class conf:
# 定义一个conf类，存储需要使用的变量
start_date='2014-01-01' # 日期，作为训练集的起始日期
end_date='2017-02-17' # 日期，作为测试集的结束日期
df = D.history_data(D.instruments(),end_date,end_date,['in_csi800'])
instruments = list(set(df[df['in_csi800']==1]['instrument']))
print('instruments len: ', len(instruments))
# 股票池
# 10日收益率
hold_days = 5
# 以沪深300为基准的相对收益
benchmark = '000300.SHA'
# 本代码由可视化策略环境自动生成 2018年1月20日 12:39
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。
m1 = M.instruments.v2(
start_date='2012-01-01',
end_date='2016-01-01',
market='CN_STOCK_A',
instrument_list = conf.instruments,
max_count=0
)
m2 = M.advanced_auto_labeler.v2(
instruments=m1.data,
label_expr="""# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
# 添加benchmark_前缀，可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_
# 计算收益：5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
shift(close, -5) / shift(open, -1)
# 极值处理：用1%和99%分位的值做clip
clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))
# 将分数映射到分类，这里使用20个分类
all_wbins(label, 10)
# 过滤掉一字涨停的情况 (设置label为NaN，在后续处理和训练中会忽略NaN的label)
where(shift(high, -1) == shift(low, -1), NaN, label)
""",
start_date='',
end_date='',
benchmark='000300.SHA',
drop_na_label=True,
cast_label_int=True
)
m3 = M.input_features.v1(
features="""# #号开始的表示注释
# 多个特征，每行一个，可以包含基础特征和衍生特征
return_5
return_10
return_20
return_40
rank_return_5
rank_return_10
rank_return_20
rank_return_40
turn_0
rank_turn_0
avg_turn_5
avg_turn_10
avg_turn_20
avg_turn_40
rank_avg_turn_5
avg_amount_5
avg_amount_10
avg_amount_20
avg_amount_40
#(volume_0+volume_1+volume_2+volume_3+volume_4)/5
#(volume_0+volume_1+volume_2+volume_3+volume_4+volume_5+volume_6+volume_7+volume_8+volume_9)/10
#(volume_0+volume_1+volume_2+volume_3+volume_4+volume_5+volume_6+volume_7+volume_8+volume_9+volume_10+volume_11+volume_12+volume_13+volume_14+volume_15+volume_16+volume_17+volume_18+volume_19)/20
#(high_0-low_0+high_1-low_1+high_2-low_2+high_3-low_3+high_4-low_4)/5
fs_common_equity_0
market_cap_0
rank_market_cap_0
market_cap_float_0
rank_market_cap_float_0
pe_ttm_0
rank_pe_ttm_0
pe_lyr_0
rank_pe_lyr_0
pb_lf_0
rank_pb_lf_0
ps_ttm_0
rank_ps_ttm_0
mf_net_amount_5
mf_net_amount_10
mf_net_amount_20
avg_mf_net_amount_5
avg_mf_net_amount_10
avg_mf_net_amount_20
rank_avg_mf_net_amount_5
rank_avg_mf_net_amount_10
rank_avg_mf_net_amount_20
fs_net_profit_0
fs_net_profit_ttm_0
fs_deducted_profit_0
fs_deducted_profit_ttm_0
fs_gross_profit_margin_0
fs_gross_profit_margin_ttm_0
fs_net_profit_margin_0
fs_net_profit_margin_ttm_0
fs_operating_revenue_0
fs_operating_revenue_ttm_0
fs_net_profit_yoy_0
rank_fs_net_profit_yoy_0
fs_net_profit_qoq_0
rank_fs_net_profit_qoq_0
fs_operating_revenue_yoy_0
rank_fs_operating_revenue_yoy_0
fs_operating_revenue_qoq_0
rank_fs_operating_revenue_qoq_0
fs_eps_yoy_0
fs_roe_0
fs_roe_ttm_0
fs_roa_0
fs_roa_ttm_0
fs_eps_0
fs_bps_0
fs_cash_ratio_0
#fs_operating_revenue_ttm_0/(fs_current_assets_0+fs_non_current_assets_0)
#fs_current_assets_0/fs_current_liabilities_0
#(fs_current_liabilities_0+fs_non_current_liabilities_0)/ fs_common_equity_0
#(fs_current_liabilities_0+fs_non_current_liabilities_0)/(fs_current_assets_0+fs_non_current_assets_0)
fs_free_cash_flow_0
fs_net_cash_flow_0
fs_net_cash_flow_ttm_0
fs_current_assets_0
fs_non_current_assets_0
fs_current_liabilities_0
fs_non_current_liabilities_0
sh_holder_avg_pct_0
rank_sh_holder_avg_pct_0
sh_holder_avg_pct_3m_chng_0
rank_sh_holder_avg_pct_3m_chng_0
sh_holder_avg_pct_6m_chng_0
rank_sh_holder_avg_pct_6m_chng_0
ta_sma_5_0
ta_sma_10_0
ta_sma_20_0
ta_atr_14_0
ta_atr_28_0
ta_mfi_14_0
ta_mfi_28_0
ta_rsi_14_0
ta_rsi_28_0
ta_trix_14_0
ta_trix_28_0
ta_sar_0
ta_mom_10_0
ta_mom_20_0
ta_mom_30_0
ta_mom_60_0
ta_willr_14_0
ta_willr_28_0
ta_ad_0
ta_aroon_down_14_0
ta_aroon_down_28_0
ta_aroon_up_14_0
ta_aroon_up_28_0
ta_aroonosc_14_0
ta_aroonosc_28_0
ta_bbands_upperband_14_0
ta_bbands_upperband_28_0
ta_bbands_middleband_14_0
ta_bbands_middleband_28_0
ta_bbands_lowerband_14_0
ta_bbands_lowerband_28_0
ta_adx_14_0
ta_adx_28_0
ta_cci_14_0
ta_cci_28_0
ta_macd_macd_12_26_9_0
ta_macd_macdsignal_12_26_9_0
ta_macd_macdhist_12_26_9_0
ta_obv_0
ta_stoch_slowk_5_3_0_3_0_0
ta_stoch_slowd_5_3_0_3_0_0
swing_volatility_5_0
swing_volatility_10_0
swing_volatility_30_0
rank_swing_volatility_5_0
rank_swing_volatility_10_0
rank_swing_volatility_30_0
volatility_5_0
volatility_10_0
volatility_30_0
rank_volatility_5_0
rank_volatility_10_0
rank_volatility_30_0
beta_csi800_5_0
beta_csi800_10_0
beta_csi800_30_0
rank_beta_csi800_5_0
rank_beta_csi800_10_0
rank_beta_csi800_30_0
"""
)
m4 = M.general_feature_extractor.v6(
instruments=m1.data,
features=m3.data,
start_date='',
end_date='',
before_start_days=0
)
m5 = M.derived_feature_extractor.v2(
input_data=m4.data,
features=m3.data,
date_col='date',
instrument_col='instrument'
)
m15 = M.transform.v2(
data=m5.data,
# stockranker 默认的转换函数，主要是将特征映射到非负整数区间，因为stockranker要求输入特征数据为非负整数
transforms=T.get_stock_ranker_default_transforms(),
drop_null=True, # 缺失数据处理，如果某一行有空列，则删除
astype='int32', # 数据类型转换
except_columns=['date', 'instrument'], # 跳过的列，不需要处理
# clip最后的数据，保证输入落到如下区间
clip_lower=0,
clip_upper=200000000
)
m7 = M.join.v3(
data1=m2.data,
data2=m15.data,
on='date,instrument',
how='inner',
sort=False
)
m13 = M.dropnan.v1(
input_data=m7.data
)
m9 = M.instruments.v2(
start_date=T.live_run_param('trading_date', '2016-01-01'),
end_date=T.live_run_param('trading_date', '2017-01-01'),
market='CN_STOCK_A',
instrument_list = conf.instruments,
max_count=0
)
m10 = M.general_feature_extractor.v6(
instruments=m9.data,
features=m3.data,
start_date='',
end_date='',
before_start_days=0
)
m11 = M.derived_feature_extractor.v2(
input_data=m10.data,
features=m3.data,
date_col='date',
instrument_col='instrument'
)
m14 = M.transform.v2(data=m11.data,
# stockranker 默认的转换函数，主要是将特征映射到非负整数区间，因为stockranker要求输入特征数据为非负整数
transforms=T.get_stock_ranker_default_transforms(),
drop_null=True, # 缺失数据处理，如果某一行有空列，则删除
astype='int32', # 数据类型转换
except_columns=['date', 'instrument'], # 跳过的列，不需要处理
# clip最后的数据，保证输入落到如下区间
clip_lower=0, clip_upper=200000000
)
m6 = M.stock_ranker_train.v5(
training_ds=m15.data,
features=m3.data,
learning_algorithm='排序',
number_of_leaves=30,
minimum_docs_per_leaf=1000,
number_of_trees=1000,
learning_rate=0.1,
max_bins=1023,
feature_fraction=1,
#m_lazy_run=False
)
print(m6.feature_gains.read_hdf())
m8 = M.stock_ranker_predict.v5(
model=m6.model,
data=m14.data,
#m_lazy_run=False
)
# 回测引擎：每日数据处理函数，每天执行一次
def m12_handle_data_bigquant_run(context, data):
# 按日期过滤得到今日的预测数据
ranker_prediction = context.ranker_prediction[
context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]
# 1. 资金分配
# 平均持仓时间是hold_days，每日都将买入股票，每日预期使用 1/hold_days 的资金
# 实际操作中，会存在一定的买入误差，所以在前hold_days天，等量使用资金；之后，尽量使用剩余资金（这里设置最多用等量的1.5倍）
is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间（前 hold_days 天）
cash_avg = context.portfolio.portfolio_value / context.options['hold_days']
cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)
cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)
positions = {e.symbol: p.amount * p.last_sale_price
for e, p in context.perf_tracker.position_tracker.positions.items()}
# 2. 生成卖出订单：hold_days天之后才开始卖出；对持仓的股票，按机器学习算法预测的排序末位淘汰
if not is_staging and cash_for_sell > 0:
equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}
instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
# print('rank order for sell %s' % instruments)
for instrument in instruments:
context.order_target(context.symbol(instrument), 0)
cash_for_sell -= positions[instrument]
if cash_for_sell <= 0:
break
# 3. 生成买入订单：按机器学习算法预测的排序，买入前面的stock_count只股票
buy_cash_weights = context.stock_weights
buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])
max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
for i, instrument in enumerate(buy_instruments):
cash = cash_for_buy * buy_cash_weights[i]
if cash > max_cash_per_instrument - positions.get(instrument, 0):
# 确保股票持仓量不会超过每次股票最大的占用资金量
cash = max_cash_per_instrument - positions.get(instrument, 0)
if cash > 0:
context.order_value(context.symbol(instrument), cash)
# 回测引擎：准备数据，只执行一次
def m12_prepare_bigquant_run(context):
pass
# 回测引擎：初始化函数，只执行一次
def m12_initialize_bigquant_run(context):
# 加载预测数据
context.ranker_prediction = context.options['data'].read_df()
# 系统已经设置了默认的交易手续费和滑点，要修改手续费可使用如下函数
context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
# 预测数据，通过options传入进来，使用 read_df 函数，加载到内存 (DataFrame)
# 设置买入的股票数量，这里买入预测股票列表排名靠前的5只
stock_count = 5
# 每只的股票的权重，如下的权重分配会使得靠前的股票分配多一点的资金，[0.339160, 0.213986, 0.169580, ..]
context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])
# 设置每只股票占用的最大资金比例
context.max_cash_per_instrument = 0.2
context.options['hold_days'] = 5
m12 = M.trade.v3(
instruments=m9.data,
options_data=m8.predictions,
start_date='',
end_date='',
handle_data=m12_handle_data_bigquant_run,
prepare=m12_prepare_bigquant_run,
initialize=m12_initialize_bigquant_run,
volume_limit=0.025,
order_price_field_buy='open',
order_price_field_sell='close',
capital_base=1000000,
benchmark='000300.SHA',
auto_cancel_non_tradable_orders=True,
data_frequency='daily',
price_type='后复权',
plot_charts=True,
backtest_only=False,
amount_integer=False
)
