reupload of current files

app.py

@@ -1,18 +1,9 @@
 import streamlit as st
 import pandas as pd
 
-st.markdown("# Introduction")
-st.sidebar.markdown("# Introduction")
-
 st.title("Movie Recommenders")
  
 st.write("""
 ### Instructions
 Check the Sidebar and choose a recommender that suits your purpose.  
-""")
-
-movies = pd.read_csv('https://raw.githubusercontent.com/tobiasaurer/recommender-systems/main/movie_data/movies.csv')
-ratings = pd.read_csv('https://raw.githubusercontent.com/tobiasaurer/recommender-systems/main/movie_data/ratings.csv')
-
-all_ratings = ratings.merge(movies, on='movieId')[['title', 'rating', 'userId']]
-all_ratings_pivoted = all_ratings.pivot_table(index='userId', columns='title', values='rating')
+""")

pages/1 - Popularity based recommender.py

@@ -1,12 +1,48 @@
 import streamlit as st
+import pandas as pd
 
-st.title("Test Page")
+# Import Data
+movies = pd.read_csv('https://raw.githubusercontent.com/tobiasaurer/recommender-systems/main/movie_data/movies.csv')
+ratings = pd.read_csv('https://raw.githubusercontent.com/tobiasaurer/recommender-systems/main/movie_data/ratings.csv')
+
+st.title("Popularity-Based Recommender")
  
 st.write("""
 ### Instructions
-Check the Sidebar and choose a recommender that suits your purpose.  
+Move the slider to the desired number of recommendations you wish to receive. 
+Afterwards, simply click the "Recommend!" button to receive recommendations of the most popular movies in our database. 
+If you want, you can narrow it down by picking one or several genre(s).  
 """)
 
-if st.button("TEST"):
+# FUNCTIONS:
+
+def get_popular_recommendations(n, genres):
+    return (
+        ratings
+            .groupby('movieId')
+            .agg(avg_rating = ('rating', 'mean'), num_ratings = ('rating', 'count'))
+            .merge(movies, on='movieId')
+            .assign(combined_rating = lambda x: x['avg_rating'] * x['num_ratings']**0.5)
+            [lambda df: df["genres"].str.contains(genres, regex=True)]
+            .sort_values('combined_rating', ascending=False)
+            .head(n)
+            [['title', 'avg_rating', 'genres']]
+    )
+
+def transform_genre_to_regex(genres):
+    regex = ""
+    for genre in genres:
+        regex += f"(?=.*{genre})"
+    return regex
+
+# USER INPUT:
+number_of_recommendations = st.slider("Number of recommendations", 1, 10, 5)
+
+genre_list = set([inner for outer in movies.genres.str.split('|') for inner in outer])
+genres = st.multiselect('Optional: Select one or more genres', genre_list, default=None, key=None, help=None, on_change=None, args=None, kwargs=None, disabled=False)
+genres_regex = transform_genre_to_regex(genres)
+
+
+if st.button("Recommend!"):
 
-    st.write(movies.head(10))
+    st.write(get_popular_recommendations(number_of_recommendations, genres_regex))

pages/3 - Old recommender.py

@@ -1,43 +0,0 @@
-import streamlit as st
-import pandas as pd
-
-
-st.title("Movie Recommender")
- 
-st.write("""
-### Instructions
-Type in a movie title with the release year in brackets (e.g. "The Matrix (1999)"), choose the number of recommendations you wish, and the app will recommend movies based on your chosen movie.\n\n 
-The recommendation process will take ca. 15 seconds. 
-""")
-
-chosen_movie = st.text_input("Movie title and release year")
-number_of_recommendations = st.slider("Number of recommendations", 1, 10, 5)
-
-movies = pd.read_csv('https://raw.githubusercontent.com/tobiasaurer/recommender-systems/main/movie_data/movies.csv')
-ratings = pd.read_csv('https://raw.githubusercontent.com/tobiasaurer/recommender-systems/main/movie_data/ratings.csv')
-
-all_ratings = ratings.merge(movies, on='movieId')[['title', 'rating', 'userId']]
-all_ratings_pivoted = all_ratings.pivot_table(index='userId', columns='title', values='rating')
-
-def get_recommendations_for_movie(movie_name, n):
-    
-    eligible_movies = []
-
-    for movie in all_ratings_pivoted.columns:
-        nr_shared_ratings = all_ratings_pivoted.loc[all_ratings_pivoted[movie_name].notnull() & all_ratings_pivoted[movie].notnull(), [movie_name, movie]].count()[0]
-        if nr_shared_ratings >= 10:
-            eligible_movies.append(movie)
-
-    return (
-        all_ratings_pivoted
-            [eligible_movies]
-            .corrwith(all_ratings_pivoted[movie_name]).sort_values(ascending=False)[1:n+1]
-            .index
-    )
-
-if st.button("Recommend"):
-    
-    recommendations = get_recommendations_for_movie(chosen_movie, number_of_recommendations)
-
-    st.write("Recommendations for", chosen_movie)
-    st.write(recommendations)