def index_components(order_book_id, date=None):
# type: (str, Optional[Union[str, datetime.date]]) -> List[str]
"""
获取某一指数的股票构成列表，也支持指数的历史构成查询。
:param order_book_id: 指数代码，可传入order_book_id
:param date: 查询日期，默认为策略当前日期。如指定，则应保证该日期不晚于策略当前日期
:return: 构成该指数股票的 order_book_id
:example:
得到上证指数在策略当前日期的构成股票的列表:
.. code-block:: python3
:linenos:
index_components('000001.XSHG')
#[Out]['600000.XSHG', '600004.XSHG', ...]
"""
env = Environment.get_instance()
dt = env.trading_dt.date()
if date is None:
date = dt
else:
date = to_date(date)
if date > dt:
raise RQInvalidArgument(
_('in index_components, date {} is no earlier than test date {}'
).format(date, dt))
order_book_id = assure_order_book_id(order_book_id)
return rqdatac.index_components(order_book_id, date=date)
def init(context):
# 在context中保存全局变量
equity_funds_list = rqdatac.index_components("000300.XSHG", "2014-01-01")
to_test_list = list(
np.random.choice(equity_funds_list, size=100, replace=False))
context.s1 = to_test_list
frequency = 15
context.rebalance_time = [get_next_trading_date(datetime.date(2014, 1, 1))]
for i in range(11):
temp = context.rebalance_time[-1] + datetime.timedelta(weeks=frequency)
context.rebalance_time.append(get_next_trading_date(temp))
# 实时打印日志
logger.info("RunInfo: {}".format(context.run_info))
def get_idx_cons(self, idx_id=None, ticker=None, index_date=None):
'''
:param idx_id: 1:上证综指； 1782：沪深300
:return:
'''
if self.source == 0:
ret = list(DataAPI.IdxConsGet(ticker=ticker, isNew=u"", intoDate=index_date,
field=["consTickerSymbol", 'consExchangeCD'], pandas="1").values)
return ['{0}.{1}'.format(item[0], item[1]) for item in ret]
elif self.source == 1:
# TODO to be added for rqdata when the proxy for SDK is solved
ret = rqdatac.index_components('000016.XSHG')
return ret
def get_explicit_factor_returns(date):
"""
:param date:日期
:return: pandas.Series
"""
previous_trading_date = rqdatac.get_previous_trading_date(date)
all_a_stocks = rqdatac.all_instruments(type="CS",date=previous_trading_date).order_book_id.tolist()
filtered_stocks = noisy_stocks_filter(all_a_stocks,previous_trading_date)
# print(all_a_stocks,previous_trading_date)
factor_exposures = rqdatac.get_style_factor_exposure(all_a_stocks, previous_trading_date, previous_trading_date, "all").sort_index()
factor_exposures.index=factor_exposures.index.droplevel(1)
closePrice = rqdatac.get_price(all_a_stocks, rqdatac.get_previous_trading_date(previous_trading_date),
previous_trading_date, fields="close")
priceChange = closePrice.pct_change().iloc[-1]
index_mapping = {"csi_300":'000300.XSHG',"csi_500":"000905.XSHG","csi_800":"000906.XSHG"}
all_stocks = {index:rqdatac.index_components(index_mapping.get(index),date=previous_trading_date) for index in index_mapping}
all_stocks['whole_market'] = filtered_stocks
def _calc_explicitReturns_with_stocksList(stocksList):
# 根据股票池计算收益率
_sizeBeta = factor_exposures[['size','beta']].loc[stocksList]
_quantileGroup = _sizeBeta.apply(lambda x:pd.cut(x,bins=3,labels=False)+1).reset_index()
_quantileStocks = _quantileGroup.groupby(['size','beta']).apply(lambda x:x.index.tolist())
market_neutralize_stocks = _quantileStocks.apply(
lambda x: pd.Series(stocksList).loc[x].values.tolist()).values.tolist()
return factor_exposures.loc[stocksList].apply(lambda x,y=market_neutralize_stocks:_calc_single_explicit_returns(x,y))
def _calc_single_explicit_returns(_factor_exposure,market_neutralize_stocks):
# 计算单一因子收益率
def _deuce(series):
median = series.median()
return [series[series<=median].index.tolist(),series[series>median].index.tolist()]
deuceResults = np.array([_deuce(_factor_exposure[neutralized_stks]) for neutralized_stks in market_neutralize_stocks]).flatten()
short_stocksList = list(reduce(lambda x,y:set(x)|set(y),np.array([s for i,s in enumerate(deuceResults) if i%2==0])))
long_stockList = list(reduce(lambda x,y:set(x)|set(y),np.array([s for i,s in enumerate(deuceResults) if i%2==1])))
return priceChange[long_stockList].mean() - priceChange[short_stocksList].mean()
results = {key: _calc_explicitReturns_with_stocksList(all_stocks.get(key)) for key in all_stocks}
return pd.DataFrame(results)[['whole_market','csi_300','csi_500','csi_800']]
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 factor_return_estimation(latest_trading_date, factor_exposure):
previous_trading_date = rqdatac.get_previous_trading_date(
latest_trading_date)
# 计算无风险日收益率
daily_return = rqdatac.get_price(
order_book_ids=factor_exposure.index.tolist(),
start_date=previous_trading_date,
end_date=latest_trading_date,
fields='close').pct_change()[-1:].T
compounded_risk_free_return = rqdatac.get_yield_curve(
start_date=latest_trading_date,
end_date=latest_trading_date,
tenor='3M')['3M']
daily_risk_free_return = (((1 + compounded_risk_free_return)**(1 / 252)) -
1)
daily_excess_return = daily_return.subtract(
daily_risk_free_return.values).T
# 以市场平方根作为加权最小二乘法的加权系数
market_cap = rqdatac.get_factor(
id_or_symbols=factor_exposure.index.tolist(),
factor='a_share_market_val',
start_date=previous_trading_date,
end_date=previous_trading_date)
missing_market_cap_stock = market_cap[market_cap.isnull() ==
True].index.tolist()
if len(missing_market_cap_stock) > 0:
price = rqdatac.get_price(missing_market_cap_stock,
previous_trading_date,
previous_trading_date,
fields='close',
frequency='1d').T
shares = rqdatac.get_shares(missing_market_cap_stock,
previous_trading_date,
previous_trading_date,
fields='total_a').T
market_cap[market_cap.isnull() == True] = (
price * shares)[previous_trading_date]
normalized_regression_weight = market_cap.pow(0.5) / market_cap.pow(
0.5).sum()
# 各行业市值之和，用于行业收益率约束条件
if str(previous_trading_date) > '2014-01-01':
industry_factors = ['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:
industry_factors = [
'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'
]
#style_factor = ['beta', 'momentum', 'earnings_yield', 'residual_volatility', 'growth', 'book_to_price',
# 'leverage', 'liquidity','size','non_linear_size']
industry_total_market_cap = market_cap.dot(
factor_exposure.loc[market_cap.index][industry_factors])
factor_return_series = pd.DataFrame()
# 对10个风格因子不添加约束，对 GICS 32个行业添加约束
factor_return_series['whole_market'] = constrainted_weighted_least_square(Y = daily_excess_return[market_cap.index].values[0], X = factor_exposure.loc[market_cap.index], weight = normalized_regression_weight,\
industry_total_market_cap = industry_total_market_cap, unconstrained_variables = 10, constrained_variables = len(industry_total_market_cap))
# 沪深300
csi_300_components = rqdatac.index_components(index_name='000300.XSHG',
date=previous_trading_date)
csi_300_components = list(
set(market_cap.index.tolist()).intersection(set(csi_300_components)))
# 各行业市值之和，用于行业收益率约束条件
csi_300_industry_total_market_cap = market_cap[csi_300_components].dot(
factor_exposure[industry_factors].loc[csi_300_components])
# 若行业市值之和小于100，则认为基准没有配置该行业
missing_industry = csi_300_industry_total_market_cap[
csi_300_industry_total_market_cap < 100].index
csi_300_industry_total_market_cap = csi_300_industry_total_market_cap.drop(
missing_industry)
# 将沪深300股票池中非线性市值暴露度与市值暴露度做正交化处理，根据定义重新计算
csi_300_factor_exposure = factor_exposure.loc[csi_300_components]
csi_300_factor_exposure['non_linear_size'] = orthogonalize(
target_variable=np.power(csi_300_factor_exposure['size'], 3),
reference_variable=csi_300_factor_exposure['size'],
regression_weight=np.sqrt(market_cap[csi_300_components]) /
(np.sqrt(market_cap[csi_300_components]).sum()))
factor_return_series['csi_300'] = constrainted_weighted_least_square(Y = daily_excess_return[factor_exposure.index][csi_300_components].values[0], X = csi_300_factor_exposure.drop(missing_industry, axis=1), weight = normalized_regression_weight[factor_exposure.index][csi_300_components],\
industry_total_market_cap = csi_300_industry_total_market_cap, unconstrained_variables = 10, constrained_variables = len(csi_300_industry_total_market_cap))
# 中证500
csi_500_components = rqdatac.index_components(index_name='000905.XSHG',
date=previous_trading_date)
csi_500_components = list(
set(market_cap.index.tolist()).intersection(set(csi_500_components)))
csi_500_industry_total_market_cap = market_cap[csi_500_components].dot(
factor_exposure[industry_factors].loc[csi_500_components])
missing_industry = csi_500_industry_total_market_cap[
csi_500_industry_total_market_cap < 100].index
csi_500_industry_total_market_cap = csi_500_industry_total_market_cap.drop(
missing_industry)
# 将中证500股票池中非线性市值暴露度与市值暴露度做正交化处理，根据定义重新计算
csi_500_factor_exposure = factor_exposure.loc[csi_500_components]
csi_500_factor_exposure['non_linear_size'] = orthogonalize(
target_variable=np.power(csi_500_factor_exposure['size'], 3),
reference_variable=csi_500_factor_exposure['size'],
regression_weight=np.sqrt(market_cap[csi_500_components]) /
(np.sqrt(market_cap[csi_500_components]).sum()))
factor_return_series['csi_500'] = constrainted_weighted_least_square(Y = daily_excess_return[factor_exposure.index][csi_500_components].values[0], X = csi_500_factor_exposure.drop(missing_industry, axis=1), weight = normalized_regression_weight[factor_exposure.index][csi_500_components],\
industry_total_market_cap = csi_500_industry_total_market_cap, unconstrained_variables = 10, constrained_variables = len(csi_500_industry_total_market_cap))
### 中证800
csi_800_components = rqdatac.index_components(index_name='000906.XSHG',
date=previous_trading_date)
csi_800_components = list(
set(market_cap.index.tolist()).intersection(set(csi_800_components)))
csi_800_industry_total_market_cap = market_cap[csi_800_components].dot(
factor_exposure[industry_factors].loc[csi_800_components])
missing_industry = csi_800_industry_total_market_cap[
csi_800_industry_total_market_cap < 100].index
csi_800_industry_total_market_cap = csi_800_industry_total_market_cap.drop(
missing_industry)
# 将中证800股票池中非线性市值暴露度与市值暴露度做正交化处理，根据定义重新计算
csi_800_factor_exposure = factor_exposure.loc[csi_800_components]
csi_800_factor_exposure['non_linear_size'] = orthogonalize(
target_variable=np.power(csi_800_factor_exposure['size'], 3),
reference_variable=csi_800_factor_exposure['size'],
regression_weight=np.sqrt(market_cap[csi_800_components]) /
(np.sqrt(market_cap[csi_800_components]).sum()))
factor_return_series['csi_800'] = constrainted_weighted_least_square(Y = daily_excess_return[factor_exposure.index][csi_800_components].values[0], X = csi_800_factor_exposure.drop(missing_industry, axis =1), weight = normalized_regression_weight[factor_exposure.index][csi_800_components],\
industry_total_market_cap = csi_800_industry_total_market_cap, unconstrained_variables = 10, constrained_variables = len(csi_800_industry_total_market_cap))
# 若指数在特定行业中没有配置任何股票，则因子收益率为 0
return factor_return_series.replace(np.nan, 0)
def get_factor(order_book_ids,
factor,
start_date=None,
end_date=None,
universe=None,
expect_df=False,
**kwargs):
"""获取因子
:param order_book_ids: 股票代码或代码列表
:param factor: 如 'total_income'
:param date: 如 date='2015-01-05', 默认为前一交易日
:param start_date: 开始日期'2015-01-05', 默认为前一交易日, 最小起始日期为'2000-01-04'
:param end_date: 结束日期
:param universe: 股票池，默认为全A股
:param expect_df: 返回 MultiIndex DataFrame (Default value = False)
:returns: pd.DataFrame
"""
order_book_ids = ensure_order_book_ids(order_book_ids, type="CS")
order_book_ids = list(set(order_book_ids))
factor = ensure_list_of_string(factor)
factor = list(OrderedDict.fromkeys(factor))
if start_date and end_date:
start_date, end_date = ensure_date_range(start_date, end_date,
datetime.timedelta(days=15))
if start_date < 20000104:
warnings.warn(
"start_date is earlier than 2000-01-04, adjusted to 2000-01-04"
)
start_date = 20000104
elif start_date:
raise ValueError("Expect end_date")
elif end_date:
raise ValueError("Expect start_date")
else:
date = kwargs.pop("date", None)
date = ensure_date_int(
date or get_previous_trading_date(datetime.date.today()))
start_date = end_date = date
if kwargs:
raise ValueError('unknown kwargs: {}'.format(kwargs))
if universe is not None:
universe = ensure_string(universe, "universe")
if universe != "all":
universe = ensure_order_book_id(universe, type="INDX")
from rqdatac import index_components
allowed_order_book_ids = set(
index_components(universe, date=end_date) or [])
not_permit_order_book_ids = [
order_book_id for order_book_id in order_book_ids
if order_book_id not in allowed_order_book_ids
]
if not_permit_order_book_ids:
warnings.warn(
"%s not in universe pool, value of those order_book_ids will always be NaN"
% not_permit_order_book_ids)
data = get_client().execute("get_factor_from_store",
order_book_ids,
factor,
start_date,
end_date,
universe=universe)
if not data:
return
factor_value_length = len(data[0][2])
if factor_value_length == 0:
return
dates = pd.to_datetime(get_trading_dates(start_date, end_date))
if len(dates) > factor_value_length:
_get_factor_warning_msg(dates[factor_value_length], dates[-1])
dates = dates[0:factor_value_length]
if expect_df or len(factor) > 1:
order_book_id_index_map = {o: i for i, o in enumerate(order_book_ids)}
factor_index_map = {f: i for i, f in enumerate(factor)}
arr = np.full((len(order_book_ids) * len(dates), len(factor)), np.nan)
for order_book_id, factor_name, values in data:
order_book_id_index = order_book_id_index_map[order_book_id]
factor_index = factor_index_map[factor_name]
slice_ = slice(order_book_id_index * len(dates),
(order_book_id_index + 1) * len(dates), None)
arr[slice_, factor_index] = values
multi_index = pd.MultiIndex.from_product(
[order_book_ids, dates], names=["order_book_id", "date"])
df = pd.DataFrame(index=multi_index, columns=factor, data=arr)
return df
order_book_id_index_map = {o: i for i, o in enumerate(order_book_ids)}
arr = np.full((len(dates), len(order_book_ids)), np.nan)
for order_book_id, _, values in data:
arr[:, order_book_id_index_map[order_book_id]] = values
df = pd.DataFrame(index=dates, columns=order_book_ids, data=arr)
if len(df.index) == 1:
return df.iloc[0]
if len(df.columns) == 1:
return df[df.columns[0]]
return df
cons = [
rqoptimizer2.WildcardIndustryConstraint(
lower_limit=-0.01,
upper_limit=0.01,
relative=True,
hard=False,
classification=rqoptimizer2.IndustryClassification.ZX),
rqoptimizer2.WildcardStyleConstraint(lower_limit=-0.3,
upper_limit=0.3,
relative=True,
hard=False)
]
# 获取前一交易日中证800成分股的净利润增长率（TTM）
previous_date = rqdatac.get_previous_trading_date(date)
index_component = rqdatac.index_components('000906.XSHG', previous_date)
indicator_series = rqdatac.get_factor(index_component,
'net_profit_growth_ratio_ttm',
previous_date, previous_date).dropna()
selected_stock = generate_stock_pool(previous_date,
indicator_series,
stock_number=5)
# 个股指标得分范围调整至0.1-1.1，避免权重过分集中于部分指标得分较大的个股
adjusted_series = ((indicator_series.loc[selected_stock] -
indicator_series.loc[selected_stock].min()) /
(indicator_series.loc[selected_stock].max() -
indicator_series.loc[selected_stock].min())) + 0.1
portfolio_weight = rqoptimizer2.portfolio_optimize(
selected_stock,
date,
bnds=bounds,
def index_compose(self, code):
return rq.index_components(code)
def factor_return_estimation(stock_list, date, factor_exposure):
latest_trading_date = rqdatac.get_previous_trading_date(
datetime.strptime(date, "%Y-%m-%d") + timedelta(days=1))
previous_trading_date = rqdatac.get_previous_trading_date(
latest_trading_date)
# 计算无风险日收益率
daily_return = rqdatac.get_price(order_book_ids=stock_list,
start_date=previous_trading_date,
end_date=latest_trading_date,
fields='close').pct_change()[-1:].T
compounded_risk_free_return = rqdatac.get_yield_curve(
start_date=latest_trading_date,
end_date=latest_trading_date,
tenor='3M')['3M']
daily_risk_free_return = (((1 + compounded_risk_free_return)**(1 / 252)) -
1)
daily_excess_return = daily_return.subtract(
daily_risk_free_return.values).T
# 以市场平方根作为加权最小二乘法的加权系数
market_cap = rqdatac.get_factor(id_or_symbols=stock_list,
factor='a_share_market_val',
start_date=latest_trading_date,
end_date=latest_trading_date)
normalized_regression_weight = market_cap.pow(0.5) / market_cap.pow(
0.5).sum()
# 各行业市值之和，用于行业收益率约束条件
industry_factors = ['CNE5S_ENERGY', 'CNE5S_CHEM', 'CNE5S_CONMAT', 'CNE5S_MTLMIN', 'CNE5S_MATERIAL', 'CNE5S_AERODEF',\
'CNE5S_BLDPROD', 'CNE5S_CNSTENG', 'CNE5S_ELECEQP', 'CNE5S_INDCONG', 'CNE5S_MACH','CNE5S_TRDDIST',\
'CNE5S_COMSERV', 'CNE5S_AIRLINE', 'CNE5S_MARINE', 'CNE5S_RDRLTRAN', 'CNE5S_AUTO', 'CNE5S_HOUSEDUR',\
'CNE5S_LEISLUX', 'CNE5S_CONSSERV', 'CNE5S_MEDIA', 'CNE5S_RETAIL', 'CNE5S_PERSPRD', 'CNE5S_BEV',\
'CNE5S_SOFTWARE', 'CNE5S_HDWRSEMI', 'CNE5S_UTILITIE']
industry_total_market_cap = market_cap.dot(
factor_exposure[industry_factors])
factor_return_series = pd.DataFrame()
# 对10个风格因子不添加约束，对 GICS 32个行业添加约束
factor_return_series['whole_market'] = constrainted_weighted_least_square(Y = daily_excess_return[factor_exposure.index].values[0], X = factor_exposure, weight = normalized_regression_weight[factor_exposure.index],\
industry_total_market_cap = industry_total_market_cap, unconstrained_variables = 10, constrained_variables = 32)
### 沪深300
csi_300_components = rqdatac.index_components(index_name='000300.XSHG',
date=previous_trading_date)
# 各行业市值之和，用于行业收益率约束条件
csi_300_industry_total_market_cap = market_cap[csi_300_components].dot(
factor_exposure[industry_factors].loc[csi_300_components])
# 若行业市值之和小于100，则认为基准没有配置该行业
missing_industry = csi_300_industry_total_market_cap[
csi_300_industry_total_market_cap < 100].index
csi_300_industry_total_market_cap = csi_300_industry_total_market_cap.drop(
missing_industry)
factor_return_series['csi_300'] = constrainted_weighted_least_square(Y = daily_excess_return[factor_exposure.index][csi_300_components].values[0], X = factor_exposure.drop(missing_industry, axis =1).loc[csi_300_components], weight = normalized_regression_weight[factor_exposure.index][csi_300_components],\
industry_total_market_cap = csi_300_industry_total_market_cap, unconstrained_variables = 10, constrained_variables = len(csi_300_industry_total_market_cap))
### 中证500
csi_500_components = rqdatac.index_components(index_name='000905.XSHG',
date=previous_trading_date)
csi_500_industry_total_market_cap = market_cap[csi_500_components].dot(
factor_exposure[industry_factors].loc[csi_500_components])
missing_industry = csi_500_industry_total_market_cap[
csi_500_industry_total_market_cap < 100].index
csi_500_industry_total_market_cap = csi_500_industry_total_market_cap.drop(
missing_industry)
factor_return_series['csi_500'] = constrainted_weighted_least_square(Y = daily_excess_return[factor_exposure.index][csi_500_components].values[0], X = factor_exposure.drop(missing_industry, axis =1).loc[csi_500_components], weight = normalized_regression_weight[factor_exposure.index][csi_500_components],\
industry_total_market_cap = csi_500_industry_total_market_cap, unconstrained_variables = 10, constrained_variables = len(csi_500_industry_total_market_cap))
### 中证800
csi_800_components = rqdatac.index_components(index_name='000906.XSHG',
date=previous_trading_date)
csi_800_industry_total_market_cap = market_cap[csi_800_components].dot(
factor_exposure[industry_factors].loc[csi_800_components])
missing_industry = csi_800_industry_total_market_cap[
csi_800_industry_total_market_cap < 100].index
csi_800_industry_total_market_cap = csi_800_industry_total_market_cap.drop(
missing_industry)
factor_return_series['csi_800'] = constrainted_weighted_least_square(Y = daily_excess_return[factor_exposure.index][csi_800_components].values[0], X = factor_exposure.drop(missing_industry, axis =1).loc[csi_800_components], weight = normalized_regression_weight[factor_exposure.index][csi_800_components],\
industry_total_market_cap = csi_800_industry_total_market_cap, unconstrained_variables = 10, constrained_variables = len(csi_800_industry_total_market_cap))
# 若指数在特定行业中没有配置任何股票，则因子收益率为 0
return factor_return_series.replace(np.nan, 0)