alphalens.utils 返回 KeyError： "None of [DatetimeIndex (['<dates>, dtype='datetime64[ns]', fr

Question

我正在尝试对10K财务报表进行情绪分析，但使用以下操作时遇到错误：

data = al.utils.get_clean_factor_and_forward_returns(cs_df.stack(), pricing.loc[cs_df.index], quantiles=5, bins=None, periods=[1])

当我print(data):时，它返回以下KeyError

KeyError: "None of [DatetimeIndex(['2012-01-01', '2013-01-01', '2014-01-01', '2015-01-01', '2016-01-01', '2017-01-01', '2018-01-01', '2019-01-01'], dtype='datetime64[ns]', freq=None)] are in the [index]"

相关代码块：

import alphalens as al
factor_data = {}
skipped_sentiments = []
for sentiment in sentiments:
cs_df = cosine_similarities_df[(cosine_similarities_df['sentiment'] == sentiment)]
cs_df = cs_df.pivot(index='date', columns='ticker', values='value')
try:
data = al.utils.get_clean_factor_and_forward_returns(cs_df.stack(), pricing.loc[cs_df.index], quantiles=5, bins=None, periods=[1])
factor_data[sentiment] = data
except:
skipped_sentiments.append(sentiment)

当运行时，它只将我所有的情绪打印为跳过，就像它跳过for循环的except:部分一样。

枢轴操作后，我的DataFramecs_df如下所示：

ticker           AMZN
date                 
2012-01-01 0.99706919
2013-01-01 0.99931987
2014-01-01 0.99841510
2015-01-01 0.99805389
2016-01-01 0.99884780
2017-01-01 0.96819148
2018-01-01 0.99957861
2019-01-01 0.99767198

在for循环中，我尝试使用日期索引创建一个新列，并将其映射到al.utils中，其中pricing.loc[cs_df.index]更改为pricing.loc[cs_df.date]行，但使用cs_df['date'] = cs_df.index无效我还尝试过用删除列名和索引名

cs_df.columns.name = None
cs_df.index.name = None

重命名列和索引会产生以下数据帧，但仍然返回相同的错误

AMZN
2012-01-01 0.99706919
2013-01-01 0.99931987
2014-01-01 0.99841510
2015-01-01 0.99805389
2016-01-01 0.99884780
2017-01-01 0.96819148
2018-01-01 0.99957861
2019-01-01 0.99767198

用cs_df = cs_df.reset_index(drop=True)重置索引也没有帮助，只是取消了我的日期。可以肯定的是，我使用al.utils操作的方式存在问题，我不认为枢轴会导致问题。有什么想法吗？感谢您的帮助和时间！

FULL TRACEBACK
---
Traceback (most recent call last):
File "~FinancialReportSentimentAnalysis.py", line 514, in <module>
print(al.utils.get_clean_factor_and_forward_returns(cs_df.stack(), pricing.loc[cs_df.index], quantiles=5, bins=None, periods=[1]))
File "~opt/anaconda3/envs/workspace/lib/python3.8/site-packages/pandas/core/indexing.py", line 879, in __getitem__
return self._getitem_axis(maybe_callable, axis=axis)
File "~opt/anaconda3/envs/workspace/lib/python3.8/site-packages/pandas/core/indexing.py", line 1099, in _getitem_axis
return self._getitem_iterable(key, axis=axis)
File "~opt/anaconda3/envs/workspace/lib/python3.8/site-packages/pandas/core/indexing.py", line 1037, in _getitem_iterable
keyarr, indexer = self._get_listlike_indexer(key, axis, raise_missing=False)
File "~opt/anaconda3/envs/workspace/lib/python3.8/site-packages/pandas/core/indexing.py", line 1254, in _get_listlike_indexer
self._validate_read_indexer(keyarr, indexer, axis, raise_missing=raise_missing)
File "~opt/anaconda3/envs/workspace/lib/python3.8/site-packages/pandas/core/indexing.py", line 1298, in _validate_read_indexer
raise KeyError(f"None of [{key}] are in the [{axis_name}]")
KeyError: "None of [DatetimeIndex(['2012-01-01', '2013-01-01', '2014-01-01', '2015-01-01', '2016-01-01', '2017-01-01', '2018-01-01', '2019-01-01'], dtype='datetime64[ns]', name='date', freq=None)] are in the [index]"
Process finished with exit code 1

Answer 1

对于任何偶然发现这一点的人。

问题在于将财务文档中的日期与定价数据表中的日期进行匹配。当我试图匹配一年中的第一天(元旦(，市场关闭，而这一天没有定价数据时，不可能匹配。因此，我将数据更改为每月一次，以获得YYYY年1月1日的汇总价格数据。

pricing.loc[cs_df.index]是问题的根源。