遗传算法在因子投资中的应用

策略分享
标签: #<Tag:0x00007f520931e8b0>

(brucemeerkat) #1

https://i.bigquant.com/user/brucemeerkat/lab/share/%E5%8F%AF%E8%A7%86%E5%8C%96%E7%AD%96%E7%95%A5-AI%E9%80%89%E8%82%A1-Copy1.ipynb?_t=1562577090248

# 本代码由可视化策略环境自动生成 2019年7月8日 19:38
# 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。


# 回测引擎:初始化函数,只执行一次
def m9_initialize_bigquant_run(context):
    # 加载预测数据
    context.ranker_prediction = context.options['data'].read_pickle()['prediction']
    context.gp_model = context.options['data'].read_pickle()['gp_model']
    print('gp_model 1:', context.gp_model)
    # 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.hold_days = 5

# 回测引擎:每日数据处理函数,每天执行一次
def m9_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.hold_days # 是否在建仓期间(前 hold_days 天)
    cash_avg = context.portfolio.portfolio_value / context.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StockRanker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StockRanker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 m9_prepare_bigquant_run(context):
    pass

# 回测引擎:每个单位时间开始前调用一次,即每日开盘前调用一次。
def m9_before_trading_start_bigquant_run(context, data):
    pass

# 回测引擎:初始化函数,只执行一次
def m10_initialize_bigquant_run(context):
    # 加载预测数据
    context.ranker_prediction = context.options['data'].read_pickle()['prediction']
    context.gp_model = context.options['data'].read_pickle()['gp_model']
    print('gp_model 2:', context.gp_model)
    # 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.hold_days = 5

# 回测引擎:每日数据处理函数,每天执行一次
def m10_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.hold_days # 是否在建仓期间(前 hold_days 天)
    cash_avg = context.portfolio.portfolio_value / context.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StockRanker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StockRanker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 m10_prepare_bigquant_run(context):
    pass

# 回测引擎:每个单位时间开始前调用一次,即每日开盘前调用一次。
def m10_before_trading_start_bigquant_run(context, data):
    pass


m1 = M.instruments.v2(
    start_date='2016-01-01',
    end_date='2017-01-31',
    market='CN_STOCK_A',
    instrument_list=''
)

m2 = M.instruments.v2(
    start_date='2017-01-31',
    end_date='2018-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m7 = M.factor_select.v16(
    feature=['alpha001', 'alpha002', 'alpha003']
)

m3 = M.input_features.v1(
    features_ds=m7.data,
    features="""price

"""
)

m5 = M.use_datasource.v1(
    instruments=m1.data,
    features=m3.data,
    datasource_id='factor_CN_STOCK_A',
    start_date='',
    end_date=''
)

m4 = M.gplearn_train.v1(
    input_1=m5.data,
    input_2=m7.data,
    IS_USE_BEST_GP=True,
    gnrtn=3,
    ppltn=80,
    max_samples=0.9,
    metric='rmse',
    stopping_criteria=0.01,
    init_depth_min=2,
    init_depth_max=6,
    p_crossover=0.9,
    p_hoist_mutation=0.01,
    p_point_mutation=0.05,
    p_point_replace=0.01,
    p_subtree_mutation=0.01
)

m9 = M.trade.v4(
    instruments=m1.data,
    options_data=m4.data_2,
    start_date='',
    end_date='',
    initialize=m9_initialize_bigquant_run,
    handle_data=m9_handle_data_bigquant_run,
    prepare=m9_prepare_bigquant_run,
    before_trading_start=m9_before_trading_start_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='close',
    order_price_field_sell='close',
    capital_base=1000000,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='后复权',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.HIX'
)

m6 = M.use_datasource.v1(
    instruments=m2.data,
    features=m3.data,
    datasource_id='factor_CN_STOCK_A',
    start_date='',
    end_date=''
)

m8 = M.GP_predict.v1(
    input_1=m4.data_1,
    input_2=m7.data,
    input_3=m6.data
)

m10 = M.trade.v4(
    instruments=m2.data,
    options_data=m8.data_1,
    start_date='',
    end_date='',
    initialize=m10_initialize_bigquant_run,
    handle_data=m10_handle_data_bigquant_run,
    prepare=m10_prepare_bigquant_run,
    before_trading_start=m10_before_trading_start_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='close',
    order_price_field_sell='close',
    capital_base=1000000,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='后复权',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.HIX'
)