新版的stockranker DAI如何固化模型

由bq8ispcb创建，最终由small_q更新于2024-01-11 07:52 被浏览 18 用户

如结果为m5.stockRanker(DAI）

用m5.model获取DataSource

import pandas as pd
pd.DataFrame([DataSource("datasource的name").read()]).to_pickle('/home/bigquant/work/userlib/model.csv') 

再在自定义python模块中输入以下内容是吗

def bigquant_run(input_1, input_2, input_3):
    data = pd.read_pickle('/home/bigquant/work/userlib/RF_model.csv')
    model_ds = DataSource.write_pickle(data.iloc[0].to_dict())
    return Outputs(data_1=model_ds)

但报错显示

319 def decode(self, input, final=False): 320 # decode input (taking the buffer into account) 321 data = self.buffer + input --> 322 (result, consumed) = self._buffer_decode(data, self.errors, final) 323 # keep undecoded input until the next call 324 self.buffer = data[consumed:] UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte

为什么会编码不对呢，新版的DAI好像可视化分享不出来

另外想问下，新版的dai只能回测，暂不支持模拟是吗

https://bigquant.com/codeshare/2fd4ddee-02d0-4c9d-bdc0-2be5929aec4d

\