view release on metacpan or  search on metacpan

xgboost/tests/python/test_basic.py  view on Meta::CPAN

# -*- coding: utf-8 -*-
import numpy as np
import xgboost as xgb
import unittest
import itertools
import json

dpath = 'demo/data/'
rng = np.random.RandomState(1994)


class TestBasic(unittest.TestCase):

    def test_basic(self):
        dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
        dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
        param = {'max_depth': 2, 'eta': 1, 'silent': 1, 'objective': 'binary:logistic'}
        # specify validations set to watch performance
        watchlist = [(dtest, 'eval'), (dtrain, 'train')]
        num_round = 2
        bst = xgb.train(param, dtrain, num_round, watchlist)
        # this is prediction
        preds = bst.predict(dtest)
        labels = dtest.get_label()
        err = sum(1 for i in range(len(preds)) if int(preds[i] > 0.5) != labels[i]) / float(len(preds))
        # error must be smaller than 10%
        assert err < 0.1

        # save dmatrix into binary buffer
        dtest.save_binary('dtest.buffer')
        # save model
        bst.save_model('xgb.model')
        # load model and data in
        bst2 = xgb.Booster(model_file='xgb.model')
        dtest2 = xgb.DMatrix('dtest.buffer')
        preds2 = bst2.predict(dtest2)
        # assert they are the same
        assert np.sum(np.abs(preds2 - preds)) == 0

    def test_record_results(self):
        dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
        dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
        param = {'max_depth': 2, 'eta': 1, 'silent': 1, 'objective': 'binary:logistic'}
        # specify validations set to watch performance
        watchlist = [(dtest, 'eval'), (dtrain, 'train')]
        num_round = 2
        result = {}
        res2 = {}
        xgb.train(param, dtrain, num_round, watchlist,
                  callbacks=[xgb.callback.record_evaluation(result)])
        xgb.train(param, dtrain, num_round, watchlist,
                  evals_result=res2)
        assert result['train']['error'][0] < 0.1
        assert res2 == result

    def test_multiclass(self):
        dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
        dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
        param = {'max_depth': 2, 'eta': 1, 'silent': 1, 'num_class': 2}
        # specify validations set to watch performance
        watchlist = [(dtest, 'eval'), (dtrain, 'train')]
        num_round = 2
        bst = xgb.train(param, dtrain, num_round, watchlist)
        # this is prediction
        preds = bst.predict(dtest)
        labels = dtest.get_label()
        err = sum(1 for i in range(len(preds)) if preds[i] != labels[i]) / float(len(preds))
        # error must be smaller than 10%
        assert err < 0.1

        # save dmatrix into binary buffer
        dtest.save_binary('dtest.buffer')
        # save model
        bst.save_model('xgb.model')
        # load model and data in
        bst2 = xgb.Booster(model_file='xgb.model')
        dtest2 = xgb.DMatrix('dtest.buffer')
        preds2 = bst2.predict(dtest2)
        # assert they are the same
        assert np.sum(np.abs(preds2 - preds)) == 0

    def test_dmatrix_init(self):
        data = np.random.randn(5, 5)

        # different length
        self.assertRaises(ValueError, xgb.DMatrix, data,
                          feature_names=list('abcdef'))
        # contains duplicates
        self.assertRaises(ValueError, xgb.DMatrix, data,
                          feature_names=['a', 'b', 'c', 'd', 'd'])
        # contains symbol
        self.assertRaises(ValueError, xgb.DMatrix, data,
                          feature_names=['a', 'b', 'c', 'd', 'e<1'])

        dm = xgb.DMatrix(data)
        dm.feature_names = list('abcde')
        assert dm.feature_names == list('abcde')

        dm.feature_types = 'q'
        assert dm.feature_types == list('qqqqq')

        dm.feature_types = list('qiqiq')
        assert dm.feature_types == list('qiqiq')

        def incorrect_type_set():
            dm.feature_types = list('abcde')

        self.assertRaises(ValueError, incorrect_type_set)

        # reset