yzkang / My Data Competition Experience
本人多次机器学习与大数据竞赛Top5的经验总结,满满的干货,拿好不谢
Stars: ✭ 271
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to My Data Competition Experience
Mljar Supervised
Automated Machine Learning Pipeline with Feature Engineering and Hyper-Parameters Tuning 🚀
Stars: ✭ 961 (+254.61%)
Mutual labels: data-science, automl, xgboost, hyperparameter-optimization, feature-engineering, lightgbm
Auto ml
[UNMAINTAINED] Automated machine learning for analytics & production
Stars: ✭ 1,559 (+475.28%)
Mutual labels: data-science, automl, xgboost, hyperparameter-optimization, feature-engineering, lightgbm
Tpot
A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.
Stars: ✭ 8,378 (+2991.51%)
Mutual labels: data-science, automl, xgboost, hyperparameter-optimization, feature-engineering
Hyperparameter hunter
Easy hyperparameter optimization and automatic result saving across machine learning algorithms and libraries
Stars: ✭ 648 (+139.11%)
Mutual labels: data-science, xgboost, hyperparameter-optimization, feature-engineering, lightgbm
Nni
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
Stars: ✭ 10,698 (+3847.6%)
Mutual labels: data-science, automl, hyperparameter-optimization, feature-engineering
Automl alex
State-of-the art Automated Machine Learning python library for Tabular Data
Stars: ✭ 132 (-51.29%)
Mutual labels: data-science, automl, xgboost, hyperparameter-optimization
Mlbox
MLBox is a powerful Automated Machine Learning python library.
Stars: ✭ 1,199 (+342.44%)
Mutual labels: data-science, automl, xgboost, lightgbm
Autodl
Automated Deep Learning without ANY human intervention. 1'st Solution for AutoDL [email protected]
Stars: ✭ 854 (+215.13%)
Mutual labels: data-science, automl, feature-engineering, lightgbm
Hyperactive
A hyperparameter optimization and data collection toolbox for convenient and fast prototyping of machine-learning models.
Stars: ✭ 182 (-32.84%)
Mutual labels: data-science, xgboost, hyperparameter-optimization, feature-engineering
AutoTabular
Automatic machine learning for tabular data. ⚡🔥⚡
Stars: ✭ 51 (-81.18%)
Mutual labels: xgboost, lightgbm, feature-engineering, automl
Evalml
EvalML is an AutoML library written in python.
Stars: ✭ 145 (-46.49%)
Mutual labels: data-science, automl, feature-engineering
Auptimizer
An automatic ML model optimization tool.
Stars: ✭ 166 (-38.75%)
Mutual labels: data-science, automl, hyperparameter-optimization
Lale
Library for Semi-Automated Data Science
Stars: ✭ 198 (-26.94%)
Mutual labels: data-science, automl, hyperparameter-optimization
Ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
Stars: ✭ 18,547 (+6743.91%)
Mutual labels: data-science, automl, hyperparameter-optimization
Lightautoml
LAMA - automatic model creation framework
Stars: ✭ 196 (-27.68%)
Mutual labels: data-science, automl, feature-engineering
Apartment-Interest-Prediction
Predict people interest in renting specific NYC apartments. The challenge combines structured data, geolocalization, time data, free text and images.
Stars: ✭ 17 (-93.73%)
Mutual labels: kaggle-competition, xgboost, lightgbm
Eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
Stars: ✭ 2,477 (+814.02%)
Mutual labels: data-science, xgboost, lightgbm
HyperGBM
A full pipeline AutoML tool for tabular data
Stars: ✭ 172 (-36.53%)
Mutual labels: xgboost, lightgbm, automl
Kaggle Competitions
There are plenty of courses and tutorials that can help you learn machine learning from scratch but here in GitHub, I want to solve some Kaggle competitions as a comprehensive workflow with python packages. After reading, you can use this workflow to solve other real problems and use it as a template.
Stars: ✭ 86 (-68.27%)
Mutual labels: kaggle-competition, data-science, feature-engineering
mindware
An efficient open-source AutoML system for automating machine learning lifecycle, including feature engineering, neural architecture search, and hyper-parameter tuning.
Stars: ✭ 34 (-87.45%)
Mutual labels: hyperparameter-optimization, feature-engineering, automl
数据科学竞赛经验谈
如何做数据分析?
如何做数据清洗?
如何做特征工程?(面向关系型数据的特征工程系统化分析方法)
如何做特征选择?
如何选择合适的机器学习模型?
如何调参?
如何做模型融合?
如何上分刷榜?
目前文字版已开源,请大家前往知乎阅读:https://zhuanlan.zhihu.com/p/149769029
纯文字PDF版已经制作完成,已与PPT版一起上传至我的知识星球。想咨询竞赛经验、快速上分、争夺奖金的同学,欢迎到大卫的小屋与我交流:https://t.zsxq.com/IMfe2vB
联系方式
E-mail: [email protected]
知识星球:https://t.zsxq.com/IMfe2vB
附录
本人竞赛成绩总结
年份 | 竞赛平台 | 举办单位 | 竞赛名称 | 竞赛成绩 | 排名 |
---|---|---|---|---|---|
2017 | 科赛网 | 中国平安 | 前海征信“好信杯”迁移学习算法大赛 | 第6名 | 6/600 |
2017 | 天池大数据众智平台 | 阿里云 | 第二届云安全算法挑战赛 | 第16名 | 16/959 |
2018 | 中国农业银行 | 中国农业银行软件开发中心 | 第一届“雅典娜杯”分析挖掘大赛 | 第2名 | 2/581 |
2018 | 马上金融AI竞赛平台 | 马上金融 | AI全球挑战者大赛 — 违约风险识别赛 | 第4名 | 4/107 |
2018 | 天池大数据众智平台 | 阿里云 | 千里马大数据竞赛——风险识别算法赛 | 第5名 | 5/245 |
2018 | 蚂蚁金服金融科技平台 | 蚂蚁金服 | 蚂蚁开发者大赛 — 支付风险识别赛题 | 第9名 | 9/2986 |
2018 | 天池大数据众智平台 | 阿里巴巴 | IJCAI2018 — 阿里妈妈国际广告算法大赛 | 前2% | |
2018 | DataFountain | 中国平安 | 产险数据建模大赛——驾驶行为预测驾驶风险 | 前2% | |
2018 | kaggle | Two Sigma | Two Sigma Investment Financial Modeling Challenge | 前3% | |
2019 | 天池大数据众智平台 | 天津市津南区政府 | 津南数字制造算法挑战赛 | 第2名 | 2/2682 |
2019 | 中国农业银行 | 中国农业银行软件开发中心 | 第二届“雅典娜杯”分析挖掘大赛 | 第4名 | 4/361 |
因时间冲突未获奖的竞赛
年份 | 竞赛平台 | 举办单位 | 竞赛名称 | 竞赛成绩 |
---|---|---|---|---|
2016 | 滴滴AI竞赛平台 | 滴滴出行 | 首届全球DI-Tech算法大赛 | |
2016 | 融360自建平台 | 融360 | “天机”金融风控大数据竞赛 | |
2017 | DataCastle | 融360 | 智慧中国杯——用户贷款风险预测 | 前10% |
2017 | Kaggle | Sberbank | Sberbank Russian Housing Market | |
2017 | 天池大数据众智平台 | 高德 | KDD CUP Highway Tollgates Traffic Flow Prediction | |
2018 | 京东智汇平台 | 京东 | JData全球运筹优化大赛 |
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].