def get_shenwan_industry_label(stock_list, date):
industry_classification = rqdatac.shenwan_instrument_industry(
stock_list, date)
industry_classification_missing_stocks = list(
set(stock_list) - set(industry_classification.index.tolist()))
# 当传入股票过多时，对于缺失行业标记的股票，RQD 目前不会向前搜索，因此需要循环单个传入查找这些股票的行业标记
if len(industry_classification_missing_stocks) != 0:
for stock in industry_classification_missing_stocks:
missing_industry_classification = rqdatac.shenwan_instrument_industry(
stock, date)
if missing_industry_classification != None:
industry_classification = industry_classification.append(
pd.Series([
missing_industry_classification[0],
missing_industry_classification[1]
],
index=['index_code', 'index_name'],
name=stock))
return industry_classification['index_name']
def get_shenwan_industry_exposure(stock_list, date):
industry_classification = rqdatac.shenwan_instrument_industry(
stock_list, date)
if date > '2014-01-01':
shenwan_industry_name = ['农林牧渔', '采掘', '化工', '钢铁', '有色金属', '电子', '家用电器', '食品饮料', '纺织服装', '轻工制造',\
'医药生物', '公用事业', '交通运输', '房地产', '商业贸易', '休闲服务','综合', '建筑材料', '建筑装饰', '电气设备',\
'国防军工', '计算机', '传媒', '通信', '银行', '非银金融', '汽车', '机械设备']
else:
shenwan_industry_name = [
'金融服务', '房地产', '医药生物', '有色金属', '餐饮旅游', '综合', '建筑建材', '家用电器',
'交运设备', '食品饮料', '电子', '信息设备', '交通运输', '轻工制造', '公用事业', '机械设备',
'纺织服装', '农林牧渔', '商业贸易', '化工', '信息服务', '采掘', '黑色金属'
]
industry_exposure_df = pd.DataFrame(0,
index=industry_classification.index,
columns=shenwan_industry_name)
for industry in shenwan_industry_name:
industry_exposure_df.loc[industry_classification[
industry_classification['index_name'] == industry].index,
industry] = 1
return industry_exposure_df.index.tolist(), industry_exposure_df
def get_industry_matching(clean_order_book_ids,
matching_date,
matching_index='000300.XSHG'):
"""
if specified industry matching, match unselected industry by matching_index
:param clean_order_book_ids:
:param matching_date:
:param matching_index:
:return:
"""
# get clean_order_book_ids industry
selected_df = pd.DataFrame(index=clean_order_book_ids)
selected_df['industry'] = [
rqdatac.shenwan_instrument_industry(s, matching_date)
for s in selected_df.index
]
selected_industry = set(selected_df.industry)
# get matching_index industry and get unselected industry weight
index_industry = get_index_component_industry_and_marketcap(
matching_index, matching_date)
match_industry = index_industry.loc[~index_industry.industry.
isin(selected_industry)]
industry_matching_weight = match_industry.percent
# get how much weights left for optimizer
optimizer_total_weight = 1 - sum(industry_matching_weight)
return optimizer_total_weight, industry_matching_weight
def to_constraint(self, order_book_ids, date):
shenwan_data = pd.DataFrame(
rqdatac.shenwan_instrument_industry(order_book_ids,
date)['index_name'])
shenwan_data = shenwan_data.reset_index()
shenwan_data['values'] = 1
dummy_variables = shenwan_data.pivot(columns="index_name",
index="index",
values="values").replace(
np.nan, 0)
return _to_constraint2(dummy_variables,
self._rules), set(order_book_ids) - set(
dummy_variables.index.tolist())
def get_index_component_industry_and_marketcap(matching_index, matching_date):
"""
get matching_index industry and market_cap
:param matching_index:
:param matching_date:
:return:
"""
# get index components, industry
i_c = rqdatac.index_components(matching_index, matching_date)
matching_index_df = pd.DataFrame(index=i_c)
matching_index_df['industry'] = [
rqdatac.shenwan_instrument_industry(s, matching_date)
for s in matching_index_df.index
]
# get index market_cap
market_cap = rqdatac.get_fundamentals(query(
fundamentals.eod_derivative_indicator.market_cap).filter(
fundamentals.eod_derivative_indicator.stockcode.in_(
matching_index_df.index)),
entry_date=matching_date)
market_cap_ = market_cap.loc[market_cap.items[0]].transpose()
# paste them as one df
matching_index_cap_df = pd.concat([matching_index_df, market_cap_], axis=1)
# change the column name
matching_index_cap_df.columns.values[1] = 'market_cap'
# calculate each component's percent by its market_cap
total_market_cap = sum(matching_index_cap_df.market_cap)
matching_index_cap_df[
'percent'] = matching_index_cap_df.market_cap / total_market_cap
# sort them by industry and market_cap
res = matching_index_cap_df.sort_values(['industry', 'market_cap'])
return res
def get_shenwan_industry_exposure(stock_list, date):
industry_classification = rqdatac.shenwan_instrument_industry(
stock_list, date)
industry_classification_missing_stocks = list(
set(stock_list) - set(industry_classification.index.tolist()))
# 当传入股票过多时，对于缺失行业标记的股票，RQD 目前不会向前搜索，因此需要循环单个传入查找这些股票的行业标记
if len(industry_classification_missing_stocks) != 0:
print(date, 'industry_classification_missing_stocks',
industry_classification_missing_stocks)
for stock in industry_classification_missing_stocks:
missing_industry_classification = rqdatac.shenwan_instrument_industry(
stock, date)
if missing_industry_classification != None:
industry_classification = industry_classification.append(
pd.Series([
missing_industry_classification[0],
missing_industry_classification[1]
],
index=['index_code', 'index_name'],
name=stock))
if date > '2014-01-01':
shenwan_industry_name = ['农林牧渔', '采掘', '化工', '钢铁', '有色金属', '电子', '家用电器', '食品饮料', '纺织服装', '轻工制造',\
'医药生物', '公用事业', '交通运输', '房地产', '商业贸易', '休闲服务','综合', '建筑材料', '建筑装饰', '电气设备',\
'国防军工', '计算机', '传媒', '通信', '银行', '非银金融', '汽车', '机械设备']
else:
shenwan_industry_name = [
'金融服务', '房地产', '医药生物', '有色金属', '餐饮旅游', '综合', '建筑建材', '家用电器',
'交运设备', '食品饮料', '电子', '信息设备', '交通运输', '轻工制造', '公用事业', '机械设备',
'纺织服装', '农林牧渔', '商业贸易', '化工', '信息服务', '采掘', '黑色金属'
]
# 在 stock_list 中仅有一个股票的情况下，返回格式为 tuple
if isinstance(industry_classification, tuple):
industry_name = industry_classification[1]
industry_exposure_df = pd.DataFrame(0,
index=shenwan_industry_name,
columns=stock_list).T
industry_exposure_df[industry_name] = 1
else:
industry_exposure_df = pd.DataFrame(
0,
index=industry_classification.index,
columns=shenwan_industry_name)
for industry in shenwan_industry_name:
industry_exposure_df.loc[industry_classification[
industry_classification['index_name'] == industry].index,
industry] = 1
return industry_exposure_df.index.tolist(), industry_exposure_df
def get_industry(universe, date):
return (rqd.shenwan_instrument_industry(
universe, date).loc[:, 'index_name'].rename('industry'))
