Hi, thanks for your codes. When I run your codes of the "preprocess_movie_imdb.py" file, it reported that the line 638 "assert len(imdb_id) == 9" was an error.

Then I commented this line and tried to continue run the codes, it reported another bugs as follows:
"

found1652/1681, dropped: 8 (not matched) + 3 (>2 titles)

mapped (director): 12621, # mapped (writer): 12518

Traceback (most recent call last):
File "preprocess_movie_imdb.py", line 682, in
year_diff_thres=4, chosen_title_type_l=["movie", "tvmovie", "tvminiseries", "video"], COS_SIM_THRES=0.3)
File "preprocess_movie_imdb.py", line 664, in match
["writer_id", "name"])
File "preprocess_movie_imdb.py", line 496, in gen_unique_info
unique_l = [[id, people_id2name_dic[id]] for id in unique.values]
File "preprocess_movie_imdb.py", line 496, in
unique_l = [[id, people_id2name_dic[id]] for id in unique_.values]
KeyError: 'nm0799875'
"

Could you help me solve this problem? Or if you have the processed data about Moivelens 10m/20m, could you send them to me? My email is [email protected].