我有以下数据框：
id my_year my_month waiting_time target
001 2018 1 95 1
002 2018 1 3 3
003 2018 1 4 0
004 2018 1 40 1
005 2018 2 97 1
006 2018 2 3 3
007 2018 3 4 0
008 2018 3 40 1
我想分组my_year和my_month，然后在每个组中我想基于
my_rate
(# of records with waiting_time <= 90 and target = 1)/ total_records in the group
即。我期待输出像：
my_year my_month my_rate
2018 1 0.25
2018 2 0.0
2018 3 0.5
我编写了以下代码来计算所需的值my_rate：
def my_rate(data):
waiting_time_list = data['waiting_time']
target_list = data['target']
total = len(data)
my_count = 0
for i in range(len(data)):
if total_waiting_time_list[i] <= 90 and target_list[i] == 1:
my_count += 1
rate = float(my_count)/float(total)
return rate
df.groupby(['my_year','my_month']).apply(my_rate)
但是，我收到以下错误：
KeyError 0
KeyErrorTraceback (most recent call last)
<ipython-input-29-5c4399cefd05> in <module>()
17
---> 18 df.groupby(['my_year','my_month']).apply(my_rate)
/opt/conda/envs/python2/lib/python2.7/site-packages/pandas/core/groupby.pyc in apply(self, func, *args, **kwargs)
714 # ignore SettingWithCopy here in case the user mutates
715 with option_context('mode.chained_assignment', None):
--> 716 return self._python_apply_general(f)
717
718 def _python_apply_general(self, f):
/opt/conda/envs/python2/lib/python2.7/site-packages/pandas/core/groupby.pyc in _python_apply_general(self, f)
718 def _python_apply_general(self, f):
719 keys, values, mutated = self.grouper.apply(f, self._selected_obj,
--> 720 self.axis)
721
722 return self._wrap_applied_output(
/opt/conda/envs/python2/lib/python2.7/site-packages/pandas/core/groupby.pyc in apply(self, f, data, axis)
1727 # group might be modified
1728 group_axes = _get_axes(group)
-> 1729 res = f(group)
1730 if not _is_indexed_like(res, group_axes):
1731 mutated = True
<ipython-input-29-5c4399cefd05> in conversion_rate(data)
8 #print total_waiting_time_list[i], target_list[i]
9 #print i, total_waiting_time_list[i], target_list[i]
---> 10 if total_waiting_time_list[i] <= 90:# and target_list[i] == 1:
11 convert_90_count += 1
12 #print 'convert ', convert_90_count
/opt/conda/envs/python2/lib/python2.7/site-packages/pandas/core/series.pyc in __getitem__(self, key)
599 key = com._apply_if_callable(key, self)
600 try:
--> 601 result = self.index.get_value(self, key)
602
603 if not is_scalar(result):
/opt/conda/envs/python2/lib/python2.7/site-packages/pandas/core/indexes/base.pyc in get_value(self, series, key)
2426 try:
2427 return self._engine.get_value(s, k,
-> 2428 tz=getattr(series.dtype, 'tz', None))
2429 except KeyError as e1:
2430 if len(self) > 0 and self.inferred_type in ['integer', 'boolean']:
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value (pandas/_libs/index.c:4363)()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value (pandas/_libs/index.c:4046)()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc (pandas/_libs/index.c:5085)()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item (pandas/_libs/hashtable.c:13913)()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item (pandas/_libs/hashtable.c:13857)()
KeyError: 0
知道我在这里做错了吗？我该如何解决？谢谢！
答案 0 :(得分：1)
我相信更好的是每组使用mean布尔掩码：
def my_rate(x):
return ((x['waiting_time'] <= 90) & (x['target'] == 1)).mean()
df = df.groupby(['my_year','my_month']).apply(my_rate).reset_index(name='my_rate')
print (df)
my_year my_month my_rate
0 2018 1 0.25
1 2018 2 0.00
2 2018 3 0.50
知道我在这里做错了吗？
问题是waiting_time_list而target_list不是list，而是Series：
waiting_time_list = data['waiting_time']
target_list = data['target']
print (type(waiting_time_list))
<class 'pandas.core.series.Series'>
print (type(target_list))
<class 'pandas.core.series.Series'>
因此，如果想要将其编入索引失败，因为在第二组中是索引4,5，而不是0,1。
if waiting_time_list[i] <= 90 and target_list[i] == 1:
为避免将Series转换为list：
waiting_time_list = data['waiting_time'].tolist()
target_list = data['target'].tolist()