如何控制xgboost的模型大小？

如何解决如何控制xgboost的模型大小？

遇到一个需要逐步训练模型的情况，我想得到一个小尺寸的模型，但是就像下面的例子，我的临时模型尺寸每次迭代都增加了，我没有知道如何控制模型大小。

# -*- coding: utf-8 -*-

import xgboost as xgb
from sklearn.model_selection import train_test_split as ttsplit
from sklearn.datasets import load_boston
from sklearn.metrics import mean_squared_error as mse

X = load_boston()['data']
y = load_boston()['target']

# split data into training and testing sets
# then split training set in half
X_train,X_test,y_train,y_test = ttsplit(X,y,test_size=0.1,random_state=0)
X_train_1,X_train_2,y_train_1,y_train_2 = ttsplit(X_train,test_size=0.5,random_state=0)

xg_train_1 = xgb.DMatrix(X_train_1,label=y_train_1)
xg_train_2 = xgb.DMatrix(X_train_2,label=y_train_2)
xg_test = xgb.DMatrix(X_test,label=y_test)

params = {'objective': 'reg:squarederror','tree_method': 'hist','max_depth': 3,'max_leaves': 100,'grow_policy': 'lossguide'}
model_1 = xgb.train(params,xg_train_1,30)
# model_1.save_model('t0.json')

# ================= train two versions of the model =====================#
model_v1 = xgb.train(params,xg_train_2,30)
model_v1.save_model('./t1.json')
print(model_v1.__dict__)

model_v2 = xgb.train(params,30,xgb_model='t1.json')
model_v2.save_model('./t2.json')
print(model_v2.__dict__)

model_v3 = xgb.train(params,xgb_model='t2.json')
model_v3.save_model('./t3.json')
print(model_v3.__dict__)

model_v4 = xgb.train(params,xgb_model='t3.json')
model_v4.save_model('./t4.json')
print(model_v4.__dict__)

model_v5 = xgb.train(params,xgb_model='t4.json')
model_v5.save_model('./t4.json')
print(model_v5.__dict__)

顺便说一句，我已经阅读了训练模型的 XGBoost 的每个参数，并尝试了 max_depth、max_leaves 和许多其他组合，但都不起作用。

解决方法

JSON 数据的详细信息显示添加的树越来越多，仔细阅读文档后发现两个参数是为此设计的。（max_depth，max_leaves 仅用于树属性，而不用于树编号）

我们可以通过下面的代码解决这个问题。

# -*- coding: utf-8 -*-

import xgboost as xgb
from sklearn.model_selection import train_test_split as ttsplit
from sklearn.datasets import load_boston
from sklearn.metrics import mean_squared_error as mse

X = load_boston()['data']
y = load_boston()['target']

# split data into training and testing sets
# then split training set in half
X_train,X_test,y_train,y_test = ttsplit(X,y,test_size=0.1,random_state=0)
X_train_1,X_train_2,y_train_1,y_train_2 = ttsplit(X_train,test_size=0.5,random_state=0)

xg_train_1 = xgb.DMatrix(X_train_1,label=y_train_1)
xg_train_2 = xgb.DMatrix(X_train_2,label=y_train_2)
xg_test = xgb.DMatrix(X_test,label=y_test)

params = {
    'objective': 'reg:squarederror','tree_method': 'hist','max_depth': 3,'max_leaves': 100,}
model_1 = xgb.train(params,xg_train_1,10)
# model_1.save_model('t0.json')

# ================= train two versions of the model =====================#
model_v1 = xgb.train(params,xg_train_2)
model_v1.save_model('./t1.json')
print(model_v1.__dict__)

params1 = params.copy()
# key arguments for this
params1['process_type'] = 'update'
params1['updater'] = 'refresh'

model_v2 = xgb.train(params1,xg_train_2,xgb_model='t1.json')
model_v2.save_model('./t2.json')
print(model_v2.__dict__)

参考：

[1]https://xgboost.readthedocs.io/en/latest/python/python_api.html#module-xgboost.training [2]https://github.com/dmlc/xgboost/issues/3055