Closed oppsig closed 4 years ago
Ok so i got a bit further. My prosessor is kinda old, it's a qx9850. So i had to downgrade tensorflow-gpu to 1.5 because of avx issue with older processors.
root@b1efe70104d6:/app/alphapy/examples/Trading Model# mflow --predict /usr/local/lib/python2.7/dist-packages/sklearn/ensemble/weight_boosting.py:29: DeprecationWarning: numpy.core.umath_tests is an internal NumPy module and should not be imported. It will be removed in a future NumPy release. from numpy.core.umath_tests import inner1d Using TensorFlow backend. None [11/01/18 17:58:54] INFO ******************************************************************************** [11/01/18 17:58:54] INFO MarketFlow Start [11/01/18 17:58:54] INFO ******************************************************************************** [11/01/18 17:58:54] INFO Training Date: 1900-01-01 [11/01/18 17:58:54] INFO Prediction Date: 2018-11-01 [11/01/18 17:58:54] INFO MarketFlow Configuration Traceback (most recent call last): File "/usr/local/bin/mflow", line 11, in <module> sys.exit(main()) File "/usr/local/lib/python2.7/dist-packages/alphapy/market_flow.py", line 394, in main market_specs = get_market_config() File "/usr/local/lib/python2.7/dist-packages/alphapy/market_flow.py", line 106, in get_market_config specs['forecast_period'] = cfg['market']['forecast_period'] KeyError: 'forecast_period'
This happends when i launch mflow --predict.