Alexandr Savinov
Alexandr Savinov
Hi, good observation. It seems that the cause is trying to fit linear regression to a series consisting of one point: ```python from scipy import stats stats.linregress([0], [1]) # Bad...
Please post your configuration here, at least the "feature_sets" list. It seems that this section is not correctly formatted. A typical format for feature_sets is in the App.config: ``` "feature_sets":...
the functions of ``grid_search`` are in ``train_signals`` so I removed it.
Thank you for using the software. If you are using the latest version, then last error seems to be caused by incompatible config. The entry `buy_window` is moved to `score_aggregation.window`...
Use the latest version 0.5.0 and the latest config (structure). `json.decoder.JSONDecodeError: Extra data: line 81 column 2 (char 1906)` - here you have syntax error in your config. `ModuleNotFoundError: No...
Thanks! Indeed, it is a consequence of last changes in the config structure. I will fix this...
It is a bug while retrieving newly introduced parameters (score_aggregation). I fixed it but the current version is still not thoroughly tested because these changes are preparations to new features...
The results depend not only on the algorithms but also on features defined. The Telegram bot has used different configurations for experimenting and test purposes. Currently it uses neural network...
Currently only NN
I did not see big benefits from using linear classifier but it is slow to train. Actually I am using NN with only slightly more parameters than LC. For 1...