import gradio as gr
import numpy as np
import pandas as pd
import ast


from datasets import load_dataset, concatenate_datasets
movies = load_dataset("jyshbgde/cinescopeDataset", data_files = "tmdb_5000_movies.csv")
credits = load_dataset("jyshbgde/cinescopeDataset", data_files = "tmdb_5000_credits.csv")

movies = movies['train']
credits = credits['train']
movies = movies.remove_columns("title")
movies = concatenate_datasets([movies, credits], axis = 1, )

movies = movies.to_pandas()
movies = movies[["movie_id", "title", "overview", "genres", "keywords", "cast", "crew"]]
movies = movies.dropna()

def convert(obj):
  L = []
  for i in ast.literal_eval(obj):
    L.append(i['name'])
  return L

movies['genres'] = movies['genres'].apply(convert)
movies['keywords'] = movies['keywords'].apply(convert)

def convert3(obj):
  L = []
  counter = 0
  for i in ast.literal_eval(obj):
    if counter != 3:
      L.append(i['name'])
      counter +=1
    else:
      break
  return L

movies['cast'] = movies['cast'].apply(convert3)

def fetch_director(obj):
  L = []
  for i in ast.literal_eval(obj):
    if(i['job'] == 'Director'):
      L.append(i['name'])
      break
  return L

movies['crew'] = movies['crew'].apply(fetch_director)

overview = movies['overview'].apply(lambda x : x.split())
genres = movies['genres'].apply(lambda x : [ i.replace(" ", "") for i in x])
keywords = movies['keywords'].apply(lambda x : [ i.replace(" ", "") for i in x])
cast = movies['cast'].apply(lambda x : [ i.replace(" ", "") for i in x])
crew = movies['crew'].apply(lambda x : [ i.replace(" ", "") for i in x])

movies['tags'] = overview + genres + keywords + cast + crew

new_movies_df = movies[['movie_id','title', 'tags']]

new_movies_df['tags'] = new_movies_df['tags'].apply(lambda x : " ".join(x))



new_movies_df['tags'] = new_movies_df['tags'].apply(lambda x : x.lower())
new_movies_df['lower_title'] = new_movies_df['title'].apply(lambda x : x.lower())

import nltk

from nltk.stem.porter import PorterStemmer
ps = PorterStemmer()

def stem(text):
  y = []
  for i in text.split():
    y.append(ps.stem(i))
  
  return " ".join(y)

new_movies_df['tags'] = new_movies_df['tags'].apply(stem)

from sklearn.feature_extraction.text import CountVectorizer

cv = CountVectorizer(max_features = 5000, stop_words = 'english')

vectors = cv.fit_transform(new_movies_df['tags']).toarray()


from sklearn.metrics.pairwise import cosine_similarity

similarity = cosine_similarity(vectors)

def recommend(movie):
  movie = movie.lower()
  if movie not in new_movies_df['lower_title'].values:
    return [{
        "error": "movie not found"
    }]
  else:
    movie_index = new_movies_df[new_movies_df['lower_title'] == movie].index[0]
    distances = similarity[movie_index]
    movies_list =sorted(list(enumerate(distances)), reverse = True, key= lambda x : x[1])[1:6]
    
    recommended_movies = []
    for i in movies_list:

        obj = {
            "_id":str(movies.iloc[i[0]]["movie_id"]),
            "title":movies.iloc[i[0]]["title"],
            "overview":movies.iloc[i[0]]["overview"],
            "genres": movies.iloc[i[0]]["genres"],
            "casts":movies.iloc[i[0]]["cast"],
            "crew": movies.iloc[i[0]]["crew"],
        }
        recommended_movies.append(obj)
        
       
        
    return recommended_movies

iface = gr.Interface(fn = recommend,
                     inputs = 'text',
                     outputs = "json",
                     title = "Movie Recommendation",
                     description = 'Get movies recommendation')
iface.launch(debug = True)