pmp55,github

burst_detection

Detect bursts in batched data using Kleinberg's (2002) algorithm.

camelot

Camelot: PDF Table Extraction for Humans

causal-inference-intro

A quick introduction to the causal inference in R using the CausalImpact package

data-scientist-profile-stackoverflow-2019

Data scientist's profiles according to the stackoverflow developer survey 2019

ds-cheatsheets

List of Data Science Cheatsheets to rule the world

ds_survey_analysis

Analysis of Stack Overflow 2018 Developer Survey data to explore the differences between data scientists and non-data scientists.

epu-index

「經濟政策的不確定性指標 (EPU指標) 」為國外學者利用透過文字探勘的技術, 從美國10份新聞資料中萃取相關的資訊, 建構一個同時涵蓋經濟、政策與不確定性等詞庫類別的指標。主旨在編制屬於台灣的EPU指標, 利用網路爬蟲技術, 從蘋果日報、自由時報、中國時報的文本資料中, 進而編制指標。

fasttext

Library for fast text representation and classification.

haystack

:mag: Transformers at scale for question answering & search

iap-cidl

Causal Inference & Deep Learning, MIT IAP 2018

kaggle-survey

My analysis of the results of Kaggle's data science survey – Winner of a Kaggle Kernels Award

Simple, Keras-powered multilingual NLP framework, allows you to build your models in 5 minutes for named entity recognition (NER), part-of-speech tagging (PoS) and text classification tasks. Includes BERT and word2vec embedding.

node2vec

Implementation of the node2vec algorithm.

opencv-face-recognition

Real-time face recognition project with OpenCV and Python

opendata_viz

Code behind medium blog

paper-management-system

本项目基于互联网+的理念，结合微信公众平台，旨在方便学生和教师，随时随地完成毕业论文的提交与审核工作。整个系统划分为四个角色：教务管理员，学生，教师，系主任。通过实现各种角色信息的导入和管理，论文题目的确定，上传与下载开题及答辩的PPT和论文，输入成绩，根据成绩计算公式导出最终成绩等功能将各个角色紧密的结合在一起。另外在微信公众平台中实现了各角色接受相关模板消息，查看基本信息及成绩等功能。