diff options
Diffstat (limited to 'src/correlations.rs')
| -rw-r--r-- | src/correlations.rs | 18 |
1 files changed, 16 insertions, 2 deletions
diff --git a/src/correlations.rs b/src/correlations.rs index 356bfcc..2b9c0f1 100644 --- a/src/correlations.rs +++ b/src/correlations.rs @@ -20,8 +20,16 @@ pub struct Pearson { degrees_of_freedom: f64, } +/// Spearman's rank correlation, on the same footing as [`Pearson`]. +/// +/// Public for the same reason `Pearson` is: a caller that already holds the +/// two value vectors (a request handler, an enrichment step, a test) should be +/// able to compute the rank correlation without going through +/// [`Compute`] -- which means writing a dataset to a file and reading the +/// result back out of a CSV. `Compute` stays the streaming path for a whole +/// dataset; this is the in-memory one, and the p-value is the same code. #[derive(PartialEq, Debug)] -struct Spearman { +pub struct Spearman { n: usize, degrees_of_freedom: f64, } @@ -127,8 +135,14 @@ impl<'a> Compute<'a> { } } + /// Sort by the correction coefficient, descending. + /// + /// NOTE: this orders by *signed* r, while [`crate::sorter::custom_float_sorter`] + /// -- the one `compute` actually uses -- orders by *magnitude*, with NaNs + /// last. The two disagree for negative correlations, so prefer the latter + /// when "same as the file path" is what a caller wants. Kept as it is + /// because it is public API, not because the difference is intended. pub fn sorter(results: &mut [(f64, f64)]) { - //naive sorter results.sort_by(|a, b| b.1.partial_cmp(&a.1).unwrap()); } |
