A histogram is your first step to seeing the shape of your data. Use it when you need to understand how values are spread out, identify common patterns, or spot unusual outliers. By grouping your data into visual bars, Lattice helps you move from raw numbers to a clear picture.
Seeing the Full Picture
A histogram organizes your data into intervals, often called 'bins.' Instead of looking at individual rows, you see the frequency of values falling into specific ranges. This makes it immediate to tell if your data clusters around a single center or if there are multiple peaks suggesting hidden categories.
On Lattice, the tool automatically calculates these bin sizes to give you the most accurate view. You can also add a density curve over the bars to smooth out the visual and highlight the underlying distribution shape.
Identifying Patterns and Skew
Visualizing your data helps you detect skewness—where the data tails off more to one side than the other. Recognizing these shapes is essential before performing more complex calculations, as certain methods perform better when data is balanced or centered.
If you see a long tail or gaps, you might consider transformations or choosing a different analytical approach. The histogram provides the visual evidence needed to make those decisions with confidence.
Grouping for Comparison
When your data contains categories—such as different store locations, test groups, or time periods—you can use the group-by option. This displays separate histograms for each category, allowing you to spot differences in spread or central tendency at a glance.
Comparing distributions side-by-side is often more informative than just looking at averages. It reveals if one group is much more consistent than another, even if their averages appear similar.
1 · Intent → method
An LLM picks plot_histogram 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.
Why does my histogram look like a single bar?
This happens when all the values in your data column are identical. A histogram requires variation in your data to draw different bars.
Can I compare different categories in one view?
Yes. By using the grouping feature, Lattice will overlay or separate the distributions, allowing you to visually compare how different categories behave.
Tool input schema
Schema for plot_histogram not exported yet (run pnpm export:registry).