Upload a CSV, pick your numeric columns, and get a full principal component analysis — scree chart, loadings, feature contributions, and an observation map. Free.
Free analyses run on up to 10,000 rows. Larger files are randomly sampled to that size — sign up to analyze your full dataset.
Computing principal components...
Sent to — scree chart, component summary, loadings, feature contributions, observation map, R code, and AI insights.
Analyze another filePCA standardizes your selected features and rotates them into independent 'principal components', ordered by how much variation each captures. The scree chart shows how many components carry real signal; loadings show which of your original columns define each component; and the observation map plots every row on the two dominant components, where clusters and group separation become visible.
Use it when you have many numeric columns and want to know what actually varies — before clustering, modelling, or building an index.
Not for categorical data, and non-linear structure (curved manifolds) is better served by t-SNE or UMAP.
Built for: Analysts and data scientists making sense of wide, correlated datasets
Typical data source: Any spreadsheet or CSV with several numeric metric columns
Any table with several numeric columns. For example, customer metrics:
Minimum 10 rows · Best with 50-10,000 rows and 3-12 numeric features
Principal component analysis on the numeric columns you choose. See how many independent dimensions your data really has, which features move together, and how observations spread across the dominant components — scree chart, loadings, contributions, and an observation map.
The scree chart — how much variation each component captures, and where the signal stops.
Eigenvalues and cumulative variance, with the standard cut-offs (Kaiser, 80%/90%) computed for you.
Your features ranked by how much they define the dominant structure.
Every observation mapped onto the two main components — clusters and gradients become visible here.
Which original columns define each component, so you can name them in your domain's language.
Plain-English interpretation — what the numbers mean, what's significant, and what to do next.
Do my 10 KPIs really measure 10 different things — or just 2?
Map your metrics as features. The scree chart shows the effective dimensionality, and the loadings reveal which KPIs are redundant restatements of the same underlying factor.
See our FAQ for details on pricing, data privacy, and how the analysis works. Every report includes a Methodology section showing the statistical test, assumptions checked, and diagnostics run.
Run any analysis on your own data — validated R analyses, interactive reports, AI insights, and PDF export.
Try Free — No Credit CardTell us what went wrong, in your own words. We capture the page you're on automatically, so no need to describe where you are.