Pipelines can reduce the chances of error in your code. In this video, learn how to create pipelines using the Python library scikit-learn to make your code cleaner and more resilient to bugs.
- [Instructor] Machine learning … is not always about applying … a single machine learning algorithm. … For a lot of machine learning applications, … you'll need to apply various data processing steps, … data transformations, … and potentially multiple machine learning algorithms. … This can lead to a lot of code. … The question becomes, how do you keep your code organized … and as bug free as possible? … In this video, I'll share with you how you can use … Pipelines in Scikit Learn to make your code cleaner … and more resilient to bugs. … To demonstrate the utility of Pipelines, … this notebook shows how much less code you need … to chain together PCA and logistic regression … for image classification. … Before getting to that though, … you need to import the libraries that you're going to use. … The dataset using this notebook … is a modified version of the MNIST dataset … that contains 2000 labeled images … of each digit, zero and one. … The images are 28 pixels by 28 pixels. … For convenience, I arranged the data into a CSV file. …
This course was created by Madecraft. We are pleased to host this content in our library.
- Why use scikit-learn?
- Supervised vs. unsupervised learning
- Linear and logistic regression
- Decision trees and random forests
- K-means clustering
- Principal component analysis (PCA)