1
0
mirror of https://github.com/microsoft/qlib.git synced 2026-06-06 05:51:17 +08:00
Files
qlib/scripts/data_collector/utils.py
you-n-g de9e13b171 release-0.5.0 (#1)
* init commit

* change the version number

* rich the docs&fix cache docs

* update index readme

* Modify cache class name

* Modify sharpe to information_ratio

* Modify Group- to Group

* add the description of graphical results & fix the backtest docs

* fix docs in details

* update docs

* Update introduction.rst

* Update README.md

* Update introduction.rst

* Update introduction.rst

* Update introduction.rst

* Update installation.rst

* Update installation.rst

* Update initialization.rst

* Update getdata.rst

* Update integration.rst

* Update initialization.rst

* Update getdata.rst

* Update estimator.rst

Modify some typos.

* Update README.md

Modify the typos.

* Update initialization.rst

* Update data.rst

* Update report.rst

* Update estimator.rst

* Update cumulative_return.py

* Update model.rst

* Update rank_label.py

* Update cumulative_return.py

* Update strategy.rst

* Update getdata.rst

* Update backtest.rst

* Update integration.rst

* Update getdata.rst

* Update introduction.rst

* Update introduction.rst

* Update README.md

* Update report.rst

* Update integration.rst

Fix typos

* Update installation.rst

Fix typos

* Update getdata.rst

* Update initialization.rst

Fix typos.

* add quick start docs&fix detials

* fix estimator docs & fix strategy docs

* fix the cahce in data.rst

* update documents

* Fix Corr && Rsquare

* fix data retrival example to csi300 & fix a data bug

* fix filter bug

* Fix data collector

* Modift model args

* add the log & fix README.md\quick.rst

* add enviroment depend & add intoduction of qlib-server online mode

* fix image center fomat & set log_only of docs is True

* fix README.md format

* update data preparation & readme logo image

* get_data support version

* Modify analysis names

* Modify analysis graph

* update report.rst & data.rst

* commmit estimator for merge

* minimal requirements

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update READEME.md

* Update READEME.md

* update estimator

* Fix doc urls

* fix get_data.py docstring

* update test_get_data.py

* Upate docs

* Upate docs

* Upate docs

Co-authored-by: bxdd <bxddream@gmail.com>
Co-authored-by: zhupr <zhu.pengrong@foxmail.com>
Co-authored-by: Wendi Li <wendili.academic@qq.com>
Co-authored-by: Dingsu Wang <dingsu.wang@gmail.com>
Co-authored-by: bxdd <45119470+bxdd@users.noreply.github.com>
Co-authored-by: cslwqxx <cslwqxx@users.noreply.github.com>
2020-09-24 12:01:39 +08:00

104 lines
2.8 KiB
Python

import re
import requests
import pandas as pd
from lxml import etree
SYMBOLS_URL = "http://app.finance.ifeng.com/hq/list.php?type=stock_a&class={s_type}"
CSI300_BENCH_URL = "http://push2his.eastmoney.com/api/qt/stock/kline/get?secid=1.000300&fields1=f1%2Cf2%2Cf3%2Cf4%2Cf5&fields2=f51%2Cf52%2Cf53%2Cf54%2Cf55%2Cf56%2Cf57%2Cf58&klt=101&fqt=0&beg=19900101&end=20220101"
SH600000_BENCH_URL = "http://push2his.eastmoney.com/api/qt/stock/kline/get?secid=1.600000&fields1=f1%2Cf2%2Cf3%2Cf4%2Cf5&fields2=f51%2Cf52%2Cf53%2Cf54%2Cf55%2Cf56%2Cf57%2Cf58&klt=101&fqt=0&beg=19900101&end=20220101"
_BENCH_CALENDAR_LIST = None
_ALL_CALENDAR_LIST = None
_HS_SYMBOLS = None
def get_hs_calendar_list(bench=False) -> list:
"""get SH/SZ history calendar list
Parameters
----------
bench: bool
whether to get the bench calendar list, by default False
Returns
-------
history calendar list
"""
global _ALL_CALENDAR_LIST
global _BENCH_CALENDAR_LIST
def _get_calendar(url):
_value_list = requests.get(url).json()["data"]["klines"]
return sorted(map(lambda x: pd.Timestamp(x.split(",")[0]), _value_list))
# TODO: get calendar from MSN
if bench:
if _BENCH_CALENDAR_LIST is None:
_BENCH_CALENDAR_LIST = _get_calendar(CSI300_BENCH_URL)
return _BENCH_CALENDAR_LIST
if _ALL_CALENDAR_LIST is None:
_ALL_CALENDAR_LIST = _get_calendar(SH600000_BENCH_URL)
return _ALL_CALENDAR_LIST
def get_hs_stock_symbols() -> list:
"""get SH/SZ stock symbols
Returns
-------
stock symbols
"""
global _HS_SYMBOLS
if _HS_SYMBOLS is None:
_res = set()
for _k, _v in (("ha", "ss"), ("sa", "sz"), ("gem", "sz")):
resp = requests.get(SYMBOLS_URL.format(s_type=_k))
_res |= set(
map(
lambda x: "{}.{}".format(re.findall(r"\d+", x)[0], _v),
etree.HTML(resp.text).xpath("//div[@class='result']/ul//li/a/text()"),
)
)
_HS_SYMBOLS = sorted(list(_res))
return _HS_SYMBOLS
def symbol_suffix_to_prefix(symbol: str, capital: bool = True) -> str:
"""symbol suffix to prefix
Parameters
----------
symbol: str
symbol
capital : bool
by default True
Returns
-------
"""
code, exchange = symbol.split(".")
if exchange.lower() in ["sh", "ss"]:
res = f"sh{code}"
else:
res = f"{exchange}{code}"
return res.upper() if capital else res.lower()
def symbol_prefix_to_sufix(symbol: str, capital: bool = True) -> str:
"""symbol prefix to sufix
Parameters
----------
symbol: str
symbol
capital : bool
by default True
Returns
-------
"""
res = f"{symbol[:-2]}.{symbol[-2:]}"
return res.upper() if capital else res.lower()