Total journals: " + str(len(set(journal_titles))))


def extract_title_keywords(data):
    title_keywords = []
    re_words = []
    for row in data:
        raw_words = row[2].split(" ")
        row_words = []
        for word in raw_words:
            re_word = re.sub(r"[^a-zA-Z\-]", "", word.lower())
            if re_word not in stop_words:
                re_words.append(re_word)
                row_words.append(re_word)
    title_keywords = [(word, row_words) for word in re_words]
    return title_keywords


def print_title_keywords(data):
    title_keywords = extract_title_keywords(data)
    title_keywords = [word[0] for word in title_keywords]
    count_title_words = Counter(title_keywords).most_common(30)
    pprint(count_title_words)


def histogram(data):
    dates = []
    for row in data:
        dates.append(int(row[4]))
    years = range(min(dates), max(dates) + 2)
    plt.hist(dates, bins=years)
    plt.show()


def names(data):
    names = []
    for row in data:
        name_parts = row[1].split(" ")
        for name in name_parts:
            name = name.rstrip(",")
            if name not in stop_words:
                if "." not in name:
                    names.append(name)
    count_names = Counter(names).most_common(30)
    pprint(count_names)


if __name__ == "__main__":
    parse_csv(file_path)
    data = data[1:]
    extract_journal_titles(data)
    print_title_keywords(data)
    # names(data)
    histogram(data)