liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-15 08:46:56 +08:00
Code Activity

Fix the number of minutes on the first and last trading day of high frequency

Browse Source
This commit is contained in:
zhupr
2021-01-26 23:20:35 +08:00
committed by you-n-g
parent 263ccdfe6f
commit 7f9216dc90
1 changed files with 9 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
scripts/data_collector/yahoo/collector.py
View File

@@ -472,7 +472,14 @@ class YahooNormalize:
df.index = pd.to_datetime(df.index) df.index = pd.to_datetime(df.index)
df = df[~df.index.duplicated(keep="first")] df = df[~df.index.duplicated(keep="first")]
if calendar_list is not None: if calendar_list is not None:
df = df.reindex(pd.DataFrame(index=calendar_list).loc[df.index.min() : df.index.max()].index) df = df.reindex(
pd.DataFrame(index=calendar_list)
.loc[
pd.Timestamp(df.index.min()).date() : pd.Timestamp(df.index.max()).date()
+ pd.Timedelta(hours=23, minutes=59)
]
.index
)
df.sort_index(inplace=True) df.sort_index(inplace=True)
df.loc[(df["volume"] <= 0) | np.isnan(df["volume"]), set(df.columns) - {symbol_field_name}] = np.nan df.loc[(df["volume"] <= 0) | np.isnan(df["volume"]), set(df.columns) - {symbol_field_name}] = np.nan
_tmp_series = df["close"].fillna(method="ffill") _tmp_series = df["close"].fillna(method="ffill")
@@ -614,6 +621,7 @@ class YahooNormalize1min(YahooNormalize, ABC):
data_1d = YahooData.get_data_from_remote(self.symbol_to_yahoo(symbol), interval="1d", start=_start, end=_end) data_1d = YahooData.get_data_from_remote(self.symbol_to_yahoo(symbol), interval="1d", start=_start, end=_end)
if data_1d is None or data_1d.empty: if data_1d is None or data_1d.empty:
df["factor"] = 1 df["factor"] = 1
# TODO: np.nan or 1 or 0
df["paused"] = np.nan df["paused"] = np.nan
else: else:
data_1d = self.data_1d_obj.normalize(data_1d) # type: pd.DataFrame data_1d = self.data_1d_obj.normalize(data_1d) # type: pd.DataFrame