| import streamlit as st | |
| import numpy as np | |
| import pandas as pd | |
| final_movie_df = pd.read_csv('movie_data.csv') | |
| similarity = np.load("similarity.npy") | |
| def recomendMovie(movie_title) : | |
| matching_indices = final_movie_df[final_movie_df['title'].str.contains(movie_title, case=False, na=False)].index | |
| if not matching_indices.empty: | |
| distance = similarity[matching_indices[0]] | |
| movie_list = sorted(list(enumerate(distance)), reverse=True, key = lambda x: x[1])[1:6] | |
| output_list = [] | |
| for movie in movie_list: | |
| output_list.append(final_movie_df.iloc[movie[0]].title) | |
| return pd.DataFrame({ | |
| 'movie_name' : output_list | |
| }) | |
| else: | |
| return "This movie isn't present in the dataset." | |
| st.title('Get recommendation related to your favourite movies 🍿 🎬') | |
| name = st.text_input("Enter Movie name: ") | |
| if name != "": | |
| output = recomendMovie(name) | |
| st.dataframe(output, use_container_width=True) |