51 lines
1.6 KiB
Python
Executable File
51 lines
1.6 KiB
Python
Executable File
#! /usr/bin/python
|
|
import sys
|
|
import numpy as np
|
|
sys.path.append('../../python/')
|
|
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 } )
|
|
sz = data.shape
|
|
|
|
train = data[:int(sz[0] * 0.7), :]
|
|
test = data[int(sz[0] * 0.7):, :]
|
|
|
|
train_X = train[:,0:33]
|
|
train_Y = train[:, 34]
|
|
|
|
|
|
test_X = test[:,0:33]
|
|
test_Y = test[:, 34]
|
|
|
|
xg_train = xgb.DMatrix( train_X, label=train_Y)
|
|
xg_test = xgb.DMatrix(test_X, label=test_Y)
|
|
# setup parameters for xgboost
|
|
param = {}
|
|
# use softmax multi-class classification
|
|
param['objective'] = 'multi:softmax'
|
|
# scale weight of positive examples
|
|
param['bst:eta'] = 0.1
|
|
param['bst:max_depth'] = 6
|
|
param['silent'] = 1
|
|
param['nthread'] = 4
|
|
param['num_class'] = 6
|
|
|
|
watchlist = [ (xg_train,'train'), (xg_test, 'test') ]
|
|
num_round = 5
|
|
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)) ))
|
|
|
|
# do the same thing again, but output probabilities
|
|
param['objective'] = 'multi:softprob'
|
|
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)) ))
|