-
Notifications
You must be signed in to change notification settings - Fork 0
docs(guides): expliquer densité et largeur des classes #31
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Changes from all commits
733fb5d
50c0e07
990bed0
6547014
4b20bf7
d1060c8
e0a71a4
bc514f5
e8636d9
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,27 @@ | ||
| Counts vs Density | ||
| ================= | ||
|
|
||
| Both columns show the same 500 observations with two different binning schemes. | ||
| With equal-width bins, counts and density have the same shape. With variable-width | ||
| bins, raw counts favor wider intervals and can distort the visual comparison. | ||
|
|
||
| .. image:: images/counts-vs-density.png | ||
|
|
||
| With equal-width bins, taller bars indicate a greater probability of falling | ||
| within that interval. When bin widths vary, height alone is not enough: | ||
| probability is represented by the bar's area, calculated as density multiplied | ||
| by bin width. | ||
|
|
||
|
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. For a detailed introduction to density and variable-width bins
Collaborator
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. done
Collaborator
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. L'utilisateur est clairement prioritaire; il faut donc garder ce tableau. Par contre, corriger:
Collaborator
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. done |
||
| Note that variable-width bins are ideal for unbalanced distributions and outliers, | ||
| as shown in `Histograms - Khiops <https://khiops.org/learn/histograms/>`_. | ||
|
|
||
| Reading variable-width histograms | ||
| --------------------------------- | ||
|
|
||
| .. csv-table:: | ||
| :header: "Question", "Use", "What to compare" | ||
| :widths: 35, 35, 30 | ||
|
|
||
| "How many observations?", "Counts (``density=False``)", "Bar heights" | ||
| "What fraction of observations?", "Counts divided by :math:`N`, or density", "Bar areas" | ||
| "Where are values concentrated?", "Density (``density=True``, the Khisto default)", "Bar heights" | ||
Large diffs are not rendered by default.

There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What does
always()add here, as it is always true? I would consider removing it.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
always() permet d’exécuter ce job lorsque build est skipped, notamment à la fermeture d’une PR. Sans lui, GitHub Actions applique implicitement success() et ignore preview, empêchant ainsi la suppression de l’aperçu. Je propose donc de le conserver.