1import numpy as np 2import scipy.sparse 3import pickle 4import xgboost as xgb 5import os 6 7# Make sure the demo knows where to load the data. 8CURRENT_DIR = os.path.dirname(os.path.abspath(__file__)) 9XGBOOST_ROOT_DIR = os.path.dirname(os.path.dirname(CURRENT_DIR)) 10DEMO_DIR = os.path.join(XGBOOST_ROOT_DIR, 'demo') 11 12# simple example 13# load file from text file, also binary buffer generated by xgboost 14dtrain = xgb.DMatrix(os.path.join(DEMO_DIR, 'data', 'agaricus.txt.train?indexing_mode=1')) 15dtest = xgb.DMatrix(os.path.join(DEMO_DIR, 'data', 'agaricus.txt.test?indexing_mode=1')) 16 17# specify parameters via map, definition are same as c++ version 18param = {'max_depth': 2, 'eta': 1, 'objective': 'binary:logistic'} 19 20# specify validations set to watch performance 21watchlist = [(dtest, 'eval'), (dtrain, 'train')] 22num_round = 2 23bst = xgb.train(param, dtrain, num_round, watchlist) 24 25# this is prediction 26preds = bst.predict(dtest) 27labels = dtest.get_label() 28print('error=%f' % 29 (sum(1 for i in range(len(preds)) if int(preds[i] > 0.5) != labels[i]) / 30 float(len(preds)))) 31bst.save_model('0001.model') 32# dump model 33bst.dump_model('dump.raw.txt') 34# dump model with feature map 35bst.dump_model('dump.nice.txt', os.path.join(DEMO_DIR, 'data/featmap.txt')) 36 37# save dmatrix into binary buffer 38dtest.save_binary('dtest.buffer') 39# save model 40bst.save_model('xgb.model') 41# load model and data in 42bst2 = xgb.Booster(model_file='xgb.model') 43dtest2 = xgb.DMatrix('dtest.buffer') 44preds2 = bst2.predict(dtest2) 45# assert they are the same 46assert np.sum(np.abs(preds2 - preds)) == 0 47 48# alternatively, you can pickle the booster 49pks = pickle.dumps(bst2) 50# load model and data in 51bst3 = pickle.loads(pks) 52preds3 = bst3.predict(dtest2) 53# assert they are the same 54assert np.sum(np.abs(preds3 - preds)) == 0 55 56### 57# build dmatrix from scipy.sparse 58print('start running example of build DMatrix from scipy.sparse CSR Matrix') 59labels = [] 60row = [] 61col = [] 62dat = [] 63i = 0 64for l in open(os.path.join(DEMO_DIR, 'data', 'agaricus.txt.train')): 65 arr = l.split() 66 labels.append(int(arr[0])) 67 for it in arr[1:]: 68 k, v = it.split(':') 69 row.append(i) 70 col.append(int(k)) 71 dat.append(float(v)) 72 i += 1 73csr = scipy.sparse.csr_matrix((dat, (row, col))) 74dtrain = xgb.DMatrix(csr, label=labels) 75watchlist = [(dtest, 'eval'), (dtrain, 'train')] 76bst = xgb.train(param, dtrain, num_round, watchlist) 77 78print('start running example of build DMatrix from scipy.sparse CSC Matrix') 79# we can also construct from csc matrix 80csc = scipy.sparse.csc_matrix((dat, (row, col))) 81dtrain = xgb.DMatrix(csc, label=labels) 82watchlist = [(dtest, 'eval'), (dtrain, 'train')] 83bst = xgb.train(param, dtrain, num_round, watchlist) 84 85print('start running example of build DMatrix from numpy array') 86# NOTE: npymat is numpy array, we will convert it into scipy.sparse.csr_matrix 87# in internal implementation then convert to DMatrix 88npymat = csr.todense() 89dtrain = xgb.DMatrix(npymat, label=labels) 90watchlist = [(dtest, 'eval'), (dtrain, 'train')] 91bst = xgb.train(param, dtrain, num_round, watchlist) 92