logic.py

import pandas as pd
from arango import ArangoClient
from tqdm import tqdm
import numpy as np
import itertools
import requests
import sys
import oasis
from arango import ArangoClient

import torch
import torch.nn.functional as F
from torch.nn import Linear
from arango import ArangoClient
import torch_geometric.transforms as T
from torch_geometric.nn import SAGEConv, to_hetero
from torch_geometric.transforms import RandomLinkSplit, ToUndirected
from sentence_transformers import SentenceTransformer
from torch_geometric.data import HeteroData
import yaml

#-------------------------------------------------------------------------------------------
# Functions

# performs user and movie mappings
def node_mappings(path, index_col):
    df = pd.read_csv(path, index_col=index_col)
    mapping = {index: i for i, index in enumerate(df.index.unique())}

    return mapping


def convert_int(x):
    try:
        return int(x)
    except:
        return np.nan


def remove_movies(m_id):
    '''
    # Remove ids which dont have meta data information
    '''
    no_metadata = []
    for idx in range(len(m_id)):
        tmdb_id = id_map.loc[id_map['movieId'] == m_id[idx]]
  
        if tmdb_id.size == 0:
            no_metadata.append(m_id[idx])
            #print('No Meta data information at:', m_id[idx])
    return no_metadata


#-------------------------------------------------------------------------------------------

def make_graph():
    metadata_path = './sampled_movie_dataset/movies_metadata.csv'
    df = pd.read_csv(metadata_path)
    df = df.drop([19730, 29503, 35587])
    df['id'] = df['id'].astype('int')

    links_small = pd.read_csv('./sampled_movie_dataset/links_small.csv')
    links_small = links_small[links_small['tmdbId'].notnull()]['tmdbId'].astype('int') # selecting tmdbId coloumn from links_small file

    sampled_md = df[df['id'].isin(links_small)]
    sampled_md['tagline'] = sampled_md['tagline'].fillna('')
    sampled_md['description'] = sampled_md['overview'] + sampled_md['tagline']
    sampled_md['description'] = sampled_md['description'].fillna('')
    sampled_md = sampled_md.reset_index()

    indices = pd.Series(sampled_md.index, index=sampled_md['title'])
    ind_gen = pd.Series(sampled_md.index, index=sampled_md['genres'])

    ratings_path = './sampled_movie_dataset/ratings_small.csv'
    ratings_df = pd.read_csv(ratings_path)
    m_id = ratings_df['movieId'].tolist()
    m_id = list(dict.fromkeys(m_id))

    user_mapping = node_mappings(ratings_path, index_col='userId')
    movie_mapping = node_mappings(ratings_path, index_col='movieId')

    id_map = pd.read_csv('./sampled_movie_dataset/links_small.csv')[['movieId', 'tmdbId']]
    id_map['tmdbId'] = id_map['tmdbId'].apply(convert_int)
    id_map.columns = ['movieId', 'id']
    id_map = id_map.merge(sampled_md[['title', 'id']], on='id').set_index('title') # tmbdid is same (of links_small) as of id in sampled_md
    indices_map = id_map.set_index('id')

    no_metadata = remove_movies(m_id)

    ## remove ids which dont have meta data information
    for element in no_metadata:
        if element in m_id:
            print("ids with no metadata information:",element)
            m_id.remove(element)

    # create new movie_mapping dict with only m_ids having metadata information
    movie_mappings = {}
    for idx, m in enumerate(m_id):
        movie_mappings[m] = idx

    return movie_mappings

    
    
def load_data_to_ArangoDB():