def create(self):
df = get_industries(name='%s_l%s' %
(self.project.name[:2], self.project.name[-1]))
#生成列表
self.to_track(df)
# 调用父类方法保存:
TPool.save(self, df)
def run(self):
# get stock blocks from sina
for category, name_ch in self.category_map.items():
df = get_industries(name=category, date=None)
df['code'] = df.index
df['exchange'] = 'cn'
df['list_date'] = df['start_date']
df['timestamp'] = df['list_date']
df['entity_type'] = 'block'
df['block_type'] = category.replace("_", "")
df['category'] = "industry"
df['id'] = df['entity_id'] = df.apply(lambda x: "block_" + x.exchange + "_" + x.code, axis=1)
df_to_db(data_schema=self.data_schema, df=df, provider=self.provider,
force_update=True)
self.logger.info(f"完成聚宽数据行业数据保存:{name_ch}")
concept_df = get_concepts()
concept_df['code'] = concept_df.index
concept_df['exchange'] = 'cn'
concept_df['list_date'] = concept_df['start_date']
concept_df['timestamp'] = concept_df['list_date']
concept_df['entity_type'] = 'block'
concept_df['category'] = "concept"
concept_df['id'] = concept_df['entity_id'] = concept_df.apply(lambda x: "block_" + x.exchange + "_" + x.code,
axis=1)
df_to_db(data_schema=self.data_schema, df=concept_df, provider=self.provider,
force_update=True)
self.logger.info(f"完成聚宽数据概念数据保存")
def get_sw1_valuation(start_date=None, end_date=None):
#2014-02-22之后申万一级行业28个
code = jd.get_industries(name='sw_l1',date='2014-02-22').index.tolist()
days = jd.get_trade_days(start_date,end_date)
index = jd.finance.run_query(jd.query(jd.finance.SW1_DAILY_VALUATION).filter(
jd.finance.SW1_DAILY_VALUATION.date=='2014-02-22'
).limit(1)).columns.tolist()
data = pd.DataFrame(columns = index)
for day in days:
df=jd.finance.run_query(jd.query(jd.finance.SW1_DAILY_VALUATION).filter(
jd.finance.SW1_DAILY_VALUATION.code.in_(code),
jd.finance.SW1_DAILY_VALUATION.date==day
))
name1 = set(list(map(lambda x:x[:-1],jd.get_industries(name='sw_l1',date='2014-02-22').name.tolist())))
name2 = set(df.name.tolist())
if not name1-name2:
data = pd.concat([data, df], axis = 0, sort=False)
return data
def init_industry():
jq.login()
industry_list = []
# sw_l1
sw_l1_data = sdk.get_industries(name='sw_l1', date='2020-10-30')
for index in sw_l1_data.index:
name = sw_l1_data.loc[index]['name']
industry = (index, name, 'sw_l1')
industry_list.append(industry)
# sw_l2
sw_l1_data = sdk.get_industries(name='sw_l1', date='2020-10-30')
for index in sw_l1_data.index:
name = sw_l1_data.loc[index]['name']
industry = (index, name, 'sw_l2')
industry_list.append(industry)
# jq_l1
sw_l1_data = sdk.get_industries(name='jq_l1', date='2020-10-30')
for index in sw_l1_data.index:
name = sw_l1_data.loc[index]['name']
industry = (index, name, 'jq_l1')
industry_list.append(industry)
# jq_l2
sw_l1_data = sdk.get_industries(name='jq_l2', date='2020-10-30')
for index in sw_l1_data.index:
name = sw_l1_data.loc[index]['name']
industry = (index, name, 'jq_l2')
industry_list.append(industry)
# zjw
sw_l1_data = sdk.get_industries(name='zjw', date='2020-10-30')
for index in sw_l1_data.index:
name = sw_l1_data.loc[index]['name']
industry = (index, name, 'zjw')
industry_list.append(industry)
print(industry_list)
insert_sql = "insert into industry(code, name, type) values (%s, %s, %s)"
my.insert_many(insert_sql, industry_list)
def get_industries_store(self, name='jq_l2', date=None):
"""
获取行业信息并存入数据
:param name:
:param date:
:return:
"""
res = jq.get_industries(name=name, date=None)
'''增加类别列,行业分类者，聚宽，申万，国证'''
res['type'] = name
'''DataFrame入库'''
pymysql.install_as_MySQLdb()
mysqlconnect = create_engine(self.mysql_conf.MYSQL_CON_STR)
res.to_sql(name='industries',
con=mysqlconnect,
if_exists='append',
index=True,
index_label='index',
chunksize=1000)
flog.FinanceLoger.logger.info('所有行业信息已经保存成功')
return
def get_industry_stocks():
df = jq.get_industries(name='zjw')
s2i = {}
row_num = len(df.index)
for i in range(row_num):
industry_code = df.index[i]
industry_name = df.iloc[i]['name']
#print industry_code, industry_name
stocks = jq.get_industry_stocks(industry_code)
for stock_code in stocks:
if stock_code in s2i:
s2i[stock_code].append(industry_name)
else:
s2i[stock_code] = [industry_name]
return s2i
def save_data(start_date, end_date):
jqdatasdk.auth(username=user_passwd.user_name,
password=user_passwd.passwd)
names_to_id = red.get('names_to_id')
names_to_id = json.loads(names_to_id)
indices = pd.read_csv(
r'C:\Users\never\Desktop\website-practice\indices.csv')
names = []
display_names = []
index_name_to_id = {}
for i in range(len(indices)):
if str(indices.start_date[i]) <= start_date and end_date <= str(
indices.end_date[i]):
names.append(indices.id[i])
display_names.append(indices.display_name[i])
index_name_to_id[indices.display_name[i]] = indices.id[i]
indices = display_names
names_to_id['index'] = index_name_to_id
industries_df = jqdatasdk.get_industries('sw_l1')
industry_end_date = {
'建筑建材I': '2014-02-21',
'机械设备I': '2014-02-21',
'交运设备I': '2014-02-21',
'信息设备I': '2014-02-21',
'金融服务I': '2014-02-21',
'信息服务I': '2014-02-21',
}
industries = []
industry_name_to_id = {}
for industry_name, industry_id, start_time in zip(
industries_df.name.values, industries_df.index.values,
industries_df.start_date.values):
st = str(start_time)
if industry_name in industry_end_date.keys(
) and st <= start_date and end_date < industry_end_date[
industry_name]:
industries.append(industry_name)
industry_name_to_id.update({industry_name: industry_id})
elif industry_name not in industry_end_date.keys(
) and st <= start_date:
industries.append(industry_name)
industry_name_to_id.update({industry_name: industry_id})
names_to_id['industry_index'] = industry_name_to_id
stock_pool = {}
stock_ids, stock_names = [], []
stock_name_to_id = {}
for i in range(len(display_names)):
display, pool_id = display_names[i], names[i]
p = jqdatasdk.get_all_securities(types=['stock'], date=start_date)
p = p[p.end_date >= end_date]
q = jqdatasdk.get_index_stocks(pool_id)
id_to_name = dict(zip(p.index.values, p.display_name.values))
stock_name_to_id.update(
dict(zip(p.display_name.values, p.index.values)))
stocks = []
for item in q:
try:
stocks.append(id_to_name[item])
stock_ids.append(item)
stock_names.append(id_to_name[item])
except Exception as e:
pass
stocks = sorted(stocks, key=lambda x: ' '.join(lazy_pinyin(x)))
stock_pool[display] = stocks
names_to_id['stock'] = stock_name_to_id
get_funds = jqdatasdk.get_all_securities('fund', date=start_date)
display_names = ['场内ETF', '场内LOF', '分级基金A', '分级基金B', '场内货币基金']
names = ['etf', 'lof', 'fja', 'fjb', 'money_market_fund']
exchanged_fund_pool = {}
exchanged_name_to_id = dict(zip(display_names, names))
for i in range(len(display_names)):
display, pool_id = display_names[i], names[i]
p = get_funds[get_funds['type'] == pool_id]
y1 = (p.start_date <= start_date).values
y2 = (p.end_date >= end_date).values
p = p[np.logical_and(y1, y2)]
q = p.index.values
id_to_name = dict(zip(p.index.values, p.display_name.values))
exchanged_name_to_id.update(
dict(zip(p.display_name.values, p.index.values)))
funds = []
for item in q:
try:
funds.append(id_to_name[item])
except Exception as e:
pass
funds = sorted(funds, key=lambda x: ' '.join(lazy_pinyin(x)))
exchanged_fund_pool[display] = funds
names_to_id['exchanged_fund'] = exchanged_name_to_id
get_funds = jqdatasdk.get_all_securities('open_fund', date=start_date)
get_funds = get_funds[get_funds.end_date >= end_date]
display_names = ['股票型', '混合型', '债券型', '货币型', 'ETF联接', '黄金', 'QDII']
names = [
'stock_fund', 'mixture_fund', 'bond_fund', 'money_market_fund',
'fund_fund', 'noble_metal_fund', 'QDII_fund'
]
open_fund_pool = {}
open_fund_name_to_id = dict(zip(display_names, names))
for i in range(len(display_names)):
display, pool_id = display_names[i], names[i]
if pool_id != 'QDII_fund':
p = get_funds[get_funds['type'] == pool_id]
else:
p = jqdatasdk.get_all_securities(pool_id)
q = p.index.values
id_to_name = dict(zip(p.index.values, p.display_name.values))
open_fund_name_to_id.update(
dict(zip(p.display_name.values, p.index.values)))
funds = []
for item in q:
try:
funds.append(id_to_name[item])
except Exception as e:
pass
funds = sorted(funds, key=lambda x: ' '.join(lazy_pinyin(x)))
open_fund_pool[display] = funds
names_to_id['open_fund'] = open_fund_name_to_id
data = {
'stock_pool': stock_pool,
'exchanged_fund_pool': exchanged_fund_pool,
'open_fund_pool': open_fund_pool,
'industry_pool': industries,
'index_pool': indices
}
key_name = 'data-' + start_date + '-' + end_date + '.pkl'
red[key_name] = json.dumps(data)
red['names_to_id'] = json.dumps(names_to_id)
# valuation是内置市值数据对象(这里表示查询valuation下所有的属性)
q = jq.query(jq.valuation).filter(jq.valuation.code=='000001.XSHE')
df = jq.get_fundamentals(q, '2021-01-01')
df
# ## 获取金融板块的股票
# In[17]:
import pandas as pd
pd.set_option('max_rows', None)
# 汽车制造 C36，零售业 F52，其他金融业：J69, 货币金融服务：J66
# 计算机、通信和其他电子设备制造业 C39
temp = jq.get_industries()
# 筛选出和金融相关的产业
temp[temp['name'].str.contains('计算机')]
# In[18]:
"""
智能投研
1.筛选2020年市盈率小于行业平均水平
2.市值大于行业平均水平的金融行业股票
3.然后观察2021年的市盈率表现
"""
#设置benchmark_date
benchmark_date = '2020-12-31'
def get_industries(*args, **kwargs):
return jqdatasdk.get_industries(*args, **kwargs)
def get_industries(self, industry_code: cfg.IndustryCode):
return jq.get_industries(name=industry_code.name)