pandrs 0.3.0

A high-performance DataFrame library for Rust, providing pandas-like API with advanced features including SIMD optimization, parallel processing, and distributed computing capabilities
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43

//! Auto-generated module
//!
//! 🤖 Generated with [SplitRS](https://github.com/cool-japan/splitrs)

/// Helper function to compute Pearson correlation coefficient
pub(super) fn pearson_correlation(x: &[f64], y: &[f64]) -> f64 {
    if x.len() != y.len() || x.is_empty() {
        return f64::NAN;
    }
    let n = x.len() as f64;
    let mean_x: f64 = x.iter().sum::<f64>() / n;
    let mean_y: f64 = y.iter().sum::<f64>() / n;
    let mut numerator = 0.0;
    let mut sum_sq_x = 0.0;
    let mut sum_sq_y = 0.0;
    for i in 0..x.len() {
        let dx = x[i] - mean_x;
        let dy = y[i] - mean_y;
        numerator += dx * dy;
        sum_sq_x += dx * dx;
        sum_sq_y += dy * dy;
    }
    let denominator = (sum_sq_x * sum_sq_y).sqrt();
    if denominator == 0.0 {
        f64::NAN
    } else {
        numerator / denominator
    }
}
/// Helper function to compute covariance
pub(super) fn covariance(x: &[f64], y: &[f64]) -> f64 {
    if x.len() != y.len() || x.is_empty() {
        return f64::NAN;
    }
    let n = x.len() as f64;
    let mean_x: f64 = x.iter().sum::<f64>() / n;
    let mean_y: f64 = y.iter().sum::<f64>() / n;
    let mut sum = 0.0;
    for i in 0..x.len() {
        sum += (x[i] - mean_x) * (y[i] - mean_y);
    }
    sum / n
}