课程: Machine Learning with Scikit-Learn

今天就学习课程吧！

今天就开通帐号，24,600 门业界名师课程任您挑！

Principal component analysis (PCA) for data visualization

Principal component analysis (PCA) for data visualization - scikit-learn教程

课程: Machine Learning with Scikit-Learn

开始一个月试用 购买团队方案

Principal component analysis (PCA) for data visualization

“

- [Narrator] Are all the features in our dataset needed? Say you have some flowers and you measure their petal length. If you have a column of that measurement in centimeters, and another column with measurement in inches do you need both columns? In that circumstance, you could probably drop either column without losing information. In other cases dropping a column could lead to issues. Principal Component Analysis better known as PCA. Is a technique that you can use to smartly reduce the dimensionality of your dataset while losing the least amount of information possible. One use of PCA, is for data visualization. In this video, I'll share with you how you can use PCA to help visualize your data. The first step is to import libraries. From there, you can load your dataset. The dataset used in this notebook is the hours dataset. The next step is to standardize your data PCA like a lot of different algorithms is…

内容