updated files to newest version

pages/1 - Popularity-Based Recommender.py

@@ -18,23 +18,11 @@ movies.loc[lambda df: df["title"].str.contains(", A", regex=True), 'title'] = mo
 
 # INSTRUCTIONS:
 st.title("Popularity-Based Recommender")
-st.write("""
-### Instructions
-Move the slider to the desired number of recommendations you wish to receive.  
-  
-__Optional__: You can receive links for popular streaming services for each  recommendation (if available) by selecting in your countrycode.  
-Leave this field empty if you don't want to get streaming links.  
-  
-__Optional__: You can narrow down the recommendations by picking one or several genre(s).  
-However, the more genres you choose, the fewer movies will be recommended.
-  
-Afterwards, simply click the "Get Recommendations" button to receive recommendations based on the most popular movies in our database.  
-""")
 
 # FUNCTIONS:
 
 def get_popular_recommendations(n, genres):
-    return (
+    recommendations = (
         ratings
             .groupby('movieId')
             .agg(avg_rating = ('rating', 'mean'), num_ratings = ('rating', 'count'))
@@ -44,7 +32,9 @@ def get_popular_recommendations(n, genres):
             .sort_values('combined_rating', ascending=False)
             .head(n)
             [['title', 'avg_rating', 'genres']]
+            .rename(columns= {'title': 'Movie Title', 'avg_rating': 'Average Rating', 'genres': 'Genres'}, inplace = True)
     )
+    return recommendations
 
 def get_popular_recommendations_streaming(n, genres, country, url, headers):
     recommendations = (
@@ -81,7 +71,9 @@ def get_popular_recommendations_streaming(n, genres, country, url, headers):
         for streaming_service in streaming_info['streamingInfo']:
             recommendations_ids.loc[recommendations_ids['imdbId'] == id, 'Streaming Availability'] += f"{streaming_service}: {streaming_info['streamingInfo'][streaming_service][country]['link']} \n" 
 
-    return recommendations_ids[['title', 'genres', 'Streaming Availability']]
+    recommendations_ids.rename(columns= {'title': 'Movie Title', 'genres': 'Genres'}, inplace = True)
+
+    return recommendations_ids[['Movie Title', 'Genres', 'Streaming Availability']]
 
 def transform_genre_to_regex(genres):
     regex = ""
@@ -90,13 +82,25 @@ def transform_genre_to_regex(genres):
     return regex
 
 # USER INPUT:
+
+st.write("""
+Move the slider to the desired number of recommendations you wish to receive.  
+""")
 number_of_recommendations = st.slider("Number of recommendations", 1, 10, 5)
 
+st.write("""
+__Optional__: You can narrow down the recommendations by picking one or several genre(s).  
+However, the more genres you choose, the fewer movies will be recommended.
+""")
 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)
 
-streaming_country = st.selectbox('Optional: Country for streaming information', ('de', 'us'))
+st.write("""
+__Optional__: You can receive links for popular streaming services for each  recommendation (if available) by selecting your countrycode.  
+Select none if you don't want to get streaming links.  
+""")
+streaming_country = st.selectbox('Optional: Country for streaming information', ('none', 'de', 'us'))
 
 # API INFORMATION:
 url = "https://streaming-availability.p.rapidapi.com/get/basic"
@@ -108,7 +112,8 @@ headers = {
 # EXECUTION:
 
 if st.button("Get Recommendations"):
-    if streaming_country == '':
+    if streaming_country == 'none':
         st.write(get_popular_recommendations(number_of_recommendations, genres_regex))
     else: 
+        st.write("Double-click on a Streaming-Availability cell to see all options.")
         st.write(get_popular_recommendations_streaming(number_of_recommendations, genres_regex, streaming_country, url, headers))

pages/2 - Similarity-Based Recommender.py

@@ -28,21 +28,8 @@ similarities_movies = pd.DataFrame(cosine_similarity(movie_user_matrix),
                                   index=movie_user_matrix.index,
                                   columns=movie_user_matrix.index)
 
-# INSTRUCTIONS:
+# TITLE:
 st.title("User-Based Recommender")
-st.write("""
-### Instructions
-Type in the title of a movie for which you would like to receive similar recommendations.  
-Move the slider to the desired number of recommendations you wish to receive.  
-  
-__Optional__: You can receive links for popular streaming services for each  recommendation (if available) by selecting in your countrycode.  
-Leave this field empty if you don't want to get streaming links.  
-  
-__Optional__: You can narrow down the recommendations by picking one or several genre(s).  
-However, the more genres you choose, the fewer movies will be recommended.
-
-Afterwards, simply click the "Get Recommendations" button to receive recommendations that are most similar to the given movie.  
-""")
 
 # FUNCTIONS:
 
@@ -61,6 +48,8 @@ def get_similar_recommendations(movie_title, n, genres):
             .head(n)
             [['title', 'genres']]
             )
+            
+    recommendations.rename(columns= {'title': 'Movie Title', 'genres': 'Genres'}, inplace = True)
 
     return recommendations
 
@@ -99,7 +88,9 @@ def get_similar_recommendations_streaming(movie_title, n, genres, country, url,
         for streaming_service in streaming_info['streamingInfo']:
             recommendations_ids.loc[recommendations_ids['imdbId'] == id, 'Streaming Availability'] += f"{streaming_service}: {streaming_info['streamingInfo'][streaming_service][country]['link']} \n" 
 
-        return recommendations_ids[['title', 'genres', 'Streaming Availability']]
+    recommendations_ids.rename(columns= {'title': 'Movie Title', 'genres': 'Genres'}, inplace = True)
+
+    return recommendations_ids[['Movie Title', 'Genres', 'Streaming Availability']]
 
 
 def transform_genre_to_regex(genres):
@@ -121,17 +112,33 @@ def find_movie_title(user_input):
     
     return result[0][0]
 
+
 # USER INPUT:
+st.write("""
+Type in the name of your movie.
+""")
 movie_title_raw = st.text_input('Movie Title')
 movie_title = find_movie_title(movie_title_raw)
 
+st.write("""
+Move the slider to the desired number of recommendations you wish to receive.  
+""")
 number_of_recommendations = st.slider("Number of recommendations", 1, 10, 5)
 
+st.write("""
+__Optional__: You can narrow down the recommendations by picking one or several genre(s).  
+However, the more genres you choose, the fewer movies will be recommended.
+""")
 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)
 
-streaming_country = st.selectbox('Optional: Country for streaming information', ('de', 'us'))
+st.write("""
+__Optional__: You can receive links for popular streaming services for each  recommendation (if available) by selecting your countrycode.  
+Select none if you don't want to get streaming links.  
+""")
+streaming_country = st.selectbox('Optional: Country for streaming information', ('none', 'de', 'us'))
+
 
 # API INFORMATION:
 url = "https://streaming-availability.p.rapidapi.com/get/basic"
@@ -143,7 +150,7 @@ headers = {
 
 # EXECUTION:
 if st.button("Get Recommendations"):
-    if streaming_country == '':
+    if streaming_country == 'none':
         st.write(get_similar_recommendations(movie_title, number_of_recommendations, genres_regex))
     else:
         st.write("Double-click on the Streaming-Availability column to see all links.")

pages/3 - User-Based Recommender.py

@@ -1,89 +0,0 @@
-import streamlit as st
-import pandas as pd
-from sklearn.metrics.pairwise import cosine_similarity
-import re
-import requests
-
-# DATA:
-movies = pd.read_csv('https://raw.githubusercontent.com/tobiasaurer/movie-recommender-streamlit/main/data/movies.csv')
-ratings = pd.read_csv('https://raw.githubusercontent.com/tobiasaurer/movie-recommender-streamlit/main/data/ratings.csv')
-links = pd.read_csv('https://raw.githubusercontent.com/tobiasaurer/movie-recommender-streamlit/main/data/links.csv')
-
-# clean titles column by moving "The" and "A" to the beginning of the string
-# this makes it more searchable for users
-movies.loc[lambda df: df["title"].str.contains(", The", regex=True), 'title'] = 'The ' + movies['title']
-movies.loc[lambda df: df["title"].str.contains(", The", regex=True), 'title'] = movies['title'].str.replace(", The", '', regex=True)
-
-movies.loc[lambda df: df["title"].str.contains(", A", regex=True), 'title'] = 'A ' + movies['title']
-movies.loc[lambda df: df["title"].str.contains(", A", regex=True), 'title'] = movies['title'].str.replace(", A", '', regex=True)
-
-# 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.  
-  
-__Optional__: You can narrow down the recommendations by picking one or several genre(s).  
-However, the more genres you choose, the fewer movies will be recommended.
-  
-Afterwards, simply click the "Get Recommendations" button to receive recommendations that are most suitable for the given user.  
-""")
-
-# 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)
-            .merge(movies, how= 'left', left_index = True, right_on = 'title')
-            [lambda df: df["genres"].str.contains(genres, regex=True)]
-            .head(n)
-    )
-
-    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("Get Recommendations"):
-    st.write(get_user_recommendations(user_id_input, number_of_recommendations, genres_regex))