from tqdm import tqdm
from movies_analyzer.RecommendationDataset import RecommendationDataSet
from movies_analyzer.Movies import Movies
from movies_analyzer.Imdb import get_imdb_movie
# download all images from imdb ased on movielens, this is very long query
# for 9000 could take about 6 hours, for all imdb (500,000) could take about 2 weeks.
recommendation_dataset = RecommendationDataSet(movies=Movies())
# all imdb movies
for tmbdid in tqdm(recommendation_dataset.movies.data.index):
tmbdid = tmbdid.replace('tt', '')
get_imdb_movie(tmbdid)
# return top-n movies
movie_ids = [
full_dataset.to_raw_iid(i)
for i in heapq.nlargest(k, candidates, key=candidates.get)
]
return self.movies.get_movie_by_movie_ids(movie_ids)
if __name__ == '__main__':
from movies_recommender.Recommender import test_recommendation
from movies_recommender.RecommenderUserBased import RecommenderUserBased
from movies_analyzer.RecommendationDataset import RecommendationDataSet
from movies_analyzer.Movies import Movies
movies = Movies()
recommendation_dataset = RecommendationDataSet(movies=movies)
recommender = RecommenderUserBased(movies)
assert recommender.__module__[:len('movies_recommender.'
)] == 'movies_recommender.'
test_recommendation(recommender,
recommendation_dataset,
example_items=['arek', 'mateusz'],
anti_test=False)
""" For test only
%load_ext autoreload
%autoreload 2
from filmweb_integrator.fwimdbmerge.filmweb import Filmweb
from filmweb_integrator.fwimdbmerge.merger import Merger, get_json_df
if EXAMPLE_USE_JSON:
logger.warning(f"Load json file: {DATA_STATIC}/{FILMWEB_EXAMPLE_CSV}")
df = get_json_df(read_file(FILMWEB_EXAMPLE_JSON))
logger.warning(f"Write to csv ({len(df)})")
df.to_csv(FILMWEB_EXAMPLE_CSV)
else:
logger.warning(f"Load csv file: {DATA_STATIC}/{FILMWEB_EXAMPLE_CSV}")
df = pd.read_csv(FILMWEB_EXAMPLE_CSV)
logger.warning(f"Write to json ({len(df)})")
with open(FILMWEB_EXAMPLE_JSON, "w", encoding="utf-8") as file_wr:
df.to_json(file_wr, orient='records')
logger.warning("Start merging")
movies = Movies()
merger = Merger(imdb=movies.imdb)
filmweb_df, merge_df = merger.get_data(df)
logger.warning(
f"Save merge.csv Filmweb({len(filmweb_df)}) -> IMDB({len(merge_df)})")
filmweb_df.to_csv(FILMWEB_EXAMPLE_FILMWEB, index=False)
merge_df.to_csv(FILMWEB_EXAMPLE_MERGE, index=True)
movielens_df = movies.merge_imdb_movielens(merge_df)
logger.warning(
f"Save movielens merge IMDB({len(merge_df)}) -> MOVIELENS({len(movielens_df)})"
)
movielens_df.to_csv(FILMWEB_EXAMPLE_MOVIELENS, index=True)
logger.warning(f"Print data ({len(movielens_df)})")