HuaBao-OK

HuaBao-OK's Stars

• facebookresearch/fastText

  Library for fast text representation and classification.

  Language:HTML25.9k8451.1k4.7k

• facebook/zstd

  Zstandard - Fast real-time compression algorithm

  Language:C23.8k4111.4k2.1k

• google/brotli

  Brotli compression format

  Language:TypeScript13.6k3344211.2k

• NLPchina/ansj_seg

  ansj分词.ict的真正java实现.分词效果速度都超过开源版的ict. 中文分词,人名识别,词性标注,用户自定义词典

  Language:Java6.5k6577102.3k

• tesseract-ocr/tessdata

  Trained models with fast variant of the "best" LSTM models + legacy models

  6.4k2311562.2k

• rmtheis/tess-two

  Fork of Tesseract Tools for Android

  Language:C3.8k2082371.4k

• huaban/jieba-analysis

  结巴分词(java版)

  Language:Java2.6k14299839

• Micro-sheep/efinance

  efinance 是一个可以快速获取基金、股票、债券、期货数据的 Python 库，回测以及量化交易的好帮手！🚀🚀🚀

  Language:Python1.9k45160479

• mpquant/Ashare

  股票行情实时数据接口-A股,完全免费的沪深证券股票数据-**股市,python最简封装的API接口,包含日线,历史K线,分时线,分钟线,全部实时采集，系统包括新浪腾讯双数据核心采集获取，自动故障切换，STOCK数据格式成DataFrame格式,可用来查询研究量化分析，股票程序自动化交易系统.为量化研究者在数据获取方面极大地减轻工作量，更加专注于策略和模型的研究与实现。

  Language:Python1.8k2014435

• naxiaoduo/1000UserGuide

  1000UserGuide：对独立开发者和创业者来说，找到前1000个早期用户太关键了。这里精心整理了300多个国内外渠道，适合独立开发者和创业者推广产品的渠道。

  Language:HTML1.7k2312129

• apache/opennlp

  Apache OpenNLP

  Language:Java1.4k900449

• florianv/swap

  :currency_exchange: Currency exchange rates library

  Language:PHP1.3k3662138

• uname-yang/pysnowball

  雪球股票数据接口 python edition

  Language:Python1.1k2226276

• maanavshah/stock-market-india

  API for Indian Stock Market's NSE and BSE.

  Language:JavaScript8754032378

• luben/zstd-jni

  JNI binding for Zstd

  Language:C86424238168

• robbiehanson/KissXML

  A replacement for Cocoa's NSXML cluster of classes. Based on libxml. Works on iOS.

  Language:Objective-C8614280332

• adaptech-cz/Tesseract4Android

  Fork of tess-two rewritten from scratch to support latest version of Tesseract OCR.

  Language:C7501561114

• zhangxiangliang/stock-api

  股票接口 | 韭菜小猪 | A股 | 美股 | 港股 | 股票 | 基金 | JavaScript

  Language:TypeScript697111397

• fawazahmed0/exchange-api

  Free Currency Exchange Rates API with 200+ Currencies & No Rate Limits

  Language:Python6861210943

• mayabot/mynlp

  一个生产级、高性能、模块化、可扩展的中文NLP工具包。（中文分词、平均感知机、fastText、拼音、新词发现、分词纠错、BM25、人名识别、命名实体、自定义词典）

  Language:Java677293589

• joestelmach/natty

  Java natural language date parser

  Language:Java52026254183

• florianv/exchanger

  :office: Currency exchange rates framework for PHP

  Language:PHP183135781

• mayabot/fastText4j

  Implementing Facebook's FastText with java

  159122823

• EugenePig/ik-analyzer-solr5

  IKAnalyzer for Solr5

  Language:Java143143103

• Waikato/weka-trunk

  No longer updated mirror of the Weka trunk branch.

  Language:Java12611433

• ellisonchan/SplashScreen

  Splash screen demo that used with Jetpack ‘SplashScreen‘ library and Android 12's Splash Screen API.

  Language:Kotlin803321

• alicelmx/SVM-Chinese-Classification

  利用支持向量机实现中文文本分类

  Language:Java29216

• rahulnadella/FuzzySearch

  Utility class to find an approximate match for specific String

  Language:Swift192111

• geek-jiaxu/CnnTextClassifyByDl4j

  采用卷积神经网络（cnn）进行文本分类，依赖dl4j

  Language:Java14212

• chenergy1991/Chinese-Text-Classification-Based-on-Naive-Bayes

  The development of computer and communications technology has resulted in huge amount of data. The automatic text classification technique has become very significant. Naive Bayes algorithm is based on probabilistic model. It is an effective way to deal with automatic text classification. The main task of this paper is to discuss the theoretical basis of Naive Bayes text classifier and describe the process of using Java language to accomplish the classifier. We can divide the classifier into two parts: the feature extraction and the calculation according to the feature. In the feature extraction part, I use the Chinese word segmentation method and the stop words filtering. In the classification part, I calculate the prior probability, the likelihood function value and the maximum a posterior estimation. During the simple test, the author uses the Sogou laboratory’s text classification corpus as the training set and the test set. During the test, the accuracy is between 39% to 56 %. The results show that there is still room for improvement. The paper also includes the discussion of its improvement methods and wider application.

  Language:Java6202