import pandas as pd user_id_df = pd.read_csv("jams.tsv",sep='\t', usecols=['user_id'], error_bad_lines=False) user_id_df

len(user_id_df)

user_id_df = user_id_df.drop_duplicates() len(user_id_df)

sample_user_id = user_id_df.sample(n=2000) sample_user_id

artist_title_df = pd.read_csv("jams.tsv",sep='\t', usecols=['user_id', 'artist', 'title'], error_bad_lines=False) artist_title_df

artist_dict = dict( zip(artist_title_df.user_id, artist_title_df.artist) ) title_dict = dict( zip(artist_title_df.user_id, artist_title_df.title) ) sample_user_id['artist'] = sample_user_id['user_id'].map(artist_dict) sample_user_id['title'] = sample_user_id['user_id'].map(title_dict) sample_user_id