python module pass basic test

python/example/demo.py

@@ -17,36 +17,17 @@ param = {'bst:max_depth':2, 'bst:eta':1, 'silent':1, 'objective':'binary:logisti
 # specify validations set to watch performance
 evallist  = [(dtest,'eval'), (dtrain,'train')]
 num_round = 2
-bst = xgb.train( param, dtrain, num_round, evallist )
+bst = xgb.train(param, dtrain, num_round, evallist)
 
 # this is prediction
-preds = bst.predict( dtest )
+preds = bst.predict(dtest)
 labels = dtest.get_label()
 print ('error=%f' % (  sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) /float(len(preds))))
 bst.save_model('0001.model')
 # dump model
 bst.dump_model('dump.raw.txt')
 # dump model with feature map
-bst.dump_model('dump.raw.txt','featmap.txt')
-
-###
-# build dmatrix in python iteratively
-#
-print ('start running example of build DMatrix in python')
-dtrain = xgb.DMatrix()
-labels = []
-for l in open('agaricus.txt.train'):
-    arr = l.split()
-    labels.append( int(arr[0]))
-    feats = []
-    for it in arr[1:]:
-        k,v = it.split(':')
-        feats.append( (int(k), float(v)) )
-    dtrain.add_row( feats )
-dtrain.set_label( labels )
-evallist  = [(dtest,'eval'), (dtrain,'train')]
-
-bst = xgb.train( param, dtrain, num_round, evallist )
+bst.dump_model('dump.nice.txt','featmap.txt')
 
 ###
 # build dmatrix from scipy.sparse
@@ -61,7 +42,6 @@ for l in open('agaricus.txt.train'):
         k,v = it.split(':')
         row.append(i); col.append(int(k)); dat.append(float(v))
     i += 1
-
 csr = scipy.sparse.csr_matrix( (dat, (row,col)) )
 dtrain = xgb.DMatrix( csr )
 dtrain.set_label(labels)
@@ -71,7 +51,7 @@ bst = xgb.train( param, dtrain, num_round, evallist )
 print ('start running example of build DMatrix from numpy array')
 # NOTE: npymat is numpy array, we will convert it into scipy.sparse.csr_matrix in internal implementation,then convert to DMatrix
 npymat = csr.todense()
-dtrain = xgb.DMatrix( npymat )
+dtrain = xgb.DMatrix( npymat)
 dtrain.set_label(labels)
 evallist  = [(dtest,'eval'), (dtrain,'train')]
 bst = xgb.train( param, dtrain, num_round, evallist )
@@ -81,16 +61,25 @@ bst = xgb.train( param, dtrain, num_round, evallist )
 # 
 print ('start running example to used cutomized objective function')
 
-# note: set objective= binary:logistic means the prediction will get logistic transformed
-#       in most case, we may want to leave it as default
-param = {'bst:max_depth':2, 'bst:eta':1, 'silent':1, 'objective':'binary:logistic' }
+# note: for customized objective function, we leave objective as default
+# note: what we are getting is margin value in prediction
+# you must know what you are doing
+param = {'bst:max_depth':2, 'bst:eta':1, 'silent':1 }
 
 # user define objective function, given prediction, return gradient and second order gradient
-def logregobj( preds, dtrain ):
+# this is loglikelihood loss
+def logregobj(preds, dtrain):
     labels = dtrain.get_label()
+    preds = 1.0 / (1.0 + np.exp(-preds))
     grad = preds - labels
     hess = preds * (1.0-preds)
     return grad, hess
 
-# training with customized objective, we can also do step by step training, simply look at xgboost.py's implementation of train
-bst = xgb.train( param, dtrain, num_round, evallist, logregobj )
+# user defined evaluation function, return a pair metric_name, result
+def evalerror(preds, dtrain):
+    labels = dtrain.get_label()
+    return 'error', float(sum(labels != (preds > 0.0))) / len(labels)
+
+# training with customized objective, we can also do step by step training
+# simply look at xgboost.py's implementation of train
+bst = xgb.train(param, dtrain, num_round, evallist, logregobj, evalerror)