get some error in example/rl_order_execution

❓ Questions and Help

We sincerely suggest you to carefully read the documentation of our library as well as the official paper. After that, if you still feel puzzled, please describe the question clearly under this issue.

in examples/rl_order_execution/scripts/gen_training_orders.py, I got two error:

df["date"] = df["datetime"].dt.date.astype("datetime64")

this will throw

TypeError: Casting to unit-less dtype 'datetime64' is not supported. Pass e.g. 'datetime64[ns]' instead.

and after I fix this problem, got another one

order_all = pd.DataFrame(df.groupby(level=(2, 0), group_keys=False).mean().dropna())

IndexError: Too many levels: Index has only 2 levels, not 3

and I change this code to

order_all = pd.DataFrame(df.groupby(level=(1, 0), group_keys=False).mean().dropna())

when traing model, get this error

Traceback (most recent call last):
  File "/opt/anaconda3/envs/qlib38/lib/python3.8/threading.py", line 932, in _bootstrap_inner
    self.run()
  File "/opt/anaconda3/envs/qlib38/lib/python3.8/threading.py", line 870, in run
    self._target(*self._args, **self._kwargs)
  File "/opt/anaconda3/envs/qlib38/lib/python3.8/site-packages/qlib/rl/utils/data_queue.py", line 181, in _producer
    for data in dataloader:
  File "/opt/anaconda3/envs/qlib38/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in __next__
    data = self._next_data()
  File "/opt/anaconda3/envs/qlib38/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 561, in _next_data
    data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
  File "/opt/anaconda3/envs/qlib38/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 46, in fetch
    data = self.dataset[possibly_batched_index]
  File "/opt/anaconda3/envs/qlib38/lib/python3.8/site-packages/qlib/rl/contrib/train_onpolicy.py", line 80, in __getitem__
    stock_id=row["instrument"],
  File "/opt/anaconda3/envs/qlib38/lib/python3.8/site-packages/pandas/core/series.py", line 1007, in __getitem__
    return self._get_value(key)
  File "/opt/anaconda3/envs/qlib38/lib/python3.8/site-packages/pandas/core/series.py", line 1116, in _get_value
    loc = self.index.get_loc(label)
  File "/opt/anaconda3/envs/qlib38/lib/python3.8/site-packages/pandas/core/indexes/base.py", line 3655, in get_loc
    raise KeyError(key) from err
KeyError: 'instrument'

So how can we get this example run?

Env

• python 3.8
• qlib 0.9.7

Start by reproducing the failures in examples/rl_order_execution/scripts/gen_training_orders.py with the reported Python and qlib versions. Inspect the dataframe index levels and columns around the date conversion, groupby, and train_onpolicy data loading. Done means the example completes training without the reported datetime, index-level, or missing-instrument errors.