def _normalize(file_path: Path):
columns = ["open", "close", "high", "low", "volume"]
df = pd.read_csv(file_path)
df.set_index("date", inplace=True)
df.index = pd.to_datetime(df.index)
df = df[~df.index.duplicated(keep="first")]
# using China stock market data calendar
df = df.reindex(pd.Index(get_calendar_list()))
df.sort_index(inplace=True)
df.loc[(df["volume"] <= 0) | np.isnan(df["volume"]),
set(df.columns) - {"symbol"}] = np.nan
df["factor"] = df["adjclose"] / df["close"]
for _col in columns:
if _col == "volume":
df[_col] = df[_col] / df["factor"]
else:
df[_col] = df[_col] * df["factor"]
_tmp_series = df["close"].fillna(method="ffill")
df["change"] = _tmp_series / _tmp_series.shift(1) - 1
columns += ["change", "factor"]
df.loc[(df["volume"] <= 0) | np.isnan(df["volume"]),
columns] = np.nan
df.index.names = ["date"]
df.loc[:,
columns].to_csv(self.normalize_dir.joinpath(file_path.name))
def calendar_list(self) -> list:
"""get history trading date
Returns
-------
"""
return get_calendar_list(bench=True)
def calendar_list(self) -> list:
"""get history trading date
Returns
-------
"""
return get_calendar_list(bench_code=self.index_name.upper())
def calendar_list(self) -> List[pd.Timestamp]:
"""get history trading date
Returns
-------
calendar list
"""
return get_calendar_list(bench_code=self.index_name.upper())
def calendar_list(self) -> List[pd.Timestamp]:
"""get history trading date
Returns
-------
calendar list
"""
_calendar = getattr(self, "_calendar_list", None)
if not _calendar:
_calendar = get_calendar_list(bench_code=self.index_name.upper())
setattr(self, "_calendar_list", _calendar)
return _calendar
def calendar_list(self) -> List[pd.Timestamp]:
"""get history trading date
Returns
-------
calendar list
"""
_calendar_list = getattr(self, "_calendar_list", None)
if _calendar_list is None:
_calendar_list = list(filter(lambda x: x >= self.bench_start_date, get_calendar_list("US_ALL")))
setattr(self, "_calendar_list", _calendar_list)
return _calendar_list
def _get_calendar_list(self):
return get_calendar_list("ALL")
def _get_1d_calendar_list(self) -> Iterable[pd.Timestamp]:
return get_calendar_list("ALL")
def _get_calendar_list(self) -> Iterable[pd.Timestamp]:
# TODO: from MSN
return get_calendar_list("ALL")
def _get_1d_calendar_list(self):
return get_calendar_list("IN_ALL")
def _get_calendar_list(self):
# TODO: from MSN
return get_calendar_list("ALL")
