import pandas as pd
df = pd.read_csv('jams.tsv', sep = '\t', error_bad_lines=False)
df
df1 = df['user_id']
df_userid = pd.Series(data=df1, name='Series')
df_userid
df_userid.sample(1000)
sample_df = df_userid.sample(1000)
sample_df = sample_df.to_frame('user_id')
df2 = df[['jam_id', 'user_id', 'artist', 'title']]
df2
df_merge = pd.merge(sample_df, df2, on = 'user_id' )
df_merge = df_merge.drop('jam_id', axis=1)
df_merge
df_merge['song_and_artist'] = df_merge['title'] + ', by ' + df_merge['artist']
df_merge = df_merge.drop(['artist', 'title'], axis=1)
df_merge
df_merge.to_csv('jam-sample.csv', header=True)
