Back Back
Index Index Next Next

Python Programming and Machine Learning Crash Course

  • Intro
  • Schedule
  • Preparation
  • Day 1
  • Day 2
  • Day 3
  • Day 4
  • Related Tutorials

Information

Course Code ARIT1507
Last updated August 25, 2026
Keywords
Primary study Master
Secondary study BK Master

Responsible

Teachers
Faculty

Python Programming and Machine Learning Crash Course 0/7

Python Programming and Machine Learning Crash Course

 

This tutorial was developed for Creative Robotics in Spatial Design, an interdisciplinary MSc course taught at the Faculty of Architecture and the Built Environment, in collaboration with the faculties of Industrial Design Engineering and Mechanical Engineering.

 

One of the modules of the course introduces students to fundamental programming skills using Python. It covers the basic concepts and methods, as well as the main libraries used in the course. The aim is to provide a starting point for students, so they can start using programming to develop robotics applications and improve their skills further.

Start Start

Python Programming and Machine Learning Crash Course 1/7

Schedule

Schedule

 
Schedule Workshop Content Learning Objectives Required Before Workshop
Preparation

Preparing the Python programming environment before the course starts
  • Install Python programming and required packages/libraries needed for the course
  • Create and launch a Jupyter Notebook to write and run code
  • Import datasets into Jupyter Notebook for analysis and modeling
Primary in Google Colab:
Alternative in VS Code: 

Wed

Sep 2

8:45-12:45

Introduction to Python

  • Data types
  • Lists
  • Variables
  • Mathematical operations
  • Basic operations

Functions and Classes

  • Defining function input/output arguments
  • Class methods and attributes
  1. Differentiate between Python data types and select the appropriate type for a given use case
  2. Assign variables of various data types and execute basic mathematical and logical operations
  3. Construct lists to store, organize, and manipulate data
  4. Define custom functions with appropriate input/output arguments to solve programming problems
  5. Explain the principles of functional programming  and apply them to structure reusable code
  6. Construct simple classes and identify the role of methods and attributes within them

 

 

 

 

 

    

Thu

Sep 3

8:45-12:45

Conditional Statements and Loops

  • if / elif / else statements
  • for-loop / while-loop
  • Iteratively append items to lists

Popular Python Libraries

  • NumPy
  • Matplotlib
  • Pandas
  1. Apply conditional statements to control program logic
  2. Implement for-loops and while-loops to repeat tasks and iteratively append items to lists
  3. Combine conditionals and loops to solve simple programming problems
  4. Differentiate between popular Python libraries and select the appropriate one for a given task
  5. Develop functions incorporating library functions
  6. Apply library functions to perform data operations

 

 

 

 

Mon

Sep 7

8:45-12:45

Introduction to Computer Vision

  • Overview of existing vision models
  • Practical object detection and segmentation concepts
  • Zero-shot learning of pre-trained vision models
  • Fine-tuning of vision models

Git Workflow

  • Version control
  • Remote server setup
  1. Compare existing vision models and their application for object detection and segmentation tasks
  2. Apply object detection and segmentation concepts to identify and localize objects in images
  3. Perform zero-shot learning or fine-tuned a pre-trained vision model for a specific object detection and segmentation task
  4. Explain the principles of version control and their role in collaborative development
  5. Set up a connection to a remote server/repository
  6. Implement a basic git workflow to track, commit, and push code changes

Tue

Sep 8

8:45-12:45

Reinforcement Learning

  • Markov Decision Process
  • Value iteration
  • Policy iteration
  • Q-learning

Python for Grasshopper

  • Create Python script for Grasshopper
  • Using Hops to run Python Scripts
  1.  Formulate a problem as a Markov Decision Process
  2. Apply value iteration and policy iteration to compute optimal policies
  3. Implement Q-learning to solve a reinforcement problem
  4. Write a Python script for use within Grasshopper
  5. Configure Hops to run Python scripts from Grasshopper
  6. Integrate Python-based computation into a Grasshopper workflow

 

Previous chapter Previous chapter Next chapter Next chapter

Python Programming and Machine Learning Crash Course 2/7

Preparation

Preparation Tutorial

This preparation tutorial is required before starting the course. You will:

  • Install Python programming and required packages/libraries needed for the course
  • Create and launch a Jupyter Notebook to write and run code
  • Import datasets into Jupyter Notebook for analysis and modelling

Complete this tutorial below:

Create Your First Programming Project Directory (Python, Jupyter Notebook)
Previous chapter Previous chapter Next chapter Next chapter

Python Programming and Machine Learning Crash Course 3/7

Day 1

Day 1 aims to boost your confidence with programming. It is good for absolute beginners with no prior background in Python or existing Python users who wish to have a refresher over the basic concepts.

Following this day’s workshops, you will be introduced to Python basics (data types, lists, variables, mathematical operations and basic operations) and learn about functions and classes (defining function input/output arguments and class methods and attributes).

Below are the links to the workshops scheduled for day 1.

Download Git Project
Project files (ZIP, 385 KB)
Download Jupyter Notebook
Jupyter Notebook for Day 1 (ZIP, 15 KB)
Previous chapter Previous chapter Next chapter Next chapter

Python Programming and Machine Learning Crash Course 4/7

Day 2

Day 2 builds on your existing understanding of Python to create complex programs using your own functions and external functions imported as libraries.

Following this day’s workshops, you will learn about conditional statements and loops (if / elif / else statements, for-loop / while-loop, iteratively append items to lists) and get familiar with popular Python libraries (NumPy, Matplotlib, Pandas).

Below are the links to the workshops scheduled for day 2.

Download Jupyter Notebook
Jupyter Notebook for Day 2 (ZIP, 872 KB)
Previous chapter Previous chapter Next chapter Next chapter

Python Programming and Machine Learning Crash Course 5/7

Day 3

Day 3 builds on your understanding of functions and classes, statements and loops, and Python libaries.

Following this day’s workshops, you will be introduced to Computer Vision (overview of existing vision models, practical object detection and segmentation concepts, zero-shot learning of pre-trained vision models, fine-tuning of vision models) and work with Git workflow (version control, remote server setup).

Below are the links to the workshops scheduled for day 3.

Download Jupyter Notebook
Jupyter Notebook for Day 3 (ZIP, 7 MB)
Previous chapter Previous chapter Next chapter Next chapter

Python Programming and Machine Learning Crash Course 6/7

Day 4

Day 4 is the final day of this course and builds on everything you’ve learned so far.

Following this day’s workshops, you will learn about Reinforcement Learning (Markov decision process, value iteration, policy iteration, and Q-learning) and use Python for Grasshopper (creating scripts and using Hops to run them).

Below are the links to the workshops scheduled for day 4.

Previous chapter Previous chapter Next chapter Next chapter

Python Programming and Machine Learning Crash Course 7/7

Related Tutorials

Previous chapter Previous chapter Next chapter Next chapter