010_streak.py 文件源码

def multi(uid):
    tmp = log[log.user_id==uid]
    ct = pd.crosstab(tmp.order_number, tmp.product_id).reset_index().set_index('order_number')
    li = []
    for pid in ct.columns:
        streak = 0
        sw_odr = False
        for onb,odr in enumerate(ct[pid].values):
            onb+=1
            if sw_odr == False and odr == 1:
                sw_odr = True
                streak = 1
                li.append([uid, pid, onb, streak])
                continue
            if sw_odr == True:
                if odr == 1 and streak>0:
                    streak += 1
                    li.append([uid, pid, onb, streak])
                elif odr == 1 and streak<=0:
                    streak = 1
                    li.append([uid, pid, onb, streak])
                elif odr == 0 and streak>0:
                    streak = 0
                    li.append([uid, pid, onb, streak])
                elif odr == 0 and streak<=0:
                    streak -= 1
                    li.append([uid, pid, onb, streak])
    return pd.DataFrame(li, columns=['user_id', 'product_id', 'order_number', 'streak'])