Applied-Machine-Learning-in-Python

This is one course I studied on Coursera which introduces the application of machine learning, focusing more on the techniques and methods than on the statistics behind these methods. (View Certificate) - October 2020

Objectives

• Identify the difference between a supervised (classification) and unsupervised (clustering) technique.
• Identify which technique they need to apply for a particular dataset and need.
• Engineer features to meet that need.
• Write python code to carry out an analysis.

Syllabus

Module 1: Fundamentals of Machine Learning - Intro to SciKit Learn

• Understand basic machine learning concepts and workflow.
• Distinguish between different types of machine learning tasks, based on examples of how they are applied to real-world problems.
• Understand how a basic classification algorithm (k-nearest neighbors) learns and makes predictions.
• Build and evaluate a basic k-nearest neighbors classifier on an example dataset using Python and scikit-learn.

Module 2: Supervised Machine Learning - Part 1

• Understand how different supervised learning algorithms - in particular, those based on linear models - estimate their own parameters from data to make new predictions.
• Understand the strengths and weaknesses of particular supervised learning methods in order to apply the right algorithm for a given task.
• Apply specific supervised machine learning algorithms in Python with scikit-learn.
• Recognize general principles of supervised machine learning that are common across algorithms, such as the connection between model complexity and generalization performance.
• Apply techniques like regularization, feature scaling, and cross-validation to avoid common pitfalls like under- and overfitting.

Module 3: Evaluation

• Understand why accuracy alone can be an inadequate metric for getting a more complete picture of a classifier's performance.
• Understand the motivation and definition of a variety of important evaluation metrics in machine learning and how to interpret the results of using a given evaluation metric.
• Optimize a machine learning algorithm using a specific evaluation metric appropriate for a given task.

Module 4: Supervised Machine Learning - Part 2

• Understand how specific supervised learning algorithms - in particular, those based on decision trees and neural networks - estimate their own parameters from data to make new predictions.
• Apply the right algorithm for a given task by understanding the strengths and weaknesses of additional supervised learning methods.
• Apply additional types of supervised machine learning algorithms in Python with scikit-learn.
• Recognize and avoid instances of data leakage.