D4PythonIntermediateAbout 150 min to complete
Statistical Visualizations
Where the previous notebooks taught you how to draw (Matplotlib) and how to draw quickly (Seaborn fundamentals), this notebook is about what to draw when you want a chart to make a statistical argument. A statistical visualization is not just a picture of numbers.
Notebook
About 150 minutes to complete
Enrol to read the notebook and download it to run.
What this module covers
Where the previous notebooks taught you how to draw (Matplotlib) and how to draw quickly (Seaborn fundamentals), this notebook is about what to draw when you want a chart to make a statistical argument. A statistical visualization is not just a picture of numbers.
By the end of it
- Distinguish the major families of statistical plots (distribution, categorical, relational, regression, multivariate) and match each to the question it answers
- Visualize a single variable's distribution using histograms, KDE curves, ECDFs, and rug plots — and explain what each reveals and hides
- Compare groups with box plots, violin plots, boxen plots, strip/swarm plots, and bar/point plots with confidence intervals
- Show relationships between two numeric variables using scatter, 2-D density, regplot, lmplot, and residual plots
- Explore many variables at once with pairplot, correlation heatmaps, and clustermap
- Read and represent uncertainty — confidence intervals, error bars, and bootstrapping — instead of hiding it
- Avoid the classic statistical-graphics mistakes (bar-charts-of-means, truncated axes, overplotting, chart-junk) that mislead readers