adds new recommender

pages/1 - Popularity based recommender.py

@@ -1,12 +1,12 @@
 import streamlit as st
 import pandas as pd
 
-# Import Data
+# 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')
 
+# INSTRUCTIONS:
 st.title("Popularity-Based Recommender")
- 
 st.write("""
 ### Instructions
 Move the slider to the desired number of recommendations you wish to receive. 
@@ -42,7 +42,6 @@ genre_list = set([inner for outer in movies.genres.str.split('|') for inner in o
 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)
 
-
+# EXECUTION:
 if st.button("Recommend!"):
-
     st.write(get_popular_recommendations(number_of_recommendations, genres_regex))

pages/2 - User based recommender.py

@@ -0,0 +1,78 @@
+import streamlit as st
+import pandas as pd
+from sklearn.metrics.pairwise import cosine_similarity
+
+# 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')
+
+# create "database" to use for recommendations
+user_item_matrix = (
+                    ratings
+                        .merge(movies, on='movieId')[['title', 'rating', 'userId']]
+                        .pivot_table(index='userId', columns='title', values='rating')
+                        .fillna(0)
+                    )
+
+similarities_users = pd.DataFrame(cosine_similarity(user_item_matrix),
+                                  index=user_item_matrix.index,
+                                  columns=user_item_matrix.index)
+
+# INSTRUCTIONS:
+st.title("User-Based Recommender")
+st.write("""
+### Instructions
+Type in the user-ID you want to receive recommendations for.  
+Move the slider to the desired number of recommendations you wish to receive. 
+""")
+st.write("""
+Optional: You can narrow down the recommendations by picking one or several genre(s).  
+  
+Note: The more genres you choose, the fewer movies will be recommended.
+""")
+
+# FUNCTIONS:
+
+def get_user_recommendations(user_id, n, genres):
+    
+    user_id = int(user_id)
+    # calculate weights for ratings
+    weights = similarities_users.loc[similarities_users.index != user_id, user_id] / sum(similarities_users.loc[similarities_users.index != user_id, user_id])
+    
+    # get unwatched movies for recommendations
+    unwatched_movies = (
+        user_item_matrix
+            .loc[user_item_matrix.index != user_id, user_item_matrix.loc[user_id,:] == 0]
+            .T
+        )
+
+    # compute weighted averages and return the n movies with the highest predicted ratings
+    weighted_averages = pd.DataFrame(unwatched_movies.dot(weights), columns = ["predicted_rating"])
+    recommendations = (
+        weighted_averages
+            .sort_values("predicted_rating", ascending=False)
+            .head(n)
+            .merge(movies, how= 'left', left_index = True, right_on = 'title')
+            [lambda df: df["genres"].str.contains(genres, regex=True)]
+    )
+
+    return recommendations[['title', 'genres']]
+
+def transform_genre_to_regex(genres):
+    regex = ""
+    for genre in genres:
+        regex += f"(?=.*{genre})"
+    return regex
+
+# USER INPUT:
+user_id_input = st.text_input('User-ID')
+
+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)
+
+# EXECUTION:
+if st.button("Recommend!"):
+    st.write(get_user_recommendations(user_id_input, number_of_recommendations, genres_regex))

requirements.txt

@@ -1,2 +1,3 @@
 streamlit
-pandas
+pandas
+scikit-learn