randogoth/lyagushka
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Density Z-Score

Browse source
This commit is contained in:
randogoth 2024-03-01 15:46:52 +02:00
parent 158d0c1bfe
commit 9c3220fd14
1 changed files with 25 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

52
src/main.rs
View file

@ -127,38 +127,36 @@ fn calculate_densities_and_gaps(dataset: &[Point], factor: f32, min_cluster_size
/// ///
fn lyagushka(dataset: Vec<Point>, factor: f32, min_cluster_size: usize) -> String { fn lyagushka(dataset: Vec<Point>, factor: f32, min_cluster_size: usize) -> String {
// Analyze the dataset to identify clusters and significant gaps. // Calculate clusters and gaps from the dataset using predefined criteria.
let mut cluster_gap_infos = calculate_densities_and_gaps(&dataset, factor, min_cluster_size); let mut cluster_gap_infos = calculate_densities_and_gaps(&dataset, factor, min_cluster_size);
// Calculate the mean distance between consecutive points in the dataset. // Calculate the mean density of clusters in the dataset for comparison.
let mean_distance: f32 = if dataset.len() > 1 { let mean_density: f32 = cluster_gap_infos.iter()
dataset.windows(2) .filter(|info| info.num_elements > 0)
.map(|w| w[1].value as f32 - w[0].value as f32) .map(|info| info.num_elements as f32 / info.span_length)
.sum::<f32>() / (dataset.len() - 1) as f32 .sum::<f32>() / cluster_gap_infos.iter().filter(|info| info.num_elements > 0).count() as f32;
} else {
0.0
};
// Calculate the standard deviation of distances between consecutive points. // Calculate the standard deviation of cluster densities to evaluate variation.
let std_deviation: f32 = if dataset.len() > 1 { let variance_density: f32 = cluster_gap_infos.iter()
(dataset.windows(2) .filter(|info| info.num_elements > 0)
.map(|w| w[1].value as f32 - w[0].value as f32 - mean_distance) .map(|info| info.num_elements as f32 / info.span_length)
.map(|d| d.powi(2)) .map(|density| (density - mean_density).powi(2))
.sum::<f32>() / (dataset.len() - 1) as f32) .sum::<f32>() / cluster_gap_infos.iter().filter(|info| info.num_elements > 0).count() as f32;
.sqrt() let std_dev_density = variance_density.sqrt();
} else {
0.0
};
// Calculate and assign z-scores for each cluster/gap based on their centroid or span length. // Calculate the average span of all clusters and gaps to assess gap significance.
for info in cluster_gap_infos.iter_mut() { let average_span: f32 = cluster_gap_infos.iter().map(|info| info.span_length).sum::<f32>() / cluster_gap_infos.len() as f32;
info.z_score = Some(if info.num_elements > 0 {
// For clusters, use the centroid for z-score calculation. // Update Z-scores for both clusters and gaps based on their deviation from mean metrics.
(info.centroid - mean_distance) / std_deviation for info in &mut cluster_gap_infos {
if info.num_elements > 0 {
// Calculate and update Z-score for clusters based on density deviation.
let cluster_density = info.num_elements as f32 / info.span_length;
info.z_score = Some((cluster_density - mean_density) / std_dev_density);
} else { } else {
// For gaps, use the span length for z-score calculation. // Calculate and update Z-score for gaps based on span length deviation.
(info.span_length - mean_distance) / std_deviation info.z_score = Some((info.span_length - average_span) / std_dev_density);
}); }
} }
serde_json::to_string_pretty(&cluster_gap_infos).unwrap_or_else(|_| "Failed to serialize data".to_string()) serde_json::to_string_pretty(&cluster_gap_infos).unwrap_or_else(|_| "Failed to serialize data".to_string())