python项目需求报告_Python数据分析-综合项目需求案例

#统计每个用户每个月的消费次数

df_purchase = df.pivot_table(index='user_id',values='order_dt',aggfunc='count',columns='month',fill_value=0) #columns='month' 对 values='order_dt'又做了一次划分

df_purchase.head()

#统计每个用户每个月是否消费，消费记录为1否则记录为0

df_purchase = df_purchase.applymap(lambda x:1 if x > 0 else 0)

df_purchase.head()

#将df_purchase中的原始数据0和1修改为new，unactive......,返回新的df叫做df_purchase_new

#固定算法 修改参数即可用

def active_status(data):

status = []#某个用户每一个月的活跃度

for i in range(18):

#若本月没有消费

if data[i] == 0:

if len(status) > 0:

if status[i-1] == 'unreg':

status.append('unreg')

else:

status.append('unactive')

else:

status.append('unreg')

#若本月消费

else:

if len(status) == 0:

status.append('new')

else:

if status[i-1] == 'unactive':

status.append('return')

elif status[i-1] == 'unreg':

status.append('new')

else:

status.append('active')

return status

pivoted_status = df_purchase.apply(active_status,axis = 1)

pivoted_status.head()

user_id

1 [new, unactive, unactive, unactive, unactive, ...

2 [new, unactive, unactive, unactive, unactive, ...

3 [new, unactive, return, active, unactive, unac...

4 [new, unactive, unactive, unactive, unactive, ...

5 [new, active, unactive, return, active, active...

dtype: object

df_purchase_new = DataFrame(data=pivoted_status.tolist(),index=df_purchase.index,columns=df_purchase.columns)

df_purchase_new.head()