fuzzy-game-recommender/main.py

import pandas as pd
from fuzzy_controllers import fuzzy_controler_similiarity
from numpy import dot
from numpy.linalg import norm
import json
import multiprocessing
from tqdm.auto import tqdm
from sys import argv
import sys, getopt
import argparse
import random

def find_games_categorical_similarity(game_1: pd.DataFrame, game_2: pd.DataFrame) -> float:
    game_1_categorical = set(game_1['all_categorical'].tolist()[0])
    game_2_categorical = set(game_2['all_categorical'].tolist()[0])
    return round(len(game_1_categorical & game_2_categorical) / len(game_1_categorical | game_2_categorical), 2)


def find_games_numerical_similarity(game_1: pd.DataFrame, game_2: pd.DataFrame) -> float:
    game_1_popularity = float(game_1["fuzzy_popularity"].to_string(index=False))
    game_2_popularity = float(game_2["fuzzy_popularity"].to_string(index=False))
    return round(abs(game_1_popularity - game_2_popularity), 2)


def find_games_word_vector_distance(game_1: pd.DataFrame, game_2: pd.DataFrame) -> float:
    game_1_vector = game_1['all_categorical_vector'].tolist()[0]
    game_2_vector = game_2['all_categorical_vector'].tolist()[0]
    return round(dot(game_1_vector, game_2_vector) / (norm(game_1_vector) * norm(game_2_vector)), 2)


def calculate_similarities(game_title, title_list, df, test=False):
    if game_title in title_list:
        title_list.remove(game_title)

    args_list = []
    for compared_title in title_list:
        args_list.append((game_title, compared_title, df))

    similarities = []
    # call the function for each item in parallel with multiprocessing
    with multiprocessing.Pool() as pool:
        for result in pool.starmap(compare_games, tqdm(args_list, total=len(args_list), desc='Searching')):
            similarities.append(result)

    all_games = []
    for title, similarity in zip(title_list, similarities):
        all_games.append({
                    "title": title,
                    "similarity": similarity
                    })

    sorted_games = sorted(all_games, key=lambda k: k['similarity'], reverse=True)
    if (test): return sorted_games[:20]
    print("\n ==== Top 20 most similar games: ====")
    for game in sorted_games[:20]:
        print(f"- {game['title']}")
    save_results(game_title=game_title, game_list=sorted_games)

def save_results(game_title, game_list):
    print("The full list of similar games available in the /results directory\n")
    with open(f"results/similarity_list_{game_title.lower().replace(' ', '_')}.txt", 'w+') as fp:
        json.dump(game_list, fp)

def compare_games(title_1, title_2, df, show_graph=False):
    game_1 = df.loc[df['name'] == title_1]
    game_2 = df.loc[df['name'] == title_2]

    categorical_similarity = find_games_categorical_similarity(game_1=game_1, game_2=game_2)
    numerical_difference = find_games_numerical_similarity(game_1=game_1, game_2=game_2)
    word_vector_distance = find_games_word_vector_distance(game_1=game_1, game_2=game_2)
    similarity_score = fuzzy_controler_similiarity(categorical_data=categorical_similarity,
                                                   numerical_data=numerical_difference,
                                                   vector_distance=word_vector_distance, show_graph=show_graph)
    return similarity_score

def get_game_info_from_df(data_games, game_title):
  finded_game = data_games.loc[data_games["name"] == game_title]
  # print(finded_game)
  result_dict = {
    "title" : finded_game["name"].values[0],
    "price" : finded_game["price"].values[0],
    "all_categorical" : finded_game["all_categorical"].values[0],
  }
  return result_dict


def get_game_info(data_game):
  # finded_game = data_games.loc[data_games["name"] == game_title]
  # print(finded_game)
  result_dict = {
    "title" : data_game["name"],
    "price" : data_game["price"],
    "all_categorical" : data_game["all_categorical"],
  }
  return result_dict

def main(argv):
    df = pd.read_pickle('data/games_processed_vectorized.csv')
    title_list = df["name"].values.tolist()

    test_mode = False
    random_mode = False
    eval_mode = False
    eval_random_mode = False

    opts, args = getopt.getopt(argv, "r:", ["pres", "eval", "evalrandom"])
    for opt, arg in opts:
        if "--pres" == opt: 
            test_mode = True
        if "--eval" == opt: 
            eval_mode = True
        if "--evalrandom" == opt: 
            eval_random_mode = True
        if "-r" == opt: 
            random_mode = arg
    if (True == test_mode):
        game_list = ["Call of Duty®: Modern Warfare® 2", "Project CARS", "DayZ", "STAR WARS™ Jedi Knight - Mysteries of the Sith™", "Overcooked"]
        if (random_mode): game_list = [random.choice(title_list)]
        if (eval_mode or eval_random_mode): game_list = [random.choice(title_list) for i in range(10)]
        result_dict = {"results": []}
        for item in game_list:
            if not eval_random_mode:
                titles_results = calculate_similarities(game_title=item, title_list=title_list, df=df, test=test_mode)
            if eval_random_mode:
                titles_results = [{"title": random.choice(title_list)} for i in range(10)]
            game_result = get_game_info_from_df(df, item)
            game_result["fuzzy_similiar"] = [get_game_info_from_df(df, title_item["title"]) for title_item in titles_results[:10]]
            result_dict["results"].append(game_result)
        with open("results/result.json", "w", encoding="UTF-8") as outfile:
          json.dump(result_dict, outfile, ensure_ascii=False)

    if (False == test_mode):
        while True:
            print("Welcome to Fuzzy Game Reccomender!\nType in a game title and we will find the most similar games from our database")
            title = input("Enter the title or type 'exit' to leave: ")
            if title == "exit":
                break
            else:
                calculate_similarities(game_title=title, title_list=title_list, df=df)


if __name__ == '__main__':
  main(sys.argv[1:])