课程: AutoML: Build Production-Ready Models Quickly!

今天就学习课程吧！

今天就开通帐号，24,100 门业界名师课程任您挑！

Choosing the right model for your data

Choosing the right model for your data - Python教程

课程: AutoML: Build Production-Ready Models Quickly!

开始一个月试用 购买团队方案

Choosing the right model for your data

“

- [Instructor] So we have successfully transformed our features into numeric values that most machine learning models prefer to deal with. Next, we must split our data set into a training and validation set. This will allow us to obtain an unbiased evaluation of the models we train before we apply them to real world data. We'll make use of psychic lens string test split function and use a 30% test size. Because our data set is imbalanced, we will also split on a target column that is claim. This will ensure that a proportion of claim to no claim is preserved in both splits of our data set. After doing this, we are ready to start building models. It is always good to start small when building machine learning models for a task. Let us build a baseline model, a simple model that we can use as a benchmark. For this, we will use logistic regression. We will initialize our logistic regression model as set is class weight to…

内容