def make(T):
log_tr = log[log.order_number_rev>T]
# dow
dow = pd.crosstab(log_tr.user_id, log_tr.order_dow).add_prefix('user_dow_freq_')
dow_ = pd.crosstab(log_tr.user_id, log_tr.order_dow, normalize='index').add_prefix('user_dow_norm_')
# timezone
timezone = pd.crosstab(log_tr.user_id, log_tr.timezone).add_prefix('user_timezone_freq_')
timezone_ = pd.crosstab(log_tr.user_id, log_tr.timezone, normalize='index').add_prefix('user_timezone_norm_')
# dow * timezone
dow_tz = pd.crosstab(log_tr.user_id, log_tr.dow_tz).add_prefix('user_dow-tz_freq_')
dow_tz_ = pd.crosstab(log_tr.user_id, log_tr.dow_tz, normalize='index').add_prefix('user_dow-tz_norm_')
tab = pd.concat([dow, dow_, timezone, timezone_, dow_tz, dow_tz_], axis=1)
tab.reset_index().to_pickle('../feature/trainT-{}/f103_user.p'.format(T))
评论列表
文章目录