def get_start_date(
self,
code_list: Union[str,
Tuple[str],
List[str]],
factor_time_range: list
):
"""
获取上市时间
"""
# stock_list = utils.QA_fmt_code_list(code_list, style="jq")
# df_local = jqdatasdk.get_all_securities(types="stock")
stock_list = utils.QA_fmt_code_list(code_list)
df_local = QA_fetch_stock_basic(status=None).set_index("code")
intersection = list(df_local.index.intersection(stock_list))
ss = df_local.loc[intersection]["list_date"]
# ss.index = ss.index.map(lambda x: x[:6])
# 日期处理
date_range = list(map(lambda x: x.date(), factor_time_range))
multiindex = pd.MultiIndex.from_product(
[date_range,
utils.QA_fmt_code_list(intersection)]
)
values = multiindex.map(lambda x: ss.loc[x[1]]).tolist()
df_local = pd.Series(index=multiindex, data=values)
df_local.index.names = ["date", "code"]
return df_local
def QA_ts_update_namechange():
"""
保存所有股票的历史曾用名
"""
# 建表
coll = DATABASE.namechange
coll.create_index(
[
("code", ASCENDING),
("start_date_stamp", ASCENDING),
("end_date_stamp", ASCENDING),
("ann_date_stamp", ASCENDING),
],
unique=True,
)
# 初始化数据接口
pro = get_pro()
# 获取历史所有股票
symbol_list = sorted(
list(set(QA_fmt_code_list(QA_fetch_stock_basic().index.tolist(),
"ts"))))
df = pd.DataFrame()
for i, symbol in enumerate(symbol_list):
if i % 100 == 0:
print(f"Saving {i}th stock name, stock is {symbol}")
try:
df = df.append(pro.namechange(ts_code=symbol))
except:
time.sleep(1)
try:
df = df.append(pro.namechange(ts_code=symbol))
except:
raise ValueError("[ERROR]\t数据获取失败")
# df.to_csv("test.csv")
df["code"] = QA_fmt_code_list(df["ts_code"])
df["start_date_stamp"] = df["start_date"].apply(QA_util_date_stamp)
df["end_date_stamp"] = df["end_date"].apply(QA_util_date_stamp)
df["ann_date_stamp"] = df["ann_date"].apply(QA_util_date_stamp)
df = df.where(pd.notnull(df), None)
js = QA_util_to_json_from_pandas(df.drop(columns=["ts_code"]))
for item in js:
if not item["end_date"]:
item["end_date_stamp"] = 9999999999
qry = {
"code": item["code"],
"start_date_stamp": item["start_date_stamp"],
"end_date_stamp": item["end_date_stamp"],
"ann_date_stamp": item["ann_date_stamp"],
}
if coll.count_documents(qry) == 0:
coll.insert_one(item)
def QA_fetch_factor_start_date(factor: pd.Series) -> pd.DataFrame:
"""
获取因子池上市时间，本地获取接口，使用前先保存股票基本信息
"""
factor = QA_fmt_factor(factor.copy())
merged_data = pd.DataFrame(factor.rename("factor"))
# 股票代码格式化
stock_list = QA_fmt_code_list(
factor.index.get_level_values("code").drop_duplicates())
# 上市时间获取
df_local = QA_fetch_stock_basic(status=None).set_index("code")
intersection = df_local.index.intersection(stock_list)
ss = df_local.loc[intersection]["list_date"]
# 拼接上市时间
merged_data = merged_data.loc[(slice(None), list(ss.index)), :]
merged_data["start_date"] = merged_data.index.map(
lambda x: ss.loc[x[1]]).tolist()
return merged_data