Data Scientist

☐ Python · Required · 6 hrs

Functions, loops, list comprehensions, OOP basics. Python is the language of data science — there is no alternative.

• What is Python? Setup & Your First Program (Python): https://chaduvuko.com/learn/python/what-is-python-setup
• Functions — Defining, Parameters, Return Values (Python): https://chaduvuko.com/learn/python/functions
• Reading & Writing Files (Python): https://chaduvuko.com/learn/python/reading-writing-files
• Exception Handling (Python): https://chaduvuko.com/learn/python/exception-handling

☐ Statistics · Required · 8 hrs

Distributions, hypothesis testing, p-values, confidence intervals, CLT. Bad statistics = wrong business decisions. This is the core skill.

• Probability Distributions and Bayes Theorem (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/math-foundations/probability-distributions

☐ SQL · Required · 5 hrs

JOINs, GROUP BY, window functions, subqueries. Real data lives in databases. You'll write SQL every single day.

• Your First Query — SELECT & FROM (SQL): https://chaduvuko.com/learn/sql/select-from
• Introduction to Joins (SQL): https://chaduvuko.com/learn/sql/joins-intro
• Grouping Data — GROUP BY (SQL): https://chaduvuko.com/learn/sql/group-by
• Subqueries — Queries Inside Queries (SQL): https://chaduvuko.com/learn/sql/subqueries

☐ Excel / Spreadsheets · Recommended · 2 hrs

Pivot tables, VLOOKUP, conditional formatting. Still used in 80% of business reporting, especially at MNCs and consulting.

☐ Pandas & NumPy · Required · 6 hrs

Data loading, cleaning, reshaping, merging. The workhorse of every data science notebook.

• Intro to NumPy and pandas (Python): https://chaduvuko.com/learn/python/numpy-pandas-intro
• Pandas for Data Analysis (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/programming/pandas-dataframes
• NumPy Arrays and Broadcasting (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/programming/numpy-arrays

☐ Data Visualisation · Required · 4 hrs

Matplotlib, Seaborn, Plotly. A good chart communicates in seconds what a table takes minutes to parse.

• Data Visualisation for ML (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/programming/matplotlib-seaborn

☐ Probability & Bayes · Required · 5 hrs

Conditional probability, Bayes theorem, priors. Required for ML models and A/B testing interpretation.

• Probability Distributions and Bayes Theorem (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/math-foundations/probability-distributions

☐ Machine Learning · Required · 15 hrs

Regression, classification, clustering, decision trees, gradient boosting (XGBoost). The core toolkit for prediction problems.

• What is Machine Learning? (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/classical-ml/what-is-ml
• Linear Regression (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/classical-ml/linear-regression
• Decision Trees (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/classical-ml/decision-trees
• Evaluation Metrics — Beyond Accuracy (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/evaluation/evaluation-metrics

☐ A/B Testing · Required · 5 hrs

Experiment design, power analysis, statistical significance, Bonferroni correction. The primary way product decisions get validated.

☐ Insight Storytelling · Required · 4 hrs

Structure findings for non-technical stakeholders, build decks, answer "so what?". The rarest skill in data science.

☐ NLP Basics · Optional · 6 hrs

Text cleaning, TF-IDF, embeddings, sentiment analysis. High demand in e-commerce and fintech for review/feedback analysis.

• Tokenisation and Word Embeddings (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/nlp/tokenisation-and-embeddings
• BERT and the Encoder-Only Family (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/nlp/bert-encoder-family

☐ Time Series · Optional · 5 hrs

ARIMA, Prophet, stationarity, decomposition. Demand forecasting is a major use case at DoorDash, Amazon, and logistics firms.

• RNNs and LSTMs — Sequence Modelling (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/deep-learning/rnns-and-lstms

☐ Model Deployment · Recommended · 5 hrs

Flask/FastAPI wrapper, Streamlit dashboards, basic Docker. A model that never ships has zero business value.

• Model Deployment — FastAPI, Docker, K8s (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/mlops/model-deployment

☐ BI Tools (Tableau / PowerBI) · Recommended · 4 hrs

Self-service dashboards for business teams. Reduces ad-hoc requests and makes your insights more accessible.