# 中文问句判断模型
一个使用xgboost的中文问句判断模型
# 模型效果
Param select 0, auc: 0.9793438, iter_round: 207, params: {'objective': u'binary:logistic', 'subsample': 0.5, 'eta': 0.1, 'max_depth': 4, 'silent': 1}, now best auc: 0.9793438
Param select 1, auc: 0.9799142, iter_round: 350, params: {'objective': u'binary:logistic', 'subsample': 0.7, 'eta': 0.1, 'max_depth': 4, 'silent': 1}, now best auc: 0.9799142
Param select 2, auc: 0.9802402, iter_round: 280, params: {'objective': u'binary:logistic', 'subsample': 1.0, 'eta': 0.1, 'max_depth': 4, 'silent': 1}, now best auc: 0.9802402
Param select 3, auc: 0.9791936, iter_round: 197, params: {'objective': u'binary:logistic', 'subsample': 0.5, 'eta': 0.1, 'max_depth': 5, 'silent': 1}, now best auc: 0.9802402
Param select 4, auc: 0.979731, iter_round: 223, params: {'objective': u'binary:logistic', 'subsample': 0.7, 'eta': 0.1, 'max_depth': 5, 'silent': 1}, now best auc: 0.9802402
Param select 5, auc: 0.97988, iter_round: 199, params: {'objective': u'binary:logistic', 'subsample': 1.0, 'eta': 0.1, 'max_depth': 5, 'silent': 1}, now best auc: 0.9802402
Param select 6, auc: 0.9792362, iter_round: 213, params: {'objective': u'binary:logistic', 'subsample': 0.5, 'eta': 0.1, 'max_depth': 6, 'silent': 1}, now best auc: 0.9802402
Param select 7, auc: 0.9798212, iter_round: 256, params: {'objective': u'binary:logistic', 'subsample': 0.7, 'eta': 0.1, 'max_depth': 6, 'silent': 1}, now best auc: 0.9802402
Param select 8, auc: 0.9800464, iter_round: 181, params: {'objective': u'binary:logistic', 'subsample': 1.0, 'eta': 0.1, 'max_depth': 6, 'silent': 1}, now best auc: 0.9802402
Param select 9, auc: 0.9795114, iter_round: 463, params: {'objective': u'binary:logistic', 'subsample': 0.5, 'eta': 0.05, 'max_depth': 4, 'silent': 1}, now best auc: 0.9802402
Param select 10, auc: 0.979777, iter_round: 443, params: {'objective': u'binary:logistic', 'subsample': 0.7, 'eta': 0.05, 'max_depth': 4, 'silent': 1}, now best auc: 0.9802402
Param select 11, auc: 0.9802696, iter_round: 484, params: {'objective': u'binary:logistic', 'subsample': 1.0, 'eta': 0.05, 'max_depth': 4, 'silent': 1}, now best auc: 0.9802696
Param select 12, auc: 0.9794792, iter_round: 440, params: {'objective': u'binary:logistic', 'subsample': 0.5, 'eta': 0.05, 'max_depth': 5, 'silent': 1}, now best auc: 0.9802696
Param select 13, auc: 0.9800954, iter_round: 427, params: {'objective': u'binary:logistic', 'subsample': 0.7, 'eta': 0.05, 'max_depth': 5, 'silent': 1}, now best auc: 0.9802696
Param select 14, auc: 0.980495, iter_round: 483, params: {'objective': u'binary:logistic', 'subsample': 1.0, 'eta': 0.05, 'max_depth': 5, 'silent': 1}, now best auc: 0.980495
Param select 15, auc: 0.9795902, iter_round: 436, params: {'objective': u'binary:logistic', 'subsample': 0.5, 'eta': 0.05, 'max_depth': 6, 'silent': 1}, now best auc: 0.980495
Param select 16, auc: 0.9804718, iter_round: 416, params: {'objective': u'binary:logistic', 'subsample': 0.7, 'eta': 0.05, 'max_depth': 6, 'silent': 1}, now best auc: 0.980495
Param select 17, auc: 0.9804004, iter_round: 382, params: {'objective': u'binary:logistic', 'subsample': 1.0, 'eta': 0.05, 'max_depth': 6, 'silent': 1}, now best auc: 0.980495
Param select 18, auc: 0.979225, iter_round: 1011, params: {'objective': u'binary:logistic', 'subsample': 0.5, 'eta': 0.02, 'max_depth': 4, 'silent': 1}, now best auc: 0.980495
Param select 19, auc: 0.980099, iter_round: 1135, params: {'objective': u'binary:logistic', 'subsample': 0.7, 'eta': 0.02, 'max_depth': 4, 'silent': 1}, now best auc: 0.980495
Param select 20, auc: 0.9802448, iter_round: 1207, params: {'objective': u'binary:logistic', 'subsample': 1.0, 'eta': 0.02, 'max_depth': 4, 'silent': 1}, now best auc: 0.980495
Param select 21, auc: 0.9792566, iter_round: 762, params: {'objective': u'binary:logistic', 'subsample': 0.5, 'eta': 0.02, 'max_depth': 5, 'silent': 1}, now best auc: 0.980495
Param select 22, auc: 0.9802228, iter_round: 852, params: {'objective': u'binary:logistic', 'subsample': 0.7, 'eta': 0.02, 'max_depth': 5, 'silent': 1}, now best auc: 0.980495
Param select 23, auc: 0.9798456, iter_round: 831, params: {'objective': u'binary:logistic', 'subsample': 1.0, 'eta': 0.02, 'max_depth': 5, 'silent': 1}, now best auc: 0.980495
Param select 24, auc: 0.97926, iter_round: 694, params: {'objective': u'binary:logistic', 'subsample': 0.5, 'eta': 0.02, 'max_depth': 6, 'silent': 1}, now best auc: 0.980495
Param select 25, auc: 0.9803058, iter_round: 824, params: {'objective': u'binary:logistic', 'subsample': 0.7, 'eta': 0.02, 'max_depth': 6, 'silent': 1}, now best auc: 0.980495
Param select 26, auc: 0.980129, iter_round: 880, params: {'objective': u'binary:logistic', 'subsample': 1.0, 'eta': 0.02, 'max_depth': 6, 'silent': 1}, now best auc: 0.980495
# 实例
from interrogative.api import *
train()
tag = recognize(u'今天 来 点 兔子 吗')
output = '是疑问句' if tag else '不是疑问句'
print(output)
### 博客
博客地址:https://blog.csdn.net/sinat_33741547/article/details/79933376
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
基于HMM的中文分词模型 基于fasttext的情感极性判断模型 基于MaxEnt的中文词性标注模型 基于CRF的中文命名实体识别模型 基于序列标注的中文依存句法分析模型 基于Xgboost的中文疑问句判别模型
资源推荐
资源详情
资源评论
收起资源包目录
基于python的自然语言基础模型.rar (87个子文件)
基于python的自然语言基础模型
.gitignore 179B
sentiment
requirements.txt 55B
src
__init__.py 0B
api.py 992B
config.py 2KB
dictionary.py 6KB
model.py 3KB
doc
Makefile 609B
index.rst 792B
conf.py 5KB
make.bat 771B
sentiment.model.rst 89B
sentiment.dict.rst 94B
sentiment.api.rst 87B
README.md 2KB
manage.py 342B
postagger
requirements.txt 61B
src
radical.py 1000B
__init__.py 24B
corpus.py 13KB
api.py 590B
config.py 1KB
model.py 4KB
doc
Makefile 606B
index.rst 823B
conf.py 5KB
make.bat 777B
postagger.model.rst 89B
postagger.corpus.rst 90B
postagger.api.rst 87B
README.md 793B
manage.py 292B
ner
requirements.txt 53B
src
__init__.py 24B
corpus.py 7KB
api.py 515B
config.py 769B
util.py 822B
model.py 3KB
doc
Makefile 600B
index.rst 820B
conf.py 5KB
ner.corpus.rst 84B
make.bat 771B
ner.api.rst 81B
ner.model.rst 83B
README.md 2KB
manage.py 282B
interrogative
requirements.txt 53B
src
__init__.py 24B
corpus.py 2KB
api.py 423B
config.py 1KB
util.py 1KB
model.py 4KB
README.md 5KB
manage.py 159B
segment
requirements.txt 58B
src
__init__.py 24B
corpus.py 6KB
api.py 528B
config.py 808B
model.py 4KB
doc
Makefile 604B
index.rst 795B
conf.py 5KB
make.bat 775B
segment.corpus.rst 88B
segment.api.rst 85B
segment.model.rst 87B
README.md 467B
manage.py 273B
depparser
requirements.txt 53B
src
__init__.py 24B
corpus.py 4KB
api.py 351B
config.py 869B
model.py 2KB
doc
depparser.api.rst 87B
Makefile 606B
index.rst 832B
conf.py 5KB
make.bat 777B
depparser.corpus.rst 90B
depparser.model.rst 89B
README.md 643B
manage.py 292B
共 87 条
- 1
资源评论
爱吃苹果的Jemmy
- 粉丝: 75
- 资源: 1148
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功