Machine Learning with Python

Welcome to the course!

This page contains the material for the Machine Learning with Python course at Sendai KOSEN on 25th to 28th February, 2020.

Please send your assignment answers for grading at latest on Tuesday, 3rd March. You can send them as email attachments to vesa.ollikainen@metropolia.fi.

Note: for Day 3, one assignment is enough. You can send the answers in ipynb or pdf format. Thank you.

Day 1: Introduction and working with data

Learning goals:

  1. Understand the basics of machine learning.
  2. Learn to process, examine and visualise data with pandas Python library.
Course material
Material Link
Lecture slides: Introduction to machine learning pdf
Lecture slides: Data manipulation pdf
Assignment: Working with data in Python html
Demo: Basic data manipulation ipynb pdf
Demo: Iris ipynb csv pdf

Day 2: Clustering

Learning goals:

  1. Learn the idea and application area of clustering.
  2. Understand the theory of k-means and hierarchical clustering.
  3. Learn to carry out clustering tasks with sklearn Python library.
Course material
Material Link
Lecture slides: Clustering pdf
Assignment: Drone delivery (clustering) html
K-means demo spreadsheet xlsm
Demo: Appreciation (k-means) ipynb pdf
External links
Title Link
Naftali Harris: Visualizing K-Means Clustering html (external)

Day 3: Classification

Learning goals:

  1. Learn the performance metrics of classifiers.
  2. Understand the principles of kNN, decision tree, and random forest classifiers.
  3. Learn the validation techniques.
  4. Learn to carry out classification tasks with sklearn Python library.
Course material
Material Link
Lecture slides: Classification pdf
Assignment option 1: Butterfly flu (kNN) html
Assignment option 2: Phishing websites (decision tree) html
kNN demo spreadsheet xlsx
Demo: ILPD (kNN) ipynb pdf
Demo: Titanic (decision tree) ipynb csv pdf

Day 4: Regression and association rule mining

Learning goals:

  1. Learn the idea of multiple linear and logistic regression.
  2. Learn how to evaluate a regression model.
  3. Understand the idea of association rule mining.
  4. Learn to carry out linear and logistic regression with sklearn Python library.
  5. Learn to carry out association analysis with apyori Python library.
Course material
Material Link
Lecture slides: Linear and logistic regression pdf
Lecture slides: Association rule mining pdf
Demo: Stack loss (linear regression) ipynb csv pdf
Demo: Stroke (logistic regression) ipynb csv pdf
Demo: Fan item store (association rule mining) ipynb csv pdf
Assignment: Diagnostic tool (logistic regression) html

Manuals and documentation

Manuals and documentation
Material Link
pandas pdf html (external)
sklearn pdf html (external)
seaborn html (external)
apyori (unofficial documentation) html (external)
Pandas Cheat Sheet html (external)