def func(omega):
w = 0
for j in range(len(returns.columns)):
ind = jq.get_industry(returns.columns[j], date="2021-04-12")
if industries[i] == ind:
w += omega[j]
return w
def get_industry_by_security(security):
"""
stock所属版块行业信息
:param security:
:return:
"""
d = jq.get_industry(security)
return (d[security]['sw_l1']['industry_name'],
d[security]['sw_l2']['industry_name'],
d[security]['sw_l3']['industry_name'])
def get_day_industry(security, date):
fields = ["sw_l1", "sw_l2", "sw_l3", "zjw", "jq_l2", "jq_l1"]
data_dict = jq.get_industry(security, date=date)
# 即使在不开盘的日期也能有返回值
if len(data_dict) == 0 or security not in data_dict:
return pd.DataFrame({col: [] for col in fields})
data_df = pd.DataFrame(columns=fields)
for field in fields:
industry = "{}_{}".format(data_dict[security][field]["industry_code"], data_dict[security][field]["industry_name"])
data_df[field] = [industry]
return data_df
def init_stock_industries():
stocks_sql = "select code from security"
stock_codes = my.select_all(stocks_sql, ())
jq.login()
stock_industry_list = []
for stock_code in stock_codes:
code = stock_code['code']
data = sdk.get_industry(code, date='2020-10-30')
print(data)
stock_industry_data = data[code]
if not bool(stock_industry_data):
continue
industry_zjw = stock_industry_data['zjw']
stock_industry_zjw = (code, 'zjw', industry_zjw['industry_code'],
industry_zjw['industry_name'])
stock_industry_list.append(stock_industry_zjw)
has_sw_l1 = 'sw_l1' in stock_industry_data.keys()
if has_sw_l1:
industry_sw_l1 = stock_industry_data['sw_l1']
industry_sw_l2 = stock_industry_data['sw_l2']
stock_industry_sw_l1 = (code, 'sw_l1',
industry_sw_l1['industry_code'],
industry_sw_l1['industry_name'])
stock_industry_sw_l2 = (code, 'sw_l2',
industry_sw_l2['industry_code'],
industry_sw_l2['industry_name'])
stock_industry_list.append(stock_industry_sw_l1)
stock_industry_list.append(stock_industry_sw_l2)
has_jq_l1 = 'jq_l1' in stock_industry_data.keys()
if has_jq_l1:
industry_jq_l1 = stock_industry_data['jq_l1']
stock_industry_jq_l1 = (code, 'jq_l1',
industry_jq_l1['industry_code'],
industry_jq_l1['industry_name'])
stock_industry_list.append(stock_industry_jq_l1)
has_jq_l2 = 'jq_l2' in stock_industry_data.keys()
if has_jq_l2:
industry_jq_l2 = stock_industry_data['jq_l2']
stock_industry_jq_l2 = (code, 'jq_l2',
industry_jq_l2['industry_code'],
industry_jq_l2['industry_name'])
stock_industry_list.append(stock_industry_jq_l2)
insert_sql = "insert into stock_industry(code, type, industry_code, industry_name) values (%s, %s, %s, %s)"
my.insert_many(insert_sql, stock_industry_list)
def normlizeCode(codes):
#from e.g. 000906.XSHG to 000906 which is the code format in quantaxis
#return ['000001','000003',....]
zz800_industry = get_industry(codes,
date=datetime.strftime(
datetime.today(), '%Y-%m-%d'))
zz800_industry = pd.DataFrame(zz800_industry).T[[industry_type]]
zz800_industry[industry_type] = zz800_industry[industry_type].apply(
lambda x: x['industry_name'])
normCode = []
for i in codes:
normCode.append([i[:6], i, zz800_industry.loc[i][0]])
return normCode
def get_securities_day_industry(security_list, date):
# 申万一级行业、申万二级行业、申万三级行业、聚宽一级行业、聚宽二级行业、证监会行业
name_list = ["sw_l1", "sw_l2", "sw_l3", "jq_l1", "jq_l2", "zjw"]
data_dict = jq.get_industry(security_list, date=date)
data_df_list = []
for security in data_dict:
industry_dict = {"security": security}
if len(data_dict[security]) == 0:
continue
for name in name_list:
if name in data_dict[security]:
industry_dict[name] = data_dict[security][name]["industry_name"]
else:
industry_dict[name] = "None"
temp_df = pd.DataFrame(industry_dict, index=[0])
data_df_list.append(temp_df)
if not data_df_list:
return pd.DataFrame({name: [] for name in ["security"] + name_list + ["date"]})
concat_df = pd.concat(data_df_list, axis=0)
result_df = concat_df.sort_values(by=["security"], ascending=True).reset_index(drop=True)
result_df["date"] = date
return result_df
def QA_fetch_get_factor_groupby(factor: pd.Series,
industry_cls: str = "sw_l1",
detailed: bool = False) -> pd.DataFrame:
"""
获取因子的行业暴露, 注意，返回的值是 pd.DataFrame 格式，包含原因子值，附加一列
因子对应的行业信息 (需先自行导入聚宽本地 sdk 并登陆)
参数
---
:param factor: 因子值，索引为 ['日期' '资产']
:param industry_cls: 行业分类，默认为申万 1 级行业
:param detailed: 是否使用详细模式，默认为 False, 即取因子日期最后一日的行业信息
返回值
---
:return: 因子数据, 包括因子值，因子对应行业
"""
warnings.warn("请先自行导入聚宽本地 sdk 并登陆", UserWarning)
# 因子格式化
factor = QA_fmt_factor(factor)
merged_data = pd.DataFrame(factor.copy().rename("factor"))
# 股票代码格式化
stock_list = QA_fmt_code_list(
factor.index.get_level_values("code").drop_duplicates(), style="jq")
# 非详细模式， 行业数据采用当前日期
if detailed:
# start_time = str(min(factor.index.get_level_values("datetime")))[:10]
# end_time = str(max(factor.index.get_level_values("datetime")))[:10]
# date_range = list(
# map(pd.Timestamp, QA_util_get_trade_range(start_time, end_time))
# )
date_range = (factor.index.get_level_values(
"datetime").drop_duplicates().tolist())
df_local = pd.DataFrame()
industries = map(partial(jqdatasdk.get_industry, stock_list),
date_range)
industries = {
d: {
s: ind.get(s).get(industry_cls,
dict()).get("industry_name", "NA")
for s in stock_list
}
for d, ind in zip(date_range, industries)
}
else:
end_time = str(max(factor.index.get_level_values("datetime")))[:10]
date_range = [pd.Timestamp(end_time)]
industries = jqdatasdk.get_industry(stock_list, end_time)
industries = {
d: {
s: industries.get(s).get(industry_cls,
dict()).get("industry_name", "NA")
for s in stock_list
}
for d in date_range
}
# 可能历史上股票没有行业信息，用之后的行业信息往前填充
df_local = pd.DataFrame(industries).T.sort_index()
df_local.columns = df_local.columns.map(str).str.slice(0, 6)
ss_local = df_local.stack(level=-1)
ss_local.index.names = ["date", "code"]
merged_data["date"] = merged_data.index.get_level_values("datetime").map(
lambda x: x.date())
merged_data = (merged_data.reset_index().set_index([
"date", "code"
]).assign(group=ss_local).reset_index().set_index(["datetime",
"code"]).drop("date",
axis=1))
group = merged_data["group"].unstack().bfill().stack()
merged_data["group"] = group
return merged_data
matplotlib.rc("font", **font)
from datetime import datetime
import seaborn as sns
# 指数
index_code = '000906.XSHG'
# 行业分类标准
industry_type = 'sw_l1'
# 宽度日期
market_breadth_days = 30
# 获取每个行业 以及 获取每个行业包含中证800的成分股的个数
zz800 = get_index_stocks('000906.XSHG')
zz800_industry = get_industry(zz800, date=datetime.strftime(datetime.today(), '%Y-%m-%d'))
zz800_industry = pd.DataFrame(zz800_industry).T[[industry_type]]
zz800_industry[industry_type] = zz800_industry[industry_type].apply(lambda x: x['industry_name'])
industries = zz800_industry[industry_type]
industries = list(set(industries))
industries.sort()
# 创建表格 列是日期，行是行业，最后需要转置
market_breadth = pd.DataFrame(index=(['zz800'] + industries))
# 根据交易日来计算宽度
# 最近80天交易日
# 然后倒序[::-1]
# 最后取出80天[:80]
trade_days = get_trade_days(start_date='2015-01-01', end_date=None)[::-1][:market_breadth_days]
import sys
import os
root_path = os.path.dirname(os.path.realpath(__file__)) + '/../'
sys.path.append(root_path + 'scripts/')
import utils
import utils_jq
import jqdatasdk
if len(sys.argv) < 3:
print("usage: ./dump_ind.py date cn")
quit()
d = sys.argv[1]
country = sys.argv[2]
if not utils.is_bday(d, country):
print('{} is {} holiday'.format(d, country))
quit()
file_path = root_path + 'data/industry/{}/'.format(country)
os.makedirs(file_path, 0o777, exist_ok=True)
stocks = utils_jq.get_universe(utils.date_str(d))
t = jqdatasdk.get_industry(stocks, date=utils.date_str(d))
t = pd.DataFrame([
dict(
zip(['ric', 'date'] + list(t[r].keys()),
[r, d] + [x['industry_code'] for x in t[r].values()]))
for r in t.keys()
])
if 0 == t.size:
quit()
print(file_path + '{}.txt'.format(d))
t.to_csv(file_path + '{}.txt'.format(d), sep='\t', index=False)
def get_instrument_industry(self, order_book_ids, dt=None):
industry = get_industry(security=order_book_ids, date=dt)
data_df = parse_industry_code_dict(industry)
return data_df
def getindustry(self, code, tday):
return jq.get_industry(code, tday)
