← Back to courses
Artificial Intelligence and Machine Learning
Machine Learning with Python and scikit-learn
From a table of data to a model you can trust
A classroom course in classical machine learning. The modules follow the sections of the scikit-learn user guide: supervised learning, unsupervised learning, model selection and evaluation, dataset transformations, inspection, model persistence, and the guide's own chapter on common pitfalls. You finish with a model trained on a dataset of your choice. This course prepares for no exam.
10Modules
IntermediateLevel
3 monthsDuration
COURSE THUMBNAIL
What you will be able to do
Prepare a dataset for modelling with pandas and scikit-learn
Train regression and classification models
Evaluate a model honestly with cross-validation and the right metric
Find structure in data with clustering
Build a pipeline, save the model and load it again
Recognise data leakage and other common mistakes
Course outline
01
Python data tools: NumPy and pandas
02
Loading datasets and dataset transformations
03
Supervised learning: regression
04
Supervised learning: classification
05
Tree-based models and ensembles
06
Model selection and evaluation: cross-validation and metrics
07
Unsupervised learning: clustering and dimensionality reduction
08
Pipelines and choosing the right estimator
09
Inspecting models and common pitfalls
10
Model persistence and a project on your own dataset
Tools you will use
Pythonscikit-learnpandasNumPyMatplotlibJupyter
What you need
Basic Python programming
School-level mathematics
