|Introduction to Machine Learning with Scikit-Learn|
|Written by Nikos Vaggalis|
|Wednesday, 14 July 2021|
A free course on the fundamentals of Machine Learning with Python, taught by Kevin Markham founder of Data School, helps you ease your way into ML and scikit-learn, one of the best-known libraries for this purpose.
Python certainly is the most popular language of doing ML, mainly due to the number of relevant libraries available. scikit-learn is one of tho top Machine Learning libraries alongside PyTorch, NumPy, SciPy, TensorFlow and Theano. Additionally, scikit-learn is one of the easiest to learn as such perfect for beginning one's ML journey. That doesn't mean that it lacks functionality though; it is perfectly capable of pulling off many ML tasks such as classification, clustering, pre-processing, regression, etc.
This fast paced course starts with the fundamentals and moves to more advanced topics in just under 4 hours. In the process you'll get to know ML,install scikit-learn & Jupyter notebook, go through the Machine Learning terminology, discover how to
There are 10 lessons:
1. What is Machine Learning, and how does it work?
2. Setting up Python for Machine Learning: scikit-learn and Jupyter Notebook
3. Getting started in scikit-learn with the iris dataset
4. Training a Machine Learning model with scikit-learn
5. Comparing Machine Learning models in scikit-learn
6. Data science pipeline: pandas, seaborn, scikit-learn
7. Cross-validation for parameter tuning, model selection, and feature selection
8. Efficiently searching for optimal tuning parameters
9. Evaluating a classification model
10. Building a Machine Learning workflow
In detail, Lesson 1 goes through the two main categories of Machine Learning (Supervised,Unsupervised) and some examples of Machine Learning.
Lesson 2 goes through Installing scikit-learn & Jupyter notebook for following along the exercises.The course code uses scikit-learn 0.23.2 and Python 3.9.1.
Lesson 3 is where the main class commences, by employing the famous Iris flowers dataset (it contains 3 classes of 50 instances each, where each class refers to a type of iris plant), loading it and working on it.
The rest of the chapters get deep into ML;training models,tuning parameters for those models, interpreting linear regression models,choosing which features to include ,doing K-fold cross-validation,evaluating a classification model,building and cross-validating ML Pipelines...
After each video there is an interactive quiz in order to check your understanding, plus pointers to recommended resources,while after completing the course you'll even get a certificate of completion.
It's a course that's valuable whether you are brand new to ML, in which case you should start from the beginning, and also if you're just new to scikit-learn, in which case you can safely skip the first few lessons and get straight into the main material. While being literate in Data Science is not a pre-requisite, but minimal knowledge of Python is.
In any case, it's a first class opportunity to ease your way into the ML world with help from a great Python library. After all, more than 80% of data scientists use scikit-learn, according to Kaggle's recent "State of Machine Learning" report. Count me in.
or email your comment to: firstname.lastname@example.org
|Last Updated ( Wednesday, 14 July 2021 )|