vkantor / MIPT_Data_Mining_In_Action_2016

"Data Mining in Action Course", Moscow Institute of Physics and Technologies
209 stars 175 forks source link

theano, логрегрессия #34

Closed tveritinova closed 7 years ago

tveritinova commented 7 years ago

Ошибка в логрегрессии в задании по theano. Не представляю, что с этим делать :(


UnicodeEncodeError Traceback (most recent call last)

in () 2 3 for i in range(5): ----> 4 loss_i = train_function(X_train,y_train) 5 print "loss at iter %i:%.4f"%(i,loss_i) 6 print "train auc:",roc_auc_score(y_train,predict_function(X_train)) /Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/theano/compile/function_module.pyc in __call__(self, *args, **kwargs) 869 node=self.fn.nodes[self.fn.position_of_error], 870 thunk=thunk, --> 871 storage_map=getattr(self.fn, 'storage_map', None)) 872 else: 873 # old-style linkers raise their own exceptions /Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/theano/gof/link.pyc in raise_with_op(node, thunk, exc_info, storage_map) 176 for subtr in tr: 177 traceback.print_list(subtr, sio) --> 178 detailed_err_msg += str(sio.getvalue()) 179 else: 180 hints.append( UnicodeEncodeError: 'ascii' codec can't encode characters in position 1486-1498: ordinal not in range(128)
senya-ashukha commented 7 years ago

Код что-ли скинь

tveritinova commented 7 years ago

https://github.com/tveritinova/MIPT_Data_Mining_In_Action_2016/blob/master/trends/hw1/theano.ipynb в конце

senya-ashukha commented 7 years ago

Привет, да ошибка тупая, на вскидку несколько проблем