Minor cleanup (dmlc#2342)

* Clean up demo of multiclass classification

* Remove extra space

Author: Juang, Yi-Lin

demo/multiclass_classification/train.py

@@ -1,22 +1,25 @@
-#! /usr/bin/python
+#!/usr/bin/python
+
+from __future__ import division
+
 import numpy as np
 import xgboost as xgb
 
 # label need to be 0 to num_class -1
-data = np.loadtxt('./dermatology.data', delimiter=',',converters={33: lambda x:int(x == '?'), 34: lambda x:int(x)-1 } )
+data = np.loadtxt('./dermatology.data', delimiter=',',
+        converters={33: lambda x:int(x == '?'), 34: lambda x:int(x)-1})
 sz = data.shape
 
 train = data[:int(sz[0] * 0.7), :]
 test = data[int(sz[0] * 0.7):, :]
 
-train_X = train[:,0:33]
+train_X = train[:, :33]
 train_Y = train[:, 34]
 
-
-test_X = test[:,0:33]
+test_X = test[:, :33]
 test_Y = test[:, 34]
 
-xg_train = xgb.DMatrix( train_X, label=train_Y)
+xg_train = xgb.DMatrix(train_X, label=train_Y)
 xg_test = xgb.DMatrix(test_X, label=test_Y)
 # setup parameters for xgboost
 param = {}
@@ -29,20 +32,20 @@
 param['nthread'] = 4
 param['num_class'] = 6
 
-watchlist = [ (xg_train,'train'), (xg_test, 'test') ]
+watchlist = [(xg_train, 'train'), (xg_test, 'test')]
 num_round = 5
-bst = xgb.train(param, xg_train, num_round, watchlist );
+bst = xgb.train(param, xg_train, num_round, watchlist)
 # get prediction
-pred = bst.predict( xg_test );
-
-print ('predicting, classification error=%f' % (sum( int(pred[i]) != test_Y[i] for i in range(len(test_Y))) / float(len(test_Y)) ))
+pred = bst.predict(xg_test)
+error_rate = np.sum(pred != test_Y) / test_Y.shape[0]
+print('Test error using softmax = {}'.format(error_rate))
 
 # do the same thing again, but output probabilities
 param['objective'] = 'multi:softprob'
-bst = xgb.train(param, xg_train, num_round, watchlist );
+bst = xgb.train(param, xg_train, num_round, watchlist)
 # Note: this convention has been changed since xgboost-unity
 # get prediction, this is in 1D array, need reshape to (ndata, nclass)
-yprob = bst.predict( xg_test ).reshape( test_Y.shape[0], 6 )
-ylabel = np.argmax(yprob, axis=1)
-
-print ('predicting, classification error=%f' % (sum( int(ylabel[i]) != test_Y[i] for i in range(len(test_Y))) / float(len(test_Y)) ))
+pred_prob = bst.predict(xg_test).reshape(test_Y.shape[0], 6)
+pred_label = np.argmax(pred_prob, axis=1)
+error_rate = np.sum(pred != test_Y) / test_Y.shape[0]
+print('Test error using softprob = {}'.format(error_rate))

python-package/xgboost/core.py

@@ -848,7 +848,7 @@ def boost(self, dtrain, grad, hess):
 
     def eval_set(self, evals, iteration=0, feval=None):
         # pylint: disable=invalid-name
-        """Evaluate  a set of data.
+        """Evaluate a set of data.
 
         Parameters
         ----------