some results running on the linux laptop with the new model:

[email protected]5548:~/code$ python3 newlfmodelradius.py
/home/liu/.local/lib/python3.5/site-packages/sklearn/cross_validation.py:41: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface
 
 of the new CV iterators are different from that of this module. This module will be removed in 0.20.
  "This module will be removed in 0.20.", DeprecationWarning)
this is test for new lightfm, 10000 checkins,and radius as 10
unique user&venue checkin combination in test 1414
unique user&venue checkin combination in
 
 test 5654
max num in matrix 14
max num in train 13
I am beginning to get negtive examples
object preprocess created
get neighbor time used: 1896.430985
Time used for negative examples: 1908.565092
I am beginning to model,this is the new model
model has been fitted
this is the model that consider the checkin times
Time used: 
 
0.7560190000001512
Train_auc is 0.545424
test auc is 0.465073

the same data with the original lightfm model:

unique user&venue checkin combination in test 1414
unique user&venue checkin combination in test 5654
max num in matrix 13
max num in train 14
I am beginning to model
model has been fitted
this is the model that consider the checkin times
Time used: 2.494451837632795
Train_auc is 0.999937
Test_aus is 0.329455
train prek is 0.545433
test prek is 0.001780

new lightfm model with different radius(updated 29th,Aug)