XGBoost 模型保存，读取

一个数据集可以分为训练集和验证集，训练完模型后，放到测试集上做预测。

#!/usr/bin/python
import numpy as np
import scipy.sparse
import pickle
import xgboost as xgb

### simple example
# load file from text file, also binary buffer generated by xgboost
dtrain = xgb.DMatrix('../data/agaricus.txt.train')
dtest = xgb.DMatrix('../data/agaricus.txt.test')
#自己读文件（Xtrain是除label外的数据）
#dmatrix_train=xgb.DMatrix(Xtrain,label=ytrain,feature_names=Xtrain.columns.values)
#dmatrix_test=xgb.DMatrix(Xtest,label=ytest)


# specify parameters via map, definition are same as c++ version
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}

# specify validations set to watch performance（查看训练集上和验证集上的分数，train上会一直下降，验证集上不一定）
watchlist = [(dtest, 'eval'), (dtrain, 'train')]

#指定查看验证集的分数，配合使用早停法
#watchlist = [(dmatrix_test, 'eval')]


num_round = 2000
bst = xgb.train(param, dtrain, num_round, watchlist)
#bst=xgb.train(params,dmatrix_train,num_rounds,watchlist,early_stopping_rounds=20)

# this is prediction（验证集上真实值和预测值做比较）
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))))

#模型保存
bst.save_model('0001.model')
# dump model
bst.dump_model('dump.raw.txt')
# dump model with feature map
bst.dump_model('dump.nice.txt', '../data/featmap.txt')
# save dmatrix into binary buffer（数据集保存）
dtest.save_binary('dtest.buffer')

#看这里
# 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

# alternatively, you can pickle the booster
pks = pickle.dumps(bst2)
# load model and data in
bst3 = pickle.loads(pks)
preds3 = bst3.predict(dtest2)
# assert they are the same
assert np.sum(np.abs(preds3 - preds)) == 0

###下面不用看
# build dmatrix from scipy.sparse
print('start running example of build DMatrix from scipy.sparse CSR Matrix')
labels = []
row = []; col = []; dat = []
i = 0
for l in open('../data/agaricus.txt.train'):
    arr = l.split()
    labels.append(int(arr[0]))
    for it in arr[1:]:
        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, label=labels)
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
bst = xgb.train(param, dtrain, num_round, watchlist)

print('start running example of build DMatrix from scipy.sparse CSC Matrix')
# we can also construct from csc matrix
csc = scipy.sparse.csc_matrix((dat, (row, col)))
dtrain = xgb.DMatrix(csc, label=labels)
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
bst = xgb.train(param, dtrain, num_round, watchlist)

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, label=labels)
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
bst = xgb.train(param, dtrain, num_round, watchlist)