Question about the mix_index_state

[ceruleanacg]

Question about the mix_index_state

[Ceruleanacg]

Sorry! That’s my fault, I wrote a bug when adding the feature of `mix_index_state`, now it has been fixed, sorry for that.

…

在 2018年5月16日，上午1:38，JS00000 ***@***.***> 写道： Can we set mix_index_state=false? But if I did this, something got wrong. Traceback (most recent call last): File "algorithm/SL/NaiveLSTM.py", line 108, in <module> main(model_launcher_parser.parse_args()) File "algorithm/SL/NaiveLSTM.py", line 103, in main algorithm.run() File "/Users/yyx/Documents/Code/python/price_prediction/Personae/base/algorithm/model.py", line 242, in run self.train() File "algorithm/SL/NaiveLSTM.py", line 55, in train _, loss = self.session.run([self.train_op, self.loss], feed_dict={self.x: batch_x, self.label: batch_y}) File "/Users/yyx/anaconda/envs/py35/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 889, in run run_metadata_ptr) File "/Users/yyx/anaconda/envs/py35/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1096, in _run % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape()))) ValueError: Cannot feed value of shape (32, 1) for Tensor 'Placeholder_1:0', which has shape '(?, 2)' — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#15 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AD3en1-uiD78eRfM3lLoS14ITZAGcmmrks5tywSRgaJpZM4T-4o8>.

[Ceruleanacg]

Sorry for the confusing parameters in the options, I have not updated the options doc in time.

mix_index_state is a option that decides whether the state or sequence data will concatenate index data like SH000001.

• Whether the code 'sh' is a stock/future index data
  sh here is index code of 000001.

• If yes, how can I get it and why you use it
  you can run the spider setting the code to be 000001 to get sh, the reason why I use it is that this mixture might give the agent or predictor a big picture of market.

Thank you very much.