Update app.py

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 import pickle
 import requests
+import pandas as pd
 
 footer="""<style>
 a:link , a:visited{
@@ -36,6 +37,26 @@ def fetch_poster(movie_id):
     full_path = "https://image.tmdb.org/t/p/w500/" + poster_path
     return full_path
 
+def get_popular(qualified):
+    top_5 = qualified.head(5)
+    return top_5
+
+
+def top_genre_based_movies(genre, percentile=0.95):
+    df = genre_df[genre_df['genres'].str.contains(genre)]
+    vote_counts = df['vote_count'].astype('int')
+    vote_averages = df['vote_average'].astype('int')
+    C = vote_averages.mean()
+    m = vote_counts.quantile(percentile)
+    qualified = df[(df['vote_count'] >= m)][['movie_id', 'title', 'vote_count', 'vote_average', 'genres']]
+    qualified['vote_count'] = qualified['vote_count'].astype('int')
+    qualified['vote_average'] = qualified['vote_average'].astype('int')
+    qualified['wr'] = qualified.apply(
+        lambda x: (x['vote_count'] / (x['vote_count'] + m) * x['vote_average']) + (m / (m + x['vote_count']) * C),
+        axis=1)
+    qualified = qualified.sort_values('wr', ascending=False).head(250)
+    return qualified
+
 def recommend(movie):
     index = movies[movies['title'] == movie].index[0]
     distances = sorted(list(enumerate(similarity[index])), reverse=True, key=lambda x: x[1])
@@ -54,6 +75,12 @@ st.title("Movie Recommender System")
 
 movies = pickle.load(open('movie_list.pkl','rb'))
 similarity = pickle.load(open('similarity.pkl','rb'))
+all_movies = pickle.load(open('movies_df.pkl','rb'))
+top_popular = pickle.load(open('top_popular.pkl','rb'))
+
+s = all_movies.apply(lambda x: pd.Series(x['genres']),axis=1).stack().reset_index(level=1, drop=True)
+s.name = 'genres'
+genre_df = all_movies.drop('genres', axis=1).join(s)
 
 movie_list = movies['title'].values
 option_selected = st.selectbox(
@@ -64,6 +91,7 @@ option_selected = st.selectbox(
 if st.button('Show Recommendation'):
     recommended_movie_names, recommended_movie_posters = recommend(option_selected)
     col1, col2, col3, col4, col5 = st.columns(5)
+    st.header("Movies Based on Movie Content: Similar Movies")
     with col1:
         st.image(recommended_movie_posters[0], caption=recommended_movie_names[0])
     with col2:
@@ -76,6 +104,73 @@ if st.button('Show Recommendation'):
     with col5:
         st.image(recommended_movie_posters[4], caption=recommended_movie_names[4])
 
+    st.header("Top Popular Movies")
+    popular = []
+    for row in top_popular_movies.loc[:,['title','movie_id']].values:
+        popular.append(row)
+    col6, col7, col8, col9, col10 = st.columns(5)
+    with col6:
+        full_path = fetch_poster(popular[0][1])
+        st.image(full_path, caption=popular[0][0])
+    with col7:
+        full_path = fetch_poster(popular[1][1])
+        st.image(full_path, caption=popular[1][0])
+    with col8:
+        full_path = fetch_poster(popular[2][1])
+        st.image(full_path, caption=popular[2][0])
+    with col9:
+        full_path = fetch_poster(popular[3][1])
+        st.image(full_path, caption=popular[3][0])
+    with col10:
+        full_path = fetch_poster(popular[4][1])
+        st.image(full_path, caption=popular[4][0])
+
+
+    st.header("Top Romantic Movies")
+    top_gener_based = top_genre_based_movies('Romance').head(5)
+    genre_popular = []
+    for row in top_gener_based.loc[:, ['title', 'movie_id']].values:
+        genre_popular.append(row)
+    col11, col12, col13, col14, col15 = st.columns(5)
+    with col11:
+        full_path = fetch_poster(genre_popular[0][1])
+        st.image(full_path, caption=genre_popular[0][0])
+    with col12:
+        full_path = fetch_poster(genre_popular[1][1])
+        st.image(full_path, caption=genre_popular[1][0])
+    with col13:
+        full_path = fetch_poster(genre_popular[2][1])
+        st.image(full_path, caption=genre_popular[2][0])
+    with col14:
+        full_path = fetch_poster(genre_popular[3][1])
+        st.image(full_path, caption=genre_popular[3][0])
+    with col15:
+        full_path = fetch_poster(genre_popular[4][1])
+        st.image(full_path, caption=genre_popular[4][0])
+
+    st.header("Top Action Movies")
+    top_gener_based = top_genre_based_movies('Action').head(5)
+    genre_popular = []
+    for row in top_gener_based.loc[:, ['title', 'movie_id']].values:
+        genre_popular.append(row)
+    col16, col17, col18, col19, col20 = st.columns(5)
+    with col16:
+        full_path = fetch_poster(genre_popular[0][1])
+        st.image(full_path, caption=genre_popular[0][0])
+    with col17:
+        full_path = fetch_poster(genre_popular[1][1])
+        st.image(full_path, caption=genre_popular[1][0])
+    with col18:
+        full_path = fetch_poster(genre_popular[2][1])
+        st.image(full_path, caption=genre_popular[2][0])
+    with col19:
+        full_path = fetch_poster(genre_popular[3][1])
+        st.image(full_path, caption=genre_popular[3][0])
+    with col20:
+        full_path = fetch_poster(genre_popular[4][1])
+        st.image(full_path, caption=genre_popular[4][0])
+
+
 
 
 st.markdown(footer,unsafe_allow_html=True)