Use this tool when a model, such as a random forest or a permutation-importance run, has told you how much each variable matters and you need a clear, report-ready figure. Upload an Excel, CSV or SPSS file (or paste it) with a feature name and its importance, optionally with the standard deviation and number of repeats, and click Analyze data to get a ranked importance plot and an APA 7 write-up.
About feature importance plots
A feature importance plot ranks the variables used by a model from most to least important. Importance values usually come from permutation importance, mean decrease in impurity or a similar measure. When you also supply the standard deviation and the number of repeats, the tool turns the ranking into inference: it computes a standard error, a 95% confidence interval and a test of whether each importance differs from zero.
When to use it
Use it to report which predictors drive a model in genomics, clinical prediction, ecology, education or any field that fits random forests, gradient boosting or similar models. It does not fit the model for you; it presents and tests importance values you already have, and it always reports relative and cumulative importance even when you supply only the values.
What this tool reports
A ranked importance plot of the top features, with error bars when a standard deviation is given.
Relative importance and cumulative importance for every feature.
Standard error, t-test against zero and 95% confidence interval from the SD and number of repeats.
Holm-adjusted p values for the multiple tests.
Editable APA7 results text and APA7-style tables.
Downloads as PNG, SVG, CSV tables and a Word (.docx) report.
Assumptions to check
Importance values come from the same model and the same scale, so they can be compared.
Permutation repeats are treated as independent when the standard error is calculated, which makes the intervals approximate.
Correlated predictors share importance, so a low value does not prove that a variable is unrelated to the outcome.
How to report it in APA7
Describe the model and the importance measure, report how many features were ranked, and give the most important features with their importance, 95% confidence interval and adjusted p value, plus the cumulative share of importance they account for. The tool writes this paragraph for you and you can edit it before downloading.
Frequently asked questions
Is the feature importance plot generator free?
Yes. You can run the analysis, edit the plot and read the APA7 results without an account. Create a free account or log in only when you want to download the results.
What data do I need?
Two columns are enough: the feature name and its importance. Add the standard deviation and the number of permutation repeats to get standard errors, confidence intervals and tests.
Does this tool train the model?
No. It presents and tests importance values from a model you have already fitted, for example in R, Python or SPSS.
Is my data uploaded to a server?
The analysis runs in your browser, so your data stays on your device while you work with the tool.