SimpleChinese2 集成了许多基本的中文NLP功能,使基于 Python 的中文文字处理和信息提取变得简单方便。

Overview

SimpleChinese2

SimpleChinese2 集成了许多基本的中文NLP功能,使基于 Python 的中文文字处理和信息提取变得简单方便。

声明

本项目是为方便个人工作所创建的,仅有部分代码原创。包括分词、词云在内的诸多功能来自于其他项目,并非本人所写,如遇问题,请至原项目链接下提问,谢谢!

安装

pip install -U simplechinese==0.2.8

如从 git 上 clone,需要从以下地址下载词向量文件:

https://drive.google.com/file/d/1ltyiTHZk8kIBYQGbZS9GoO_DwDOEWnL9/view?usp=sharing

并拷贝至"./simplechinese/data/"文件夹下

使用方法

import simplechinese as sc

1. 文字预处理

>> print(sc.only_digits(x)) # 仅保留数字 01234 >>> print(sc.only_zh(x)) # 仅保留中文 测试测试测试测试 >>> print(sc.only_en(x)) # 仅保留英文 TestING >>> print(sc.remove_space(x)) # 去除空格 测试测试,TestING;¥%&01234测试测试 >>> print(sc.remove_digits(x)) # 去除数字 测试测试,TestING ;¥%& 测试测试 >>> print(sc.remove_zh(x)) # 去除中文 ,TestING ;¥%& 01234 >>> print(sc.remove_en(x)) # 去除英文 测试测试, ;¥%& 01234测试测试 >>> print(sc.remove_punctuations(x)) # 去除标点符号 测试测试TestING 01234测试测试 >>> print(sc.toLower(x)) # 修改为全小写字母 测试测试,testing ;¥%& 01234测试测试 >>> print(sc.toUpper(x)) # 修改为全大写字母 测试测试,TESTING ;¥%& 01234测试测试 >>> x = "测试,TestING:12345@#【】+=-()。." >>> print(sc.punc_norm(x)) # 将中文标点符号转换成英文标点符号 测试,TestING:12345@#[]+=-().. >>> # y = fillna(df) # 将pandas.DataFrame中的N/A单元格填充为长度为0的str ">
>>> x = "测试测试,TestING    ;¥%& 01234测试测试"

>>> print(sc.only_digits(x))         # 仅保留数字
01234

>>> print(sc.only_zh(x))             # 仅保留中文
测试测试测试测试

>>> print(sc.only_en(x))             # 仅保留英文
TestING

>>> print(sc.remove_space(x))        # 去除空格
测试测试,TestING;¥%&01234测试测试

>>> print(sc.remove_digits(x))       # 去除数字
测试测试,TestING    ;¥%& 测试测试

>>> print(sc.remove_zh(x))           # 去除中文
,TestING    ;¥%& 01234

>>> print(sc.remove_en(x))           # 去除英文
测试测试,    ;¥%& 01234测试测试

>>> print(sc.remove_punctuations(x)) # 去除标点符号
测试测试TestING     01234测试测试

>>> print(sc.toLower(x))             # 修改为全小写字母
测试测试,testing    ;¥%& 01234测试测试

>>> print(sc.toUpper(x))             # 修改为全大写字母
测试测试,TESTING    ;¥%& 01234测试测试

>>> x = "测试,TestING:12345@#【】+=-()。."
>>> print(sc.punc_norm(x))           # 将中文标点符号转换成英文标点符号
测试,TestING:12345@#[]+=-()..

>>> # y = fillna(df) # 将pandas.DataFrame中的N/A单元格填充为长度为0的str

2. 基础NLP信息提取功能

该部分中,分词功能使用 jieba 实现,源码请参考:https://github.com/fxsjy/jieba

同/近义词查找功能复用了 synonyms 中的词向量数据文件,源码请参考:https://github.com/chatopera/Synonyms 但有所改动,改动如下

  1. 由于 pip 上传文件限制,synonyms 需要用户在完成 pip 安装后再下载词向量文件,国内下载需要设置镜像地址或使用特殊手段,有所不便。因此此处将词向量用 float16 表示,并使用 pca 降维至 64 维。总体效果差别不大,如果在意,请直接安装 synonyms 处理同/近义词查找任务。

  2. 原项目通过构建 KDTree 实现快速查找,但比较相似度是使用 cosine similarity,而 KDTree (sklearn) 本身不支持通过 cosine similarity 构建。因此原项目使用欧式距离构建树,导致输出结果有部分顺序混乱。为修复该问题,本项目将词向量归一化后再构建 KDTree,使得向量间的 cosine similarity 与欧式距离(即割线距离)正相关。具体推导可参考下文:https://stackoverflow.com/questions/34144632/using-cosine-distance-with-scikit-learn-kneighborsclassifier

  3. 原项目中未设置缓存上限,本项目中仅保留最近10000次查找记录。

x = "今天是我参加工作的第1天,我花了23.33元买了写零食犒劳一下自己。"
print(sc.extract_nums(x))              # 提取数字信息
[1.0, 23.33]

# mode: 0: No single character words. The words may be overlapped.
#       1: Have single character words. The words may be overlapped.
#       2: No single character words. The words are not overlapped.
#       3: Have single character words. The words are not overlapped.
#       4: Only single characters.
print(sc.extract_words(x, mode=0))      # 分词
['今天', '参加', '工作', '我花', '23.33', '零食', '犒劳', '一下', '自己']

a = "做人真的好难"
b = "做人实在太难了"
print(sc.string_distance(a,b))  # 编辑距离
0.46153846153846156

x = "种族歧视"
print(sc.find_synonyms(x, n=3))  # 同/近义词
[('种族歧视', 1.0), ('种族主义', 0.84619140625), ('歧视', 0.76416015625)]

3. 繁体简体转换

该部分使用 chinese_converter 实现,源码请参考:https://github.com/zachary822/chinese-converter

>> print(sc.to_traditional(x)) # 转换为繁体 烏龜測試123 >>> x = "烏龜測試123" >>> print(sc.to_simplified(x)) # 转换为简体 乌龟测试123 ">
>>> x = "乌龟测试123"
>>> print(sc.to_traditional(x))  # 转换为繁体
烏龜測試123

>>> x = "烏龜測試123"
>>> print(sc.to_simplified(x))   # 转换为简体
乌龟测试123

4. 特征提取和向量化

5. 词云和可视化

TODO:

  1. 句子向量化及句子相似度
  2. 其他特征提取相关工具
Owner
Ming
惊了
Ming
Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations

Expediting Vision Transformers via Token Reorganizations This repository contain

Youwei Liang 101 Dec 26, 2022
nlpcommon is a python Open Source Toolkit for text classification.

nlpcommon nlpcommon, Python Text Tool. Guide Feature Install Usage Dataset Contact Cite Reference Feature nlpcommon is a python Open Source

xuming 3 May 29, 2022
Local cross-platform machine translation GUI, based on CTranslate2

DesktopTranslator Local cross-platform machine translation GUI, based on CTranslate2 Download Windows Installer You can either download a ready-made W

Yasmin Moslem 29 Jan 05, 2023
Ελληνικά νέα (Python script) / Greek News Feed (Python script)

Ελληνικά νέα (Python script) / Greek News Feed (Python script) Ελληνικά English Το 2017 είχα υλοποιήσει ένα Python script για να εμφανίζει τα τωρινά ν

Loren Kociko 1 Jun 14, 2022
✨Fast Coreference Resolution in spaCy with Neural Networks

✨ NeuralCoref 4.0: Coreference Resolution in spaCy with Neural Networks. NeuralCoref is a pipeline extension for spaCy 2.1+ which annotates and resolv

Hugging Face 2.6k Jan 04, 2023
A modular Karton Framework service that unpacks common packers like UPX and others using the Qiling Framework.

Unpacker Karton Service A modular Karton Framework service that unpacks common packers like UPX and others using the Qiling Framework. This project is

c3rb3ru5 45 Jan 05, 2023
Main repository for the chatbot Bobotinho.

Bobotinho Bot Main repository for the chatbot Bobotinho. ℹ️ Introduction Twitch chatbot with entertainment commands. ‎ 💻 Technologies Concurrent code

Bobotinho 14 Nov 29, 2022
CrossNER: Evaluating Cross-Domain Named Entity Recognition (AAAI-2021)

CrossNER is a fully-labeled collected of named entity recognition (NER) data spanning over five diverse domains (Politics, Natural Science, Music, Literature, and Artificial Intelligence) with specia

Zihan Liu 89 Nov 10, 2022
Weakly-supervised Text Classification Based on Keyword Graph

Weakly-supervised Text Classification Based on Keyword Graph How to run? Download data Our dataset follows previous works. For long texts, we follow C

Hello_World 20 Dec 29, 2022
SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples

SNCSE SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples This is the repository for SNCSE. SNCSE aims to allev

Sense-GVT 59 Jan 02, 2023
Source code for AAAI20 "Generating Persona Consistent Dialogues by Exploiting Natural Language Inference".

Generating Persona Consistent Dialogues by Exploiting Natural Language Inference Source code for RCDG model in AAAI20 Generating Persona Consistent Di

16 Oct 08, 2022
Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。

GPT2-NewsTitle 带有超详细注释的GPT2新闻标题生成项目 UpDate 01.02.2021 从网上收集数据,将清华新闻数据、搜狗新闻数据等新闻数据集,以及开源的一些摘要数据进行整理清洗,构建一个较完善的中文摘要数据集。 数据集清洗时,仅进行了简单地规则清洗。

logCong 785 Dec 29, 2022
novel deep learning research works with PaddlePaddle

Research 发布基于飞桨的前沿研究工作,包括CV、NLP、KG、STDM等领域的顶会论文和比赛冠军模型。 目录 计算机视觉(Computer Vision) 自然语言处理(Natrual Language Processing) 知识图谱(Knowledge Graph) 时空数据挖掘(Spa

1.5k Jan 03, 2023
A python package for deep multilingual punctuation prediction.

This python library predicts the punctuation of English, Italian, French and German texts. We developed it to restore the punctuation of transcribed spoken language.

Oliver Guhr 27 Dec 22, 2022
ByT5: Towards a token-free future with pre-trained byte-to-byte models

ByT5: Towards a token-free future with pre-trained byte-to-byte models ByT5 is a tokenizer-free extension of the mT5 model. Instead of using a subword

Google Research 409 Jan 06, 2023
The Internet Archive Research Assistant - Daily search Internet Archive for new items matching your keywords

The Internet Archive Research Assistant - Daily search Internet Archive for new items matching your keywords

Kay Savetz 60 Dec 25, 2022
Generate text line images for training deep learning OCR model (e.g. CRNN)

Generate text line images for training deep learning OCR model (e.g. CRNN)

532 Jan 06, 2023
Finetune gpt-2 in google colab

gpt-2-colab finetune gpt-2 in google colab sample result (117M) from retraining on A Tale of Two Cities by Charles Di

212 Jan 02, 2023