double ensemble training bug after recent updates

[2young-2simple-sometimes-naive]

🐛 Bug Description

[38178:MainThread](2022-02-23 02:40:54,390) ERROR - qlib.workflow - [utils.py:41] - An exception has been raised[KeyError: 0].
  File "./workflow.py", line 167, in <module>
    model.fit(dataset)
  File "/xxxxxxxxxx/.venv/lib/python3.8/site-packages/pyqlib-0.8.3.99-py3.8-linux-x86_64.egg/qlib/contrib/model/double_ensemble.py", line 95, in fit
    weights = self.sample_reweight(loss_curve, loss_values, k + 1)
  File "/xxxxxxxxxx/.venv/lib/python3.8/site-packages/pyqlib-0.8.3.99-py3.8-linux-x86_64.egg/qlib/contrib/model/double_ensemble.py", line 163, in sample_reweight
    weights[h["bins"] == b] = 1.0 / (self.decay**k_th * h_avg[i_b] + 0.1)
  File "/xxxxxxxxxx/.venv/lib/python3.8/site-packages/pandas/core/series.py", line 958, in __getitem__
    return self._get_value(key)
  File "/xxxxxxxxxx/.venv/lib/python3.8/site-packages/pandas/core/series.py", line 1069, in _get_value
    loc = self.index.get_loc(label)
  File "/xxxxxxxxxx/.venv/lib/python3.8/site-packages/pandas/core/indexes/base.py", line 3619, in get_loc
    casted_key = self._maybe_cast_indexer(key)
  File "/xxxxxxxxxx/.venv/lib/python3.8/site-packages/pandas/core/indexes/category.py", line 471, in _maybe_cast_indexer
    return self._data._unbox_scalar(key)
  File "/xxxxxxxxxx/.venv/lib/python3.8/site-packages/pandas/core/arrays/categorical.py", line 1956, in _unbox_scalar
    code = self.categories.get_loc(key)
  File "/xxxxxxxxxx/.venv/lib/python3.8/site-packages/pandas/core/indexes/interval.py", line 637, in get_loc
    raise KeyError(key)

The setup for double ensemble is the default setup (workflow_config_doubleensemble_Alpha158.yaml)
This bug does not appear after switch model to lightgbm.

Environment

Linux
x86_64
Linux-4.18.0-147.el8.x86_64-x86_64-with-glibc2.2.5
#1 SMP Wed Dec 4 21:51:45 UTC 2019

Python version: 3.8.6 (default, Oct 22 2020, 17:03:03) [GCC 9.3.0]

Qlib version: 0.8.3.99
numpy==1.22.2
pandas==1.4.1
scipy==1.8.0
requests==2.27.1
sacred==0.8.2
python-socketio==5.5.2
redis==4.2.0rc1
python-redis-lock==3.7.0
schedule==1.1.0
cvxpy==1.1.18
hyperopt==0.1.2
fire==0.4.0
statsmodels==0.13.2
xlrd==2.0.1
plotly==5.6.0
matplotlib==3.5.1
tables==3.7.0
pyyaml==5.4.1
mlflow==1.23.1
tqdm==4.62.3
loguru==0.6.0
lightgbm==3.3.2
tornado==6.1
joblib==1.1.0
fire==0.4.0
ruamel.yaml==0.17.21