复制链接
克隆策略

    {"description":"实验创建于2017/8/26","graph":{"edges":[{"to_node_id":"-36:features","from_node_id":"-331:data"},{"to_node_id":"-36:instruments","from_node_id":"-312:data"},{"to_node_id":"-36:user_functions","from_node_id":"-932:functions"}],"nodes":[{"node_id":"-331","module_id":"BigQuantSpace.input_features.input_features-v1","parameters":[{"name":"features","value":"_ret_log = np.log(close.pct_change().fillna(method='bfill'))\n_ret = close.pct_change().fillna(method='bfill')\n_rk1 = _ret.loc[93500:100000]\n_rk2 = _ret.loc[110000:113000]\n_rk3 = _ret.loc[143000:145700]\n\n# 高频波动- 收益波动因子\nret_vol = np.power(RVar(_ret), 0.5)\n\n# 高频上行波动-上行波动因子\nup_vol = np.sqrt(np.power(_ret*where(_ret>0, 1, 0), 2).sum())\n\n# 高频下行波动-下行波动因子\ndown_vol = np.sqrt(np.power(_ret*where(_ret<0, 1, 0), 2).sum())\n\n# 上行波动占比因子\n#up_vol_ratio = where(RVar(_ret)==0, 1, up_vol / RVar(_ret)) # hcd \nup_vol_ratio = where(RVar(_ret)==0, 1, np.power(up_vol,2) / RVar(_ret)) #sst\n\n\n# 下行波动占比因子\n#down_vol_ratio = where(RVar(_ret)==0, 1, down_vol / RVar(_ret)) #hcd\ndown_vol_ratio = where(RVar(_ret)==0, 1, np.power(down_vol,2) / RVar(_ret)) #sst\n\n\n\n\n\n","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"-331"}],"output_ports":[{"name":"data","node_id":"-331"}],"cacheable":true,"seq_num":1,"comment":"","comment_collapsed":true},{"node_id":"-312","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2020-03-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2020-05-01","type":"Literal","bound_global_parameter":null},{"name":"market","value":"CN_STOCK_A","type":"Literal","bound_global_parameter":null},{"name":"instrument_list","value":"000001.SZA\n000002.SZA\n000005.SZA","type":"Literal","bound_global_parameter":null},{"name":"max_count","value":0,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"rolling_conf","node_id":"-312"}],"output_ports":[{"name":"data","node_id":"-312"}],"cacheable":true,"seq_num":2,"comment":"","comment_collapsed":true},{"node_id":"-932","module_id":"BigQuantSpace.feature_extractor_user_function.feature_extractor_user_function-v1","parameters":[{"name":"name","value":"RVar","type":"Literal","bound_global_parameter":null},{"name":"func","value":"def bigquant_run(df, ret):\n return np.power(ret, 2).sum()\n","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_functions","node_id":"-932"}],"output_ports":[{"name":"functions","node_id":"-932"}],"cacheable":false,"seq_num":5,"comment":"","comment_collapsed":true},{"node_id":"-36","module_id":"BigQuantSpace.feature_extractor_1m.feature_extractor_1m-v2","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":"20","type":"Literal","bound_global_parameter":null},{"name":"workers","value":2,"type":"Literal","bound_global_parameter":null},{"name":"parallel_mode","value":"测试","type":"Literal","bound_global_parameter":null},{"name":"table_1m","value":"level2_bar1m_CN_STOCK_A","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-36"},{"name":"features","node_id":"-36"},{"name":"user_functions","node_id":"-36"}],"output_ports":[{"name":"data","node_id":"-36"}],"cacheable":true,"seq_num":6,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='-331' Position='-51.06403350830078,-52.102778911590576,200,200'/><node_position Node='-312' Position='-327.5753974914551,-46.94521427154541,200,200'/><node_position Node='-932' Position='237.74810791015625,-37.55187630653381,200,200'/><node_position Node='-36' Position='-46.95121765136719,120.8016357421875,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}
    In [14]:
    # 本代码由可视化策略环境自动生成 2022年11月18日 18:59
# 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。


def m5_func_bigquant_run(df, ret):
    return np.power(ret, 2).sum()


m1 = M.input_features.v1(
    features="""_ret_log = np.log(close.pct_change().fillna(method='bfill'))
_ret = close.pct_change().fillna(method='bfill')
_rk1 = _ret.loc[93500:100000]
_rk2 = _ret.loc[110000:113000]
_rk3 = _ret.loc[143000:145700]

# 高频波动- 收益波动因子
ret_vol = np.power(RVar(_ret), 0.5)

# 高频上行波动-上行波动因子
up_vol = np.sqrt(np.power(_ret*where(_ret>0, 1, 0), 2).sum())

# 高频下行波动-下行波动因子
down_vol = np.sqrt(np.power(_ret*where(_ret<0, 1, 0), 2).sum())

# 上行波动占比因子
#up_vol_ratio = where(RVar(_ret)==0, 1, up_vol / RVar(_ret)) # hcd 
up_vol_ratio = where(RVar(_ret)==0, 1, np.power(up_vol,2) / RVar(_ret)) #sst


# 下行波动占比因子
#down_vol_ratio = where(RVar(_ret)==0, 1, down_vol / RVar(_ret)) #hcd
down_vol_ratio = where(RVar(_ret)==0, 1, np.power(down_vol,2) / RVar(_ret)) #sst





"""
)

m2 = M.instruments.v2(
    start_date='2020-03-01',
    end_date='2020-05-01',
    market='CN_STOCK_A',
    instrument_list="""000001.SZA
000002.SZA
000005.SZA""",
    max_count=0
)

m5 = M.feature_extractor_user_function.v1(
    name='RVar',
    func=m5_func_bigquant_run
)

m6 = M.feature_extractor_1m.v2(
    instruments=m2.data,
    features=m1.data,
    user_functions=m5.functions,
    start_date='',
    end_date='',
    before_start_days=20,
    workers=2,
    parallel_mode='测试',
    table_1m='level2_bar1m_CN_STOCK_A'
)
    In [15]:
    dt = m6.data.read()
dt.shape, dt.date.min(), dt.date.max()
dt
    Out[15]:
    ret_vol up_vol down_vol up_vol_ratio down_vol_ratio date instrument
    0 0.015571 0.011097 0.010922 0.507954 0.492046 2020-02-10 000001.SZA
    1 0.027859 0.023014 0.015701 0.682373 0.317627 2020-02-10 000002.SZA
    2 0.046506 0.032360 0.033402 0.484169 0.515831 2020-02-10 000005.SZA
    3 0.018749 0.014083 0.012378 0.564187 0.435812 2020-02-11 000001.SZA
    4 0.025979 0.019466 0.017205 0.561418 0.438582 2020-02-11 000002.SZA
    ... ... ... ... ... ... ... ...
    169 0.016196 0.012253 0.010591 0.572350 0.427650 2020-04-29 000002.SZA
    170 0.039274 0.027835 0.027707 0.502316 0.497684 2020-04-29 000005.SZA
    171 0.021652 0.015422 0.015198 0.507340 0.492660 2020-04-30 000001.SZA
    172 0.014198 0.010013 0.010066 0.497342 0.502658 2020-04-30 000002.SZA
    173 0.036632 0.025681 0.026123 0.491458 0.508542 2020-04-30 000005.SZA

    174 rows × 7 columns

    In [8]:
    dt.head().T
    Out[8]:
    0 1 2 3 4
    ret_vol 0.015571 0.027859 0.046506 0.018749 0.025979
    up_vol 0.011097 0.023014 0.03236 0.014083 0.019466
    down_vol 0.010922 0.015701 0.033402 0.012378 0.017205
    up_vol_ratio 0.507954 0.682373 0.484169 0.564187 0.561418
    down_vol_ratio 0.492046 0.317627 0.515831 0.435812 0.438582
    date 2020-02-10 00:00:00 2020-02-10 00:00:00 2020-02-10 00:00:00 2020-02-11 00:00:00 2020-02-11 00:00:00
    instrument 000001.SZA 000002.SZA 000005.SZA 000001.SZA 000002.SZA
    In [9]:
    dt.isna().sum()
    Out[9]:
    ret_vol           0
up_vol            0
down_vol          0
up_vol_ratio      0
down_vol_ratio    0
date              0
instrument        0
dtype: int64
    In [10]:
    dt.describe().T
    Out[10]:
    count mean std min 25% 50% 75% max
    ret_vol 174.0 0.026355 0.010155 0.009907 0.017162 0.024761 0.034587 0.058712
    up_vol 174.0 0.019071 0.007660 0.007058 0.012720 0.018480 0.025069 0.049393
    down_vol 174.0 0.018069 0.006991 0.006952 0.011857 0.016529 0.024140 0.038609
    up_vol_ratio 174.0 0.524604 0.076069 0.329336 0.484230 0.515049 0.567403 0.739061
    down_vol_ratio 174.0 0.475396 0.076069 0.260939 0.432596 0.484951 0.515770 0.670664
    In [11]:
    dt2 = dt.set_index(['date','instrument'])
dt2.head()
    Out[11]:
    ret_vol up_vol down_vol up_vol_ratio down_vol_ratio
    date instrument
    2020-02-10 000001.SZA 0.015571 0.011097 0.010922 0.507954 0.492046
    000002.SZA 0.027859 0.023014 0.015701 0.682373 0.317627
    000005.SZA 0.046506 0.032360 0.033402 0.484169 0.515831
    2020-02-11 000001.SZA 0.018749 0.014083 0.012378 0.564187 0.435812
    000002.SZA 0.025979 0.019466 0.017205 0.561418 0.438582
    In [12]:
    import seaborn as sns
import matplotlib.pyplot as plt
    In [13]:
    # %%time
n=4#行数
m=dt2.shape[1]
x=m%n
fig,axes=plt.subplots(n,int((m - x + (n if x else x))/n),figsize=(20, 10))
axes=axes.reshape((-1,))
for i in range(dt2.shape[1]):    
    sns.distplot(dt2[dt2.columns[i]],ax=axes[i])
    In [51]:
    # for i in dt2.columns[:]:
#     dt2[i].to_hdf(f'XX券商-XXXX研报-{i}.h5', 'fac', mode='w')