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):
    try:
        with open(file_path, "r") as file:
            reader = csv.reader(file)
            for row in reader:
                data.append(row)
    except FileNotFoundError:
        print(f"Error: File {file_path} not found")
        return
    except Exception as e:
        print(f"Error reading file: {e}")
        return


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 = []
    for row in data:
        raw_words = row[2].split(" ")
        for word in raw_words:
            re_word = re.sub(r"[^a-zA-Z\-]", "", word.lower())
            if re_word not in stop_words and re_word != "":
                title_keywords.append(re_word)
    return Counter(title_keywords).most_common(30)


def print_title_keywords(data):
    title_keywords = extract_title_keywords(data)
    pprint(title_keywords)


def histogram(data):
    dates = []
    for row in data:
        try:
            dates.append(int(row[4]))
        except (ValueError, IndexError):
            # Skip invalid date entries
            continue
    
    if not dates:
        print("No valid dates found")
        return
        
    min_year = min(dates)
    max_year = max(dates)
    
    # Create bins with reasonable spacing
    years = range(min_year, max_year + 1)
    plt.hist(dates, bins=len(years), edgecolor='black')
    plt.xlabel('Year')
    plt.ylabel('Frequency')
    plt.title('Publication Year Distribution')
    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 and name != "":
                    names.append(name)
    count_names = Counter(names).most_common(30)
    pprint(count_names)


if __name__ == "__main__":
    parse_csv(file_path)
    if data:  # Only process if data was loaded
        data = data[1:]  # Skip header row
        extract_journal_titles(data)
        print_title_keywords(data)
        # names(data)
        histogram(data)
    else:
        print("No data to process")