The Data Science roadmap, five lines at a time.

Getting a defensible answer out of messy data. Each module is numbered in the order it is meant to be read; every one of the 189 concepts has its five lines free.

189Concepts

14Modules

18Graded tests

258Questions

Start studying →

Jump to a module

Data Basics

14 concepts · 14 questions Study module 01 →

How raw observations become structured datasets, the forms data takes, and the roles that turn it into insight.

9 basics5 how it works

Maths for Data

13 concepts · 13 questions Study module 02 →

The core linear algebra and arithmetic notation needed to express and transform datasets efficiently.

5 basics6 how it works2 the edge

Descriptive Statistics

14 concepts · 14 questions Study module 03 →

Summarising the central tendency, spread, and shape of a dataset using compact numerical measures.

10 basics2 how it works2 the edge

Probability

14 concepts · 14 questions Study module 04 →

The mathematical rules governing uncertainty, likelihood, and the classic distributions that shape real data.

7 basics7 how it works

SQL

14 concepts · 14 questions Study module 05 →

Querying relational tables to filter, aggregate, join, and compute analytical metrics over tabular records.

6 basics6 how it works2 the edge

Data Wrangling

14 concepts · 14 questions Study module 06 →

Reshaping, filtering, grouping and joining tables with spreadsheets, NumPy arrays and pandas DataFrames.

5 basics7 how it works2 the edge

Data Cleaning

13 concepts · 14 questions Study module 07 →

Detecting and repairing corrupt entries, duplicates, inconsistent formats and erroneous observations.

5 basics7 how it works1 the edge

Visualisation

13 concepts · 13 questions Study module 08 →

Communicating numerical patterns through clear charts, perceptual colour choices and honest visual geometry.

8 basics5 how it works

Sampling and Inference

16 concepts · 16 questions Study module 09 →

Drawing reliable conclusions about large populations from small representative samples with quantified uncertainty.

6 basics9 how it works1 the edge

Experimentation

13 concepts · 14 questions Study module 10 →

Testing product and business changes against control groups with randomised trials and rigorous decision rules.

4 basics5 how it works4 the edge

Causal Inference

13 concepts · 13 questions Study module 11 →

Disentangling true cause and effect from mere statistical correlation when controlled experiments are impossible.

5 basics4 how it works4 the edge

Time Series

13 concepts · 14 questions Study module 12 →

Analysing chronological observations to identify trends, seasonal rhythms and historical projections.

4 basics7 how it works2 the edge

Data Engineering Basics

13 concepts · 14 questions Study module 13 →

The storage formats, distributed pipelines and orchestration platforms that supply data to analytical teams.

4 basics9 how it works

Data Science in Practice

12 concepts · 12 questions Study module 14 →

Translating technical analysis into business metrics, cohort behaviour, ethical governance and strategic decisions.

5 basics6 how it works1 the edge

Concept browser

All 189 concepts, A to Z, when you know the name and just want the page. The roadmap above is the reading order; this is the index.

A/B Testing Aggregate Functions Apache Spark ARIMA Models Array Broadcasting Autocorrelation Autoregressive Models Bar Charts Batch vs Stream Processing Bayes' Theorem Big Data Characteristics Binomial Distribution Box Plots Categorical vs Numerical Data Central Limit Theorem Chi-Square Test Choosing the Right Chart Cluster and Systematic Sampling Cohort Analysis Collider Bias Column Data Types Common Table Expressions Communicating Insights Complement and Union of Events Conditional Probability Confidence Intervals Confounding Variables Control and Treatment Groups Correlation Correlation vs Causation Covariance CSV Format Data Analytics vs Data Science Data Anonymisation Techniques Data Collection Data Engineering Data Ethics Data Granularity Data Lakehouses Data Lakes Data Lineage Data Literacy Data Privacy and Regulations Data Profiling Data Quality Dimensions Data Validation Rules Data Warehouses Date Parsing and Time Zones Deduplication Defining Good Metrics Difference in Differences Differencing Directed Acyclic Graphs in Causality Distributed Data Processing Dot Product Eigenvalues and Eigenvectors ELT Pipelines ETL Pipelines Expected Value Exploratory Data Analysis Exponential Growth Exponential Smoothing Filtering Groups with HAVING Filtering Rows Filtering with WHERE Forecast Evaluation Metrics Forecasting Horizon Funnel Analysis Goodhart's Law Groupby Grouping with GROUP BY Guardrail Metrics Handling NULL Values Heatmaps in Data Visualisation Histograms Hypothesis Testing Identity and Inverse Matrices Inconsistent Categories Inner Join Instrumental Variables Interaction Effects in Experiments Interquartile Range JSON Format Jupyter Notebooks Key Performance Indicators Kurtosis Law of Large Numbers Line Charts Logarithmic Scales Logarithms Matrices Matrix Multiplication Matrix Rank Matrix Transpose Mean Median Melting Wide to Long Merging DataFrames Minimum Detectable Effect Misleading Visualisations Missing Value Patterns Mode Moving Averages in Time Series Multi-Armed Bandits in Testing Multiple Testing Problem Natural Experiments Normal Distribution Norms and Distance Metrics Novelty and Primacy Effects NumPy Arrays Observational Studies Outer Joins Outlier Detection with IQR Outlier Detection with Z-Scores Outlier Treatment Outliers P-Value Parquet File Format Peeking in A/B Tests Percentiles and Quartiles Pipeline Orchestration Pivot Tables Pivoting Long to Wide Plotting Libraries Poisson Distribution Population vs Sample Primary Metrics Probability and Events Probability Distributions Propensity Score Matching Purpose of Visualisation Qualitative vs Quantitative Data Random Variables Randomised Controlled Trials Range Regression Discontinuity Relational Tables in SQL Reproducibility in Data Science Retention and Churn Metrics Rollout Strategies Row-Oriented vs Columnar Storage Rows and Columns Sample Ratio Mismatch Sample Size Determination Sampling Bias Sampling Distribution Scatter Plots Schema Enforcement Seasonality and Cycles Selecting with loc and iloc Selection Bias Self Join and Cross Join Series and DataFrames Simple Random Sampling Simpson's Paradox Skewness Small Multiples Sorting with ORDER BY Spearman Rank Correlation Spreadsheets Standard Deviation Standard Error Stationarity in Time Series Statistical Independence Statistical Power Stratified Sampling String Normalisation in Data Structured vs Unstructured Data Subqueries Summation Notation T-Test The Data Science Workflow The Null Hypothesis The SELECT Statement Tidy Data Time Series Cross-Validation Time Series Data Trend Component Type Coercion Type I and Type II Errors Uniform Distribution Unit of Randomisation Variance Vector Operations Vectorisation Vectors Visual Encoding and Colour Palettes What is Data Science?Window Functions