Machine Learning Fundamentals

Course Description

As the use of machine learning algorithms becomes popular for solving problems in a number of industries, so does the development of new tools for optimizing the process of programming such algorithms. This course aims to explain the scikit-learn API, which is a package created to facilitate the process of building machine learning applications. By explaining the difference between supervised and unsupervised models, as well as by applying algorithms to real-life datasets, this course will help beginners to start programming machine learning algorithms.

Course Length

Two days

Target Audience

This course is perfect for beginners in the field of machine learning. No prior knowledge of the use of scikit-learn or machine learning algorithms is required. The students must have prior knowledge and experience of Python programming.

Technical Requirements

Hardware:

• Processor: Intel Core i5 or equivalent
• Memory: 4GB RAM or higher

Software:

• Sublime Text (latest version), Atom IDE (latest version), or other similar text editor applications.
• Python 3 installed
• The following Python libraries installed: NumPy, SciPy, scikit-learn, Matplotlib, Pandas, pickle, jupyter, and seaborn

Installation and Setup

Before you start this course, you'll need to install Python 3.6, pip, scikit-learn, and the other libraries used in this course. You will find the steps to install these here:

Installing Python

• Install Python 3.6 by following the instructions at this link: https://realpython.com/installing-python/.

Installing pip

• To install pip, go to the following link and download the get-pip.py file: https://pip.pypa.io/en/stable/installing/.
• Then, use the following command to install it: python get-pip.py

You might need to use the python3 get-pip.py command, due to previous versions of Python on your computer are already using use the python command.

Installing libraries

Using the pip command, install the following libraries:

• python -m pip install --user numpy scipy matplotlib jupyter pandas seaborn

Installing scikit-learn

• Install scikit-learn using the following command: pip install -U scikit-learn

Course Outline

Lesson 1: Introduction to scikit-learn

• scikit-learn
• Data Representation
• Data Preprocessing
• scikit-learn API
• Supervised and Unsupervised Learning

Lesson 2: Unsupervised Learning: Real-life Applications

• Clustering
• Exploring a Dataset: Wholesale Customers Dataset
• Data Visualization
• k-means Algorithm
• Mean-Shift Algorithm
• DBSCAN Algorithm
• Evaluating the Performance of Clusters

Lesson 3: Supervised Learning: Key Steps

• Model Validation and Testing
• Evaluation Metrics
• Error Analysis

Lesson 4: Supervised Learning Algorithms: Predict Annual Income

• Exploring the Dataset
• Naïve Bayes Algorithm
• Decision Tree Algorithm
• Support Vector Machine Algorithm
• Error Analysis

Lesson 5: Artificial Neural Networks: Predict Annual Income

• Artificial Neural Networks
• Applying an Artificial Neural Network
• Performance Analysis

Lesson 6: Building your own Program

• Program Definition
• Saving and Loading a Trained Model
• Interacting with a Trained Model