Spaces:
Runtime error
Runtime error
File size: 7,653 Bytes
8b2ad1d bf962cf 8b2ad1d bf962cf 8b2ad1d 4b93540 8b2ad1d c0503dc 8b2ad1d 4b93540 8b2ad1d ea43f50 8b2ad1d 4b93540 8b2ad1d c0503dc 8b2ad1d 4b93540 bf962cf 4b93540 bf962cf 5ee2e22 bf962cf c0503dc bf962cf 8b2ad1d c0503dc 8b2ad1d c0503dc 8b2ad1d c0503dc 8b2ad1d 4b93540 c0503dc 8b2ad1d c0503dc bf962cf e6c0240 bf962cf 8b2ad1d c0503dc 1b3c4fd bf962cf 4b93540 1b3c4fd 4b93540 1b3c4fd 4b93540 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 |
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)
# extract year from title and store it in new column
movies= movies.assign(year = lambda df_ : df_['title'].replace(r'(.*)\((\d{4})\)', r'\2', regex= True))
movies.year = pd.to_numeric(movies.year, errors= 'coerce').fillna(0).astype('int')
# create "database" to use for recommendations
movie_user_matrix = (
ratings
.merge(movies, on='movieId')[['title', 'rating', 'userId']]
.pivot_table(index='title', columns='userId', values='rating')
.fillna(0)
)
similarities_movies = pd.DataFrame(cosine_similarity(movie_user_matrix),
index=movie_user_matrix.index,
columns=movie_user_matrix.index)
# TITLE:
st.title("User-Based Recommender")
# FUNCTIONS:
def get_similar_recommendations(movie_title, n, genres, time_range):
# select similarity for chosen movie
similarities = pd.DataFrame(
(similarities_movies.query("index != @movie_title")[movie_title] / sum(similarities_movies.query("index != @movie_title")[movie_title]))
.sort_values(ascending= False))
# exclude genres if necessary and return the n movies with the highest similarity
recommendations = (
similarities
.merge(movies, how= 'left', left_index = True, right_on = 'title')
[lambda df: df["genres"].str.contains(genres, regex=True)]
.loc[lambda df : ((df['year'] >= time_range[0]) & ( df['year'] <= time_range[1]))]
.head(n)
[['title', 'genres']]
)
recommendations.rename(columns= {'title': 'Movie Title', 'genres': 'Genres'}, inplace = True)
return recommendations
def get_similar_recommendations_streaming(movie_title, n, genres, time_range, country, url, headers):
# select similarity for chosen movie
similarities = pd.DataFrame(
(similarities_movies.query("index != @movie_title")[movie_title] / sum(similarities_movies.query("index != @movie_title")[movie_title]))
.sort_values(ascending= False))
# exclude genres if necessary and return the n movies with the highest similarity
recommendations = (
similarities
.merge(movies, how= 'left', left_index = True, right_on = 'title')
[lambda df: df["genres"].str.contains(genres, regex=True)]
.loc[lambda df : ((df['year'] >= time_range[0]) & ( df['year'] <= time_range[1]))]
.head(n)
[['title', 'genres', 'movieId']]
)
# merge recommendations with links df to get imdbIds for the API calls
recommendations_ids = recommendations.merge(links, how = 'left', on = 'movieId')[['title', 'genres', 'imdbId']]
recommendations_ids['imdbId'] = 'tt0' + recommendations_ids['imdbId'].astype('str')
imdb_ids = list(recommendations_ids['imdbId'])
# create new column for streaming links
recommendations_ids['Streaming Availability'] = ""
# loop through imdb_ids to make one api call for each to get available streaming links
for id in imdb_ids:
# make api call
try:
querystring = {"country":country,"imdb_id":id,"output_language":"en"}
response = requests.request("GET", url, headers=headers, params=querystring)
streaming_info = response.json()
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"
except:
continue
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 = ""
for genre in genres:
regex += f"(?=.*{genre})"
return regex
def find_movie_title(user_input):
title_list = movies.title.unique()
r = re.compile(f".*{user_input}.*")
result = []
for title in title_list:
match = r.findall(title)
if match:
result.append(match)
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("""
Move the sliders to choose a timeperiod for your recommendations.
""")
time_range = st.slider('Time-period:', min_value=1900, max_value=2018, value=(1900, 2018), step=1)
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)
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"
headers = {
"X-RapidAPI-Key": st.secrets["api_key"],
"X-RapidAPI-Host": "streaming-availability.p.rapidapi.com"
}
# EXECUTION:
if st.button("Get Recommendations"):
if streaming_country == 'none':
st.write(get_similar_recommendations(movie_title, number_of_recommendations, genres_regex, time_range))
else:
try:
recommendations = get_similar_recommendations_streaming(movie_title, number_of_recommendations, genres_regex, time_range, streaming_country, url, headers)
st.write("Double-click on a Streaming-Availability cell to see all options.", recommendations)
except:
recommendations = get_similar_recommendations(movie_title, number_of_recommendations, genres_regex, time_range)
st.write('Error: Streaming information could not be gathered. Providing output without streaming availability instead.', recommendations) |