python_xgboost例02_predict_leaf_indices获得叶子索引

本专栏所有例题数据放在 网址https://download.csdn.net/download/u012338969/85439555

%matplotlib inline

Demo for obtaining leaf index

import os
import xgboost as xgb

# load data in do training
dtrain = xgb.DMatrix( './data/agaricus.txt.train')
dtest = xgb.DMatrix( './data/agaricus.txt.test')

param = {'max_depth': 2, 'eta': 1, 'objective': 'binary:logistic'}
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 20
bst = xgb.train(param, dtrain, num_round, watchlist)
print('start testing predict the leaf indices')
# predict using first 2 tree

[0]	eval-logloss:0.22669	train-logloss:0.23338
[1]	eval-logloss:0.13787	train-logloss:0.13666
[2]	eval-logloss:0.08046	train-logloss:0.08253
[3]	eval-logloss:0.05833	train-logloss:0.05647
[4]	eval-logloss:0.03829	train-logloss:0.04151
[5]	eval-logloss:0.02663	train-logloss:0.02961
[6]	eval-logloss:0.01388	train-logloss:0.01919
[7]	eval-logloss:0.01020	train-logloss:0.01332
[8]	eval-logloss:0.00848	train-logloss:0.01113
[9]	eval-logloss:0.00692	train-logloss:0.00663
[10]	eval-logloss:0.00544	train-logloss:0.00504
[11]	eval-logloss:0.00445	train-logloss:0.00420
[12]	eval-logloss:0.00336	train-logloss:0.00356
[13]	eval-logloss:0.00277	train-logloss:0.00281
[14]	eval-logloss:0.00252	train-logloss:0.00244
[15]	eval-logloss:0.00177	train-logloss:0.00194
[16]	eval-logloss:0.00157	train-logloss:0.00161
[17]	eval-logloss:0.00135	train-logloss:0.00142
[18]	eval-logloss:0.00123	train-logloss:0.00125
[19]	eval-logloss:0.00107	train-logloss:0.00107
start testing predict the leaf indices


D:\d_programe\Anaconda3\lib\site-packages\xgboost\core.py:525: FutureWarning: Pass `evals` as keyword args.  Passing these as positional arguments will be considered as error in future releases.
  warnings.warn(

leafindex = bst.predict(
    dtest, iteration_range=(0, 2), pred_leaf=True, strict_shape=True
)
print(leafindex.shape)

(1611, 2, 1, 1)

print(leafindex)

[[[[4.]]

  [[3.]]]


 [[[3.]]

  [[3.]]]


 [[[4.]]

  [[3.]]]


 ...


 [[[3.]]

  [[3.]]]


 [[[5.]]

  [[4.]]]


 [[[3.]]

  [[3.]]]]

# predict all trees
leafindex = bst.predict(dtest, pred_leaf=True)
print(leafindex.shape)

(1611, 20)