Function create_partial_dependence_plot 

pub fn create_partial_dependence_plot(
    feature_values: &ArrayView1<'_, Float>,
    pd_values: &ArrayView1<'_, Float>,
    ice_curves: Option<&ArrayView2<'_, Float>>,
    feature_name: &str,
    config: &PlotConfig,
    show_ice: bool,
) -> SklResult<PartialDependencePlot>

Create partial dependence plot (PDP) with optional ICE curves

Generates partial dependence plots showing how model predictions change with feature values, with optional Individual Conditional Expectation curves.

Arguments

• feature_values - Feature values for x-axis (sorted grid points)
• pd_values - Partial dependence values corresponding to feature values
• ice_curves - Optional ICE curves (instances × feature_values)
• feature_name - Name of the feature being analyzed
• config - Plot configuration settings
• show_ice - Whether to display individual ICE curves

Returns

Result containing partial dependence plot data or error

Errors

• InvalidInput - If feature values and PD values lengths don’t match
• InvalidInput - If ICE curves columns don’t match feature values length

Examples

use sklears_inspection::visualization::plotting_functions::*;
// ✅ SciRS2 Policy Compliant Import
use scirs2_core::ndarray::array;

let feature_values = array![0.0, 0.2, 0.4, 0.6, 0.8, 1.0];
let pd_values = array![0.1, 0.3, 0.5, 0.4, 0.2, 0.1];
let config = PlotConfig::default();

let plot = create_partial_dependence_plot(
    &feature_values.view(),
    &pd_values.view(),
    None,
    "feature_1",
    &config,
    false,
).unwrap();

assert_eq!(plot.feature_name, "feature_1");
assert_eq!(plot.feature_values.len(), 6);
assert_eq!(plot.pd_values.len(), 6);
assert!(!plot.show_ice);