TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Web App with GUI for AutoML on Tabular Data

41 点作者 pplonski86超过 1 年前

2 条评论

canvascritic超过 1 年前
The real challenge with AutoML isn&#x27;t just the pipeline creation, but ensuring that the models generalize well to unseen data and real-world scenarios. Your project here is neat and I appreciate that it includes support for preprocessing and model explanations as these are often overlooked.<p>I wonder though about the robustness and reliability of the models it generates. automl, in its essence, risks overfitting or underfitting if not carefully managed, and introduces a layer of indirection that can make debugging far more difficult. how does this project avoid those pitfalls?<p>It would be interesting to see how your tool performs in diverse datasets and how resilient the models are against drift over time. nevertheless, it&#x27;s always good to see new takes on AutoML. keep probing the space and refining your approach
评论 #37253003 未加载
pplonski86超过 1 年前
Web App is using two open-source packages that I&#x27;ve created:<p>- MLJAR AutoML - Python package for AutoML on tabular data <a href="https:&#x2F;&#x2F;github.com&#x2F;mljar&#x2F;mljar-supervised">https:&#x2F;&#x2F;github.com&#x2F;mljar&#x2F;mljar-supervised</a><p>- Mercury - framework for converting Jupyter Notebooks into Web App <a href="https:&#x2F;&#x2F;github.com&#x2F;mljar&#x2F;mercury">https:&#x2F;&#x2F;github.com&#x2F;mljar&#x2F;mercury</a><p>You can run Web App locally. What is more, you can adjust notebook&#x27;s code for your needs. For example, you can set different validation strategies or evalutaion metrics or longer training times. The notebooks in the repo are good starting point for you to develop more advanced apps.