From the course: More Python Tips, Tricks, and Techniques for Data Science
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Creating machine learning pipelines - Python Tutorial
From the course: More Python Tips, Tricks, and Techniques for Data Science
Creating machine learning pipelines
- [Instructor] Handling multiple feature engineering or transformational steps can quickly become very tedious. Especially if we want to string these steps together. For example, in a machine learning project, we often want to impute missing values, scale numerical attributes, handle outliers and then train the model in that particular order. So, to automate such tasks, we can actually create processing pipelines and Python offers this using the circuit learn package and we have a pipeline class from the pipeline module to create such pipelines. So, to demonstrate this, I have created some sample data X which is a containing some missing values. And then I have VI which contains five values for each of the firewalls defined in X. So let's create this random data, now to create a pipeline. We have imported a few classes. So first of all, we have pipeline and we have simple imputed class for imputing missing values. We…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.