From fbe5695edaf0be2f67ef097f705171478e84d02b Mon Sep 17 00:00:00 2001 From: Linlang Date: Tue, 5 Mar 2024 17:01:13 +0800 Subject: [PATCH] download orderbook data --- examples/orderbook_data/README.md | 3 +-- qlib/data/dataset/utils.py | 8 ++++++-- qlib/tests/data.py | 3 +++ 3 files changed, 10 insertions(+), 4 deletions(-) diff --git a/examples/orderbook_data/README.md b/examples/orderbook_data/README.md index 059ee2705..623d84a7c 100644 --- a/examples/orderbook_data/README.md +++ b/examples/orderbook_data/README.md @@ -27,8 +27,7 @@ pip install arctic # NOTE: pip may fail to resolve the right package dependency 2. Please follow following steps to download example data ```bash cd examples/orderbook_data/ -wget http://fintech.msra.cn/stock_data/downloads/highfreq_orderboook_example_data.tar.bz2 -tar xf highfreq_orderboook_example_data.tar.bz2 +python scripts/get_data.py qlib_data --target_dir "~/.qlib/orderbook_data" --name orderbook_data ``` 3. Please import the example data to your mongo db diff --git a/qlib/data/dataset/utils.py b/qlib/data/dataset/utils.py index f19dfe08f..76f3ed404 100644 --- a/qlib/data/dataset/utils.py +++ b/qlib/data/dataset/utils.py @@ -71,11 +71,15 @@ def fetch_df_by_index( if fetch_orig: for slc in idx_slc: if slc != slice(None, None): - return df.loc[pd.IndexSlice[idx_slc],] # noqa: E231 + return df.loc[ + pd.IndexSlice[idx_slc], + ] # noqa: E231 else: # pylint: disable=W0120 return df else: - return df.loc[pd.IndexSlice[idx_slc],] # noqa: E231 + return df.loc[ + pd.IndexSlice[idx_slc], + ] # noqa: E231 def fetch_df_by_col(df: pd.DataFrame, col_set: Union[str, List[str]]) -> pd.DataFrame: diff --git a/qlib/tests/data.py b/qlib/tests/data.py index f6bd78090..43c75c83e 100644 --- a/qlib/tests/data.py +++ b/qlib/tests/data.py @@ -183,6 +183,9 @@ class GetData: def _get_file_name_with_version(qlib_version, dataset_version): dataset_version = "v2" if dataset_version is None else dataset_version file_name_with_version = f"{dataset_version}/{name}_{region.lower()}_{interval.lower()}_{qlib_version}.zip" + file_name_with_version = ( + "highfreq_orderbook_example_data.zip" if name == "orderbook_data" else file_name_with_version + ) return file_name_with_version file_name = _get_file_name_with_version(qlib_version, dataset_version=version)