Machine learning
The analyst being asked for predictions, who needs the workflow to be honest about what a model does and does not know.
4 modules from the Python for Data Analysis curriculum.
What you'll learn
By the end of this course
- Describe the scikit-learn API — the fit / transform / predict pattern shared by every tool
- Split data into train and test sets (with stratification) and explain why holding out data is non-negotiable
- Scale features (StandardScaler, MinMaxScaler, RobustScaler) and know which models need it
- Encode categorical variables (OneHotEncoder, OrdinalEncoder)
- Impute missing values (SimpleImputer, KNNImputer)
- Combine steps cleanly with ColumnTransformer and Pipeline
- Recognise and prevent data leakage — the most damaging, most common ML mistake
- Use the uniform scikit-learn classifier API — fit / predict / predict_proba
Curriculum
4 sections · 4 lessons
Section 1
4 modules
Section 1
- Data Preparation for Machine LearningWelcome to machine learning. You've already built predictive models by hand with statsmodels; now we switch to scikit-learn, the standard Python ML toolkit, and adopt its professional workflow.~180 min
- ClassificationClassification is the task of predicting a category: which species, spam or not, will churn or stay. You met one classifier already — logistic regression (Notebook 46).~180 min
- ClusteringEvery model so far learned from labelled examples — you told it the right answer (species, survived, churned) and it learned to reproduce it. Clustering is different: it is unsupervised.~180 min
- End-to-End Machine Learning Workflow (Scikit-learn)This is the finale of the numbered curriculum — the notebook that ties everything together. You've learned the pieces: preparing data (47), classifying (48), clustering (49).~210 min
About this course
4 modules from the Python for Data Analysis curriculum.
This course covers Data Preparation for Machine Learning, Classification, Clustering and End-to-End Machine Learning Workflow (Scikit-learn).
About 12h 30m of material across 4 modules, each with the dataset it teaches from and exercises with worked solutions.
Every module is a notebook you download and run yourself in JupyterLab — the point is that you execute the code, not that you watch someone else execute it. Recordings are added module by module; a module without one yet is taught in full by its notebook.
Who it's for
- Researchers and postgraduate students who need the analysis done properly, not just done
- Analysts moving from spreadsheets to something repeatable and auditable
- Anyone who has followed a Python tutorial and still cannot open their own data and get an answer
- Practitioners who can already run the basics and want Machine learning to a standard they can defend
What you'll need
- A computer you can install Python and JupyterLab on — notebook 02 walks you through it, on Windows and on macOS
- No prior programming experience for the foundations; the later tracks assume the earlier ones
- Comfort with the earlier tracks of Python for Data Analysis, or equivalent experience
- Your own dataset is welcome but not required — every module ships with the data it teaches from
Start Machine learning today
Lifetime access, on any device, with your progress saved as you go.
You’ll sign in first — your access is tied to your account.