DATA & TECH
Data Science & Machine Learning with Python: From pandas to a Deployed Model
The next rung after Python and data analysis — clean real Nigerian data with pandas 3, explore it, train and honestly evaluate regression, classification, clustering and forecasting models with scikit-learn, handle the ethics and the NDPA, and deploy a working prediction app to a free cloud tier.
- 12 lessons
- ~3 hours
- Intermediate
- Project + certificate
Free account required to open the lessons. Any price is shown before you pay.
- Free to startOpen a free account and start. Any price is shown before you pay.
- Earned, not boughtCertificates are never sold. You pass a graded project, and anyone can verify it.
- Self-pacedShort lessons you take at your own pace. Your progress is saved.
- Built for real workLessons follow how the work is actually done and paid for, and end in a project you can show.
What you'll learn
- Data science
- Machine learning
- Python for data science
- pandas and NumPy
- Data cleaning
- Exploratory data analysis
- Data visualisation
- Applied statistics
- scikit-learn
- Regression and classification
- Model evaluation
- Feature engineering
- Clustering and anomaly detection
- Time-series forecasting
- Responsible AI and data protection (NDPA)
- Model deployment (FastAPI, Streamlit)
- Data science portfolio
About this course
You can write Python and you can make a spreadsheet tell a story. This course takes you the rest of the way: from a messy CSV to a machine-learning model that runs on the internet and answers questions people will pay for. Working on two deliberately messy Nigerian datasets — Lagos rent listings and a lender's loan-repayment records — you learn pandas 3 the way it is used in 2026, the cleaning that takes most of a data scientist's week, exploratory analysis and the charts that carry an argument, the statistics behind an honest claim, regression and classification with scikit-learn 1.9, the metrics that stop you fooling yourself when 85 percent of borrowers repay anyway, feature engineering and model selection without leakage, clustering, anomaly detection, forecasting and a first look at text, and the responsible-ML questions the Nigeria Data Protection Act now makes law: lawful basis, profiling, automated decisions, proxies for ethnicity and gender. Then you ship it — a saved model behind a FastAPI endpoint and a Streamlit app on a free tier — and build the portfolio and the career plan that the Nigerian and remote job markets actually reward. Every tool is free; every fact is dated September 2026.
A trader in Aba wants to know which customers will pay late. A landlord in Lekki wants to know what a flat is worth. A hospital in Kano wants to know which children will miss their second vaccination. None of these people wants 'machine learning'; they want a better decision. Data science is the discipline of turning a question and a pile of records into that decision, and machine learning is one of its tools — a powerful one that is also the wrong answer surprisingly often. This course teaches the whole pipeline on two Nigerian datasets, in the Python you already know, with the tools that are free in September 2026, and it ends with a model running on the internet that answers a real question.
Who it's for
Intermediate. Some grounding in the subject will help you move faster.
The lessons 12 lessons, ending in a graded project
- 1What data science is for — the pipeline from question to deployed model, when not to use machine learning, the 2026 Python stack, and where Nigerian data lives13 min
- 2pandas 3 fundamentals — DataFrames and Series, reading a CSV, types, selecting and filtering, groupby, merge, dates, and what changed in 3.015 min
- 3Cleaning real Nigerian data — missing values and why they are missing, naira strings, three date formats, duplicates, outliers, inconsistent categories, and a clean() function you can rerun15 min
- 4Exploratory analysis — distributions, groups and relationships; charts that make one point each; base rates, Simpson's paradox and the questions to ask before any model14 min
- 5The statistics you actually need — samples and populations, uncertainty and confidence intervals, hypothesis tests and what a p-value is not, A/B tests, and correlation versus causation14 min
- 6Your first model: regression — predicting Lagos rent with scikit-learn, train/test splits, a baseline, Pipelines and ColumnTransformers, MAE, RMSE and R², residuals, and overfitting15 min
- 7Classification — predicting loan default with logistic regression, trees, random forests and gradient boosting; the accuracy trap, precision, recall, ROC and PR curves, thresholds set by cost, and calibration16 min
- 8Feature engineering and model selection — domain features, dates, encodings, leakage, tuning with cross-validation, learning curves, importance and SHAP, and making it all reproducible15 min
- 9Beyond prediction — customer segmentation with k-means, PCA, anomaly detection for fraud, forecasting sales and FX with time series, a first look at Nigerian text, and when to call an LLM instead15 min
- 10Responsible machine learning in Nigeria — the NDPA on lawful basis, profiling and automated decisions; proxies for ethnicity, religion, gender and state; fairness checks; explanations; model cards; and anonymisation that actually works15 min
- 11Deploying the model — saving the pipeline, a FastAPI prediction endpoint, a Streamlit app, free hosting on Hugging Face Spaces or Streamlit Community Cloud, Docker basics, and monitoring for drift15 min
- 12The portfolio and the career — notebooks into repositories, Kaggle and open data, the roles and pay in Nigeria and remotely, interviews, certifications honestly rated, and your project13 min
- Project: Your End-to-End ML Project, DeployedGraded
THE PROJECT AND YOUR CERTIFICATE
Your End-to-End ML Project, Deployed
One shared link (Google Doc, Notion page or the README itself) containing the live app URL, the public repository URL, and the responsible-ML note.
Certificates on Skillnaija are earned, not issued for attendance: you submit this project, an examiner grades the real work against a published rubric (you need 65% to pass), and passing issues a certificate anyone can verify. If you don't pass yet, you get written feedback and can try again.
- A real, decision-relevant question on a dataset of 1,000+ rows, with the user and the decision named10%
- Cleaning is documented step by step with before/after counts, and exploration produces five or more single-point charts with interpretations and a stated base rate or typical value20%
- A baseline plus two model families in Pipelines, honest evaluation with problem-appropriate metrics and a stated threshold, a justified choice, and a leakage check30%
- The responsible-ML note addresses lawful basis, profiling and automated decisions, proxy features and their mitigation, and gives a plain-language explanation15%
- The deployed app is live, accepts new input, returns a prediction with a version and caveat15%
- The repository is public, runnable from pinned requirements, free of secrets and raw personal data, with a README that reports metrics beside the baseline10%
Frequently asked questions
Is Data Science & Machine Learning with Python: From pandas to a Deployed Model free?
Most Skillnaija courses can be started free with a free account: your first two courses are free to start, then one new course each month. Some courses are paid; the course page in the app shows whether Data Science & Machine Learning with Python: From pandas to a Deployed Model is one, and its price, before you pay. You can also buy any course on its own for twelve months, or open every course with the All-Access Pass. Certificates are never sold: you earn one by passing the course's project.
How long does Data Science & Machine Learning with Python: From pandas to a Deployed Model take to complete?
8 weeks · ~5 hrs/week. There are 12 lessons, about 3 hours of material in total. You learn at your own pace and your progress is saved.
Do I need any experience to start Data Science & Machine Learning with Python: From pandas to a Deployed Model?
Intermediate. Some prior grounding in the subject will help you move faster.
What will I learn in Data Science & Machine Learning with Python: From pandas to a Deployed Model?
You will build practical skills in Data science, Machine learning, Python for data science, pandas and NumPy, Data cleaning, Exploratory data analysis, Data visualisation, Applied statistics, scikit-learn, Regression and classification, Model evaluation, Feature engineering, Clustering and anomaly detection, Time-series forecasting, Responsible AI and data protection (NDPA), Model deployment (FastAPI, Streamlit), Data science portfolio. Every lesson is written in plain English, with examples drawn from how the work is actually done and paid for, in Nigeria and beyond.
Do I get a certificate for Data Science & Machine Learning with Python: From pandas to a Deployed Model?
Yes, but it has to be earned. You complete the course project — Your End-to-End ML Project, Deployed and submit it for grading. Passing the project issues a verifiable certificate; finishing the lessons alone does not.
Ready to start Data Science & Machine Learning with Python: From pandas to a Deployed Model?
It is self-paced, and it ends with something you can show an employer.
Start learning free