Tutorial: Supervised machine learning（教程：监督式机器学习（Supervised Machine Learning））¶
This tutorial will walk you through a simplified supervised machine learning project in Foundry and will cover the following steps:
- Set up a machine learning project in Foundry
- Train a model in Model Studio, Jupyter® notebooks, Code Repositories
2a. Train a model in Model Studio
2b. Train a model in a Jupyter® notebook
2c. Train a model in Code Repositories 3. Evaluate the performance of your models 4. Productionize a model
In this tutorial, we solve a hypothetical task of building a machine learning model to predict the average housing prices across American census districts. Our hypothetical company has access to regularly updating census district-level data that does not contain the average housing prices. We want to create a model that will provide an accurate prediction of house prices for our finance team.
To get started, start by learning to set up your project for machine learning.
Jupyter®, JupyterLab®, and the Jupyter® logos are trademarks or registered trademarks of NumFOCUS.
All third-party trademarks (including logos and icons) referenced remain the property of their respective owners. No affiliation or endorsement is implied.
中文翻译¶
教程：监督式机器学习（Supervised Machine Learning）¶
本教程将引导您在 Foundry 中完成一个简化的监督式机器学习项目，涵盖以下步骤：
- 在 Foundry 中设置机器学习项目
- 在 Model Studio、Jupyter® 笔记本（Jupyter® Notebooks）或代码仓库（Code Repositories）中训练模型
2c. 在代码仓库中训练模型 3. 评估模型性能 4. 将模型投入生产
在本教程中，我们将解决一个假设性任务：构建一个机器学习模型，用于预测美国人口普查区域的平均房价。假设我们所在的公司能够获取定期更新的普查区域级数据，但这些数据不包含平均房价。我们希望创建一个模型，为财务团队提供准确的房价预测。
要开始操作，请先学习如何为机器学习设置项目。
Jupyter®、JupyterLab® 以及 Jupyter® 标识均为 NumFOCUS 的商标或注册商标。
所有第三方商标（包括标识和图标）均归其各自所有者所有。本文不暗示任何关联或认可关系。