A box plot shows you how data is spread out across different groups. You should use this method when you want to compare numerical values across categories, identify extreme outliers, or understand the overall shape and center of your data in a single, clear summary view.
Understanding the Summary
A box plot simplifies complex datasets into a five-number summary: the minimum, first quartile, median, third quartile, and maximum. By displaying these values as a box with whiskers, it reveals where the majority of your data points cluster and how much variance exists within each group.
When you use this method in Lattice, it automatically calculates these boundaries for you. It also highlights extreme values as individual points, allowing you to spot anomalies in your data without having to scan through hundreds of rows manually.
Comparing Multiple Groups
One of the most effective ways to use this tool is for side-by-side comparisons. If you categorize your data—for example, comparing sales performance across different regions or manufacturing yield across different shifts—Lattice will generate a box plot for each category.
This layout allows you to visually identify if one group has a significantly higher median or a wider range of variation than others. It is an ideal first step before moving to more advanced testing methods, as it helps you confirm if the differences you see are worth further analysis.
Detecting Data Anomalies
The whiskers of the plot define the 'normal' range of your data based on the interquartile range. Any data point that falls outside of this range is flagged, giving you an immediate view of potential errors or unusual events in your dataset.
Because this method is deterministic, you get the exact same representation every time, ensuring that your initial assessment of the data is consistent. This helps you decide whether you need to investigate those extreme points or if they represent valid, extreme real-world observations.
1 · Intent → method
An LLM picks plot_boxplot from a fixed catalog.
2 · Method → numbers
Deterministic Python engine runs the math. Same input → same output.
3 · Numbers → plain language
A second LLM translates the result into your domain’s vocabulary.
What do the dots outside the box represent?
The dots outside the box are outliers, also known as 'fliers.' These are individual data points that fall beyond the standard range defined by the box plot's whiskers.
How is the range of the box calculated?
The box covers the middle 50% of your data, spanning from the 25th percentile (Q1) to the 75th percentile (Q3). The line inside the box represents the median value.
Tool input schema
Schema for plot_boxplot not exported yet (run pnpm export:registry).