secs = int(train_time % 60)
print('training error: ' + str(mins) + 'm ' + str(secs) + 's')
start_time = time.time()
auc, rmse = get_err_bat(test_file)
test_time = time.time() - start_time
mins = int(test_time / 60)
secs = int(test_time % 60)
log_p( 'Test Err:' + str(i) + '\t' + str(auc) + '\t' + str(rmse))
print( 'test error: ' + str(mins) + 'm ' + str(secs) + 's')
#stop training when no improvement for a while
if auc>min_err:
best_w1=w1t
best_w2=w2t
best_w3=w3t
best_b1=b1t
best_b2=b2t
best_b3=b3t
min_err=auc
min_err_epoch=i
if times_reduce<3:
times_reduce+=1
else:
times_reduce-=1
if times_reduce<0:
break
log_p( 'Minimal test error is '+ str( min_err)+' , at EPOCH ' + str(min_err_epoch))
ut.save_weights("mlp3fm_train_"+advertiser+".p",get_pred(train_file,best_w1,best_w2,best_w3,best_b1,best_b2,best_b3))
ut.save_weights("mlp3fm_test_"+advertiser+".p",get_pred(test_file,best_w1,best_w2,best_w3,best_b1,best_b2,best_b3))
secs = int(train_time % 60)
print 'training error: ' + str(mins) + 'm ' + str(secs) + 's'
start_time = time.time()
auc, rmse = get_err_bat(test_file)
test_time = time.time() - start_time
mins = int(test_time / 60)
secs = int(test_time % 60)
ut.log_p( 'Test Err:' + str(i) + '\t' + str(auc) + '\t' + str(rmse))
print 'test error: ' + str(mins) + 'm ' + str(secs) + 's'
#stop training when no improvement for a while
if auc>min_err:
best_w1=w1t
best_w2=w2t
best_w3=w3t
best_b1=b1t
best_b2=b2t
best_b3=b3t
min_err=auc
min_err_epoch=i
if times_reduce<3:
times_reduce+=1
else:
times_reduce-=1
if times_reduce<0:
break
ut.log_p( 'Minimal test error is '+ str( min_err)+' , at EPOCH ' + str(min_err_epoch))
ut.save_weights("mlp3fm_train_"+advertiser+".p",get_pred(train_file,best_w1,best_w2,best_w3,best_b1,best_b2,best_b3))
ut.save_weights("mlp3fm_test_"+advertiser+".p",get_pred(test_file,best_w1,best_w2,best_w3,best_b1,best_b2,best_b3))
clk = data[0]
pclk = pred(data[1])[0]
y.append(clk)
yp.append(pclk)
fi.close()
auc = roc_auc_score(y, yp)
rmse = math.sqrt(mean_squared_error(y, yp))
print '%d\t%.8f\t%.8f\t%dm%ds' % (round, auc, rmse, train_min, train_sec)
fo.write('%d\t%.8f\t%.8f\t%dm%ds\n' % (round, auc, rmse, train_min, train_sec))
fo.flush()
if overfitting and auc < best_auc:
print 'rewriting ' + trainlog_file + ' into ' + traindl_file
rewrite_train_test(trainlog_file, traindl_file)
print 'rewriting ' + testlog_file + ' into ' + testdl_file
rewrite_train_test(testlog_file, testdl_file)
print 'output model into ' + model_file
output_model(model_file)
break # stop training when overfitting two rounds already
if auc > best_auc:
best_auc = auc
best_w=w
best_v=v
best_w_0=w_0
overfitting = False
else:
overfitting = True
ut.save_weights("fm_train_"+advertiser+".p",pred_all(train_file,best_w,best_v,best_w_0))
ut.save_weights("fm_test_"+advertiser+".p",pred_all(test_file,best_w,best_v,best_w_0))
fo.close()
