Hands-On Machine Learning with Python and Scikit-Learn, published by Packt
This is the code repository for Hands-On Machine Learning with Python and Scikit-Learn [Video], published by Packt. It contains all the supporting project files necessary to work through the video course from start to finish.
Machine learning and artificial intelligence are the new big data—at least as far as buzzwords in the workplace go. The scikit-learn library is one of the most popular platforms for everyday Machine Learning and data science because it is built upon Python, a fully featured programming language. This course will help you discover the magical black box that is Machine Learning by teaching a practical approach to modeling using Python along with the Scikit-Learn library.
We begin our journey by observing the end result of a Machine Learning deployment before moving back to the fundamentals and into exploratory data analysis. Moving on, we learn to develop complex pipelines and techniques for building custom transformer objects for feature extraction, manipulation, and other effective data cleansing techniques. Finally, we discover how to select a model, apply optimal hyper-parameters, and deploy it.
This video course highlights clean coding techniques, object-oriented transformer design and best practices in Machine Learning while using the Scikit-Learn library and also maintaining a focus on practicality and re-usability, ensuring these techniques can be applied to Machine Learning projects of any size.
- Split data effectively using the Scikit-Learn package
- Explore, organize, manipulate, and analyze your data (including some visual and descriptive statistics techniques)
- Enhance your model performance using cross-validation
- Build and design model pipelines using Scikit-Learn paired with your custom transformers
- Tune and optimize hyperparameters to select the best model for the job
- Persist a model for use in production
To fully benefit from the coverage included in this course, you will need:
This course is aimed at students and data-scientists with prior Python programming experience and keen to upgrade their Machine Learning skills using Python.A basic familiarity with, or exposure to, some level of statistics is recommended, but not required.
This course has the following software requirements:
This course has the following software requirements: ● Anaconda 4+ ● Python 2.7+ ● Package requirements (installed in video 1.2 and included in environment.yml): ● numpy ● scipy ● scikit-learn >= 0.18 ● pandas ● bokeh ● matplotlib ● seaborn ● flask ● requests This course has been tested on the following system configuration: ● OS: Mac OS X 10.12 ● Processor: 2.5 GHz Intel Core i7 ● Memory: 16GB ● Hard Disk Space: 500MB