# 本代码由可视化策略环境自动生成 2022年1月23日 17:37
# 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。


# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m6_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    df = input_1.read_df()
    ins = m1.data.read_pickle()['instruments']
    start = m1.data.read_pickle()['start_date']
    end = m1.data.read_pickle()['end_date']
    
    df1 = D.features(ins,start,end,fields=['rank_turn_0','rank_amount_0','st_status_0'])
    df_final = pd.merge(df,df1,on=['date','instrument'])
    df_final = df_final[df_final['instrument'].str.startswith("688") == False]
    df_final = df_final[df_final['instrument'].str.startswith("3") == False]

    df_final = df_final[df_final["st_status_0"] == 0]
    df_final = df_final[df_final['rank_turn_0'] >= 0.9]
    df_final = df_final[df_final['rank_amount_0'] >= 0.85]
    print("用于训练的样本总个数为",len(df_final))
    print(df_final.iloc[0])
    data_1 = DataSource.write_df(df_final)
    return Outputs(data_1=data_1, data_2=None, data_3=None)

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m6_post_run_bigquant_run(outputs):
    return outputs

# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m8_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    df = input_1.read_df()
    ins = m9.data.read_pickle()['instruments']
    start = m9.data.read_pickle()['start_date']
    end = m9.data.read_pickle()['end_date']
    
    df1 = D.features(ins,start,end,fields=['rank_turn_0','rank_amount_0','st_status_0'])
    df_final = pd.merge(df,df1,on=['date','instrument'])
    df_final = df_final[df_final['instrument'].str.startswith("688") == False]
    df_final = df_final[df_final['instrument'].str.startswith("3") == False]

    df_final = df_final[df_final["st_status_0"] == 0]
    df_final = df_final[df_final['rank_turn_0'] >= 0.9]
    df_final = df_final[df_final['rank_amount_0'] >= 0.85]
    print("用于回测的样本总个数为",len(df_final))
    data_1 = DataSource.write_df(df_final)
    return Outputs(data_1=data_1, data_2=None, data_3=None)

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m8_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m4_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))

    # 持股数
    context.stock_num = 10
    #权重
    context.weight = 1 / context.stock_num
    #计数
    context.count = 0
    #最小持仓天数
    context.min_hold_days = 15
    #股票最近卖出日
    context.sell_date = {}
    #股票最少买入日
    context.min_sell_days = 15

# 回测引擎：每日数据处理函数，每天执行一次
def m4_handle_data_bigquant_run(context, data):
    # 按日期过滤得到今日的预测数据
    today = data.current_dt.strftime('%Y-%m-%d')

    #含有买入时间的持仓信息
    positions_lastdate = {e.symbol:p.last_sale_date for e,p in context.portfolio.positions.items()}
    
    ranker_prediction = context.ranker_prediction[context.ranker_prediction.date == today]
    
    hold_stocks = list(positions_lastdate.keys())

    #卖出分位数过滤
    threshold_sell = ranker_prediction['position'].quantile(q=0.3)
    sell_df = ranker_prediction[ranker_prediction['position']>threshold_sell]
    sell_stocks = list(sell_df.instrument)
    sell_stocks = list(set(hold_stocks).intersection(set(sell_stocks)))
    #卖出
    for instrument in sell_stocks:
        #满足持仓天数大于指定天数
        if data.current_dt - positions_lastdate[instrument]>=datetime.timedelta(context.min_hold_days):
            context.order_target(context.symbol(instrument), 0)
            #保存卖出时间
            context.sell_date[instrument] = data.current_dt
        else:
            print(instrument,"持仓不足天数，不能卖出!","买入时间:",positions_lastdate[instrument],"当前时间:",data.current_dt)
            pass
    need_buy_num = context.stock_num - len(hold_stocks) + len(sell_stocks)
    #买入分位数过滤
    threshold_buy = ranker_prediction['position'].quantile(q=0.01)
    buy_df = ranker_prediction[ranker_prediction['position']<threshold_buy]
    buy_stocks = list(buy_df.instrument)
    if(len(buy_stocks)>need_buy_num):
        buy_stocks = buy_stocks[0:need_buy_num]

    #买入
    for instrument in buy_stocks:
        sell_date = context.sell_date.get(instrument)
        if sell_date!=None and data.current_dt - sell_date<datetime.timedelta(context.min_sell_days):
            print(instrument,"不足天数不能买入！：","卖出时间:",sell_date,"当前时间:",data.current_dt)
            continue
        context.order_target_percent(context.symbol(instrument), context.weight)


# 回测引擎：准备数据，只执行一次
def m4_prepare_bigquant_run(context):
    pass


m1 = M.instruments.v2(
    start_date='2014-01-01',
    end_date='2019-1-01',
    market='CN_STOCK_A',
    instrument_list='',
    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, -2) / 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, 0.03))

# 将分数映射到分类，这里使用20个分类
all_wbins(label, 20)

# 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="""
shift(stock_status_CN_STOCK_A__price_limit_status, 10)

# return_10"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=0
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m16.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m6 = M.cached.v3(
    input_1=m7.data,
    run=m6_run_bigquant_run,
    post_run=m6_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2019-01-01'),
    end_date=T.live_run_param('trading_date', '2025-01-01'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=30
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m8 = M.cached.v3(
    input_1=m18.data,
    run=m8_run_bigquant_run,
    post_run=m8_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m10 = M.lightgbm.v2(
    training_ds=m6.data_1,
    features=m3.data,
    predict_ds=m8.data_1,
    num_boost_round=79,
    objective='排序(ndcg)',
    num_class=1,
    num_leaves=60,
    learning_rate=0.1,
    min_data_in_leaf=900,
    max_bin=1023,
    key_cols='date,instrument',
    group_col='date',
    random_seed=101,
    other_train_parameters={'n_jobs':4,'label_gain':','.join([str(x) for x in range(20)]),"max_position":29,"eval_at":"1,3,5,10"}
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m10.predictions,
    start_date='2019-01-01',
    end_date='2022-03-07',
    initialize=m19_initialize_bigquant_run,
    handle_data=m19_handle_data_bigquant_run,
    prepare=m19_prepare_bigquant_run,
    before_trading_start=m19_before_trading_start_bigquant_run,
    volume_limit=1,
    order_price_field_buy='open',
    order_price_field_sell='open',
    capital_base=10000,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.SHA'
)