erap129

ratings_df = pd.read_csv(f'{BASE_FOLDER}/MovieLens-1M/ratings.dat',
                         delimiter='::', engine='python', header=None,
                         names=['user_id', 'movie_id', 'rating', 'time'])
ratings_df.head()

erap129

users_df_occupation_by_gender = users_df.groupby(['occupation', 'gender']).size().reset_index(name='occupation_by_gender_count')
gender_count = users_df['gender'].value_counts()
users_df_occupation_by_gender['occupation_by_gender_count'] = \
    users_df_occupation_by_gender['occupation_by_gender_count'].div(users_df_occupation_by_gender['gender'].map(gender_count))
users_df_occupation_by_gender
occupation_by_gender_plot = px.bar(users_df_occupation_by_gender, x='occupation', y='occupation_by_gender_count', color='gender', barmode='group')
occupation_by_gender_plot

erap129

erap129

readme_text = np.array(open(f'{BASE_FOLDER}/MovieLens-1M/README').read().splitlines())
start_index = np.flatnonzero(np.core.defchararray.find(readme_text,'Occupation is chosen')!=-1)[0]
end_index = np.flatnonzero(np.core.defchararray.find(readme_text,'MOVIES FILE DESCRIPTION')!=-1)[0]
occupation_list = [x.split('"')[1] for x in readme_text[start_index:end_index][2:-1].tolist()]
occupation_dict = dict(zip(range(len(occupation_list)), occupation_list))

users_df = pd.read_csv(f'{BASE_FOLDER}/MovieLens-1M/users.dat',
                       delimiter='::', engine='python', header=None,
                       names=['user_id', 'gender', 'age', 'occupation', 'zip_code'])
users_df['occupation'] = users_df['occupation'].replace(occupation_dict)

erap129

movies_df['year'] = movies_df['movie_name'].apply(lambda movie_name: re.search('\((\d*)\)', movie_name).groups(1)[0])
movie_count_by_year = px.histogram(movies_df, x='year', height=400, title='Movie count by year').update_xaxes(categoryorder="total descending")
movie_count_by_year

erap129

movies_df['genre'] = movies_df['genre'].apply(lambda x: x.split('|'))
movies_df_exploded = movies_df.explode('genre')
px.histogram(movies_df_exploded, x='genre', height=400, title='Movie count by genre').update_xaxes(categoryorder="total descending")

erap129

erap129

movies_df = pd.read_csv(f'{BASE_FOLDER}/MovieLens-1M/movies.dat',
                        delimiter='::', engine= 'python', header=None,
                        names=['movie_name', 'genre'])
movies_df.head()

erap129

import pandas as pd
import plotly.express as px
from sklearn.feature_extraction.text import TfidfVectorizer
import wikipedia
import numpy as np
from tqdm.notebook import tqdm
import re
import os
from sklearn.metrics.pairwise import linear_kernel
from surprise import Dataset

erap129

import sys
from PyQt6.QtWidgets import QApplication, QHBoxLayout, QMainWindow, QPushButton, QSpinBox, QVBoxLayout, QWidget, QFileDialog, QLabel, QErrorMessage
from PyQt6.QtGui import QImage, QPixmap
import cv2
import numpy as np