Deborah.Rebekah.Heatmaps

render_bhattacharyya_heatmap(
    bc_arr::Array{Float64,2},
    N_lb_arr::Vector{Int},
    N_tr_arr::Vector{Int},
    key::Symbol,
    pred_tag::Symbol,
    overall_name::String,
    figs_dir::String;
    key_tex::String = "",
    save_file::Bool = false,
    annotate::Bool = true,
    cmap_name::String = "viridis",
    levels::Vector{Float64} = [0.6, 0.8, 0.9],
    draw_contours::Bool = true
) -> Nothing

Render a single heatmap for the Bhattacharyya coefficient ($\mathrm{BC}$ in $[0,1]$).

• Colormap spans 0.0 (worst) to 1.0 (best).
• Optional numeric annotations per cell.
• Optional contour lines at given levels for quick visual thresholds.

Arguments

• bc_arr : 2D array of Bhattacharyya coefficients in $[0,1]$.
• N_lb_arr : $y$-axis tick labels (LBP $\%$).
• N_tr_arr : $x$-axis tick labels (TRP $\%$).
• key : Observable symbol (e.g., :TrM1).
• pred_tag : Prediction method symbol (e.g., :Y_P2).
• overall_name: Identifier used in filename.
• figs_dir : Output directory.

Keywords

• key_tex="" : $\LaTeX$ label (e.g., $\chi$).
• save_file=false: If true, saves a cropped PDF in figs_dir.
• annotate=true : If true, prints $\mathrm{BC}$ values in each cell.
• cmap_name="viridis": Matplotlib colormap name.
• levels=[0.6,0.8,0.9]: Contour levels for $\mathrm{BC}$.
• draw_contours=true : Whether to draw contour overlays.

Side Effects

• Displays the heatmap; optionally writes <figs_dir>/heatmap_bc_<key>_<pred_tag>_<overall_name>.pdf.

render_jsd_heatmap(
    jsd_arr::Array{Float64,2},
    N_lb_arr::Vector{Int},
    N_tr_arr::Vector{Int},
    key::Symbol,
    pred_tag::Symbol,
    overall_name::String,
    figs_dir::String;
    key_tex::String = "",
    save_file::Bool = false,
    annotate::Bool = true,
    cmap_name::String = "viridis",
    levels::Vector{Float64} = [0.2, 0.4, 0.6, 0.8],
    draw_contours::Bool = true
) -> Nothing

Render a single heatmap for the Jensen-Shannon divergence ($\mathrm{JSD}$ in $[0,1]$, base-2).

• Lower is better (0 = identical, 1 = worst).
• Optional per-cell annotations and contour overlays.

Arguments

• jsd_arr : 2D array of $\mathrm{JSD}$ values in $[0,1]$.
• N_lb_arr : $y$-axis tick labels (LBP $\%$).
• N_tr_arr : $x$-axis tick labels (TRP $\%$).
• key : Observable symbol (e.g., :TrM1).
• pred_tag : Prediction method symbol (e.g., :Y_P1).
• overall_name: Identifier used in filename.
• figs_dir : Output directory.

Keywords

• key_tex="" : $\LaTeX$ label (e.g., $\chi$).
• save_file=false: If true, saves a cropped PDF in figs_dir.
• annotate=true : If true, prints $\mathrm{JSD}$ values in each cell.
• cmap_name="viridis": Matplotlib colormap name.
• levels=[0.2,0.4,0.6,0.8]: Contour levels for $\mathrm{JSD}$.
• draw_contours=true : Whether to draw contour overlays.

Side Effects

• Displays the heatmap; optionally writes <figs_dir>/heatmap_jsd_<key>_<pred_tag>_<overall_name>.pdf.

render_overlap_and_error_heatmaps(
    chk_arr::Array{Int, 2},
    err_arr::Array{Float64, 2},
    N_lb_arr::Vector{Int},
    N_tr_arr::Vector{Int},
    key::Symbol,
    pred_tag::Symbol,
    overall_name::String,
    figs_dir::String;
    key_tex::String = "",
    save_file::Bool = false
) -> Nothing

Render side-by-side heatmaps showing overlap (CHK) and error ratio (ERR) matrices for a given observable and prediction method.

This function generates a two-panel static figure using PyPlot.jl:

• Left panel (CHK): overlap matrix with categorical values (0 = black, 1 = gray, 2 = white).
• Right panel (ERR): error ratio matrix, colormapped from 1.0 to 7.0. If any values fall outside this range, the out-of-range values are shown as overlaid text.

Axis ticks are labeled using N_tr_arr ($x$-axis) and N_lb_arr ($y$-axis), with $\LaTeX$-rendered labels using key_tex. Title includes the observable and method tag.

Arguments

• chk_arr::Array{Int,2}: Overlap matrix (each entry 0, 1, or 2).
• err_arr::Array{Float64,2}: Error ratio matrix.
• N_lb_arr::Vector{Int}: Labeled set percentage values for $y$-axis ticks.
• N_tr_arr::Vector{Int}: Training set percentage values for $x$-axis ticks.
• key::Symbol: Observable identifier (e.g., :TrM1, :TrM4).
• pred_tag::Symbol: Prediction method (e.g., :Y_P1, :Y_P2).
• overall_name::String: Identifier used in the output filename.
• figs_dir::String: Directory path to save the resulting figure.

Keyword Arguments

• key_tex::String="": $\LaTeX$-formatted string for $y$-axis label (e.g., $\mathcal{R}_{\mathrm{LB}}$).
• save_file::Bool=false: Whether to save the figure as a PDF file under figs_dir.

Side Effects

• Displays the generated heatmap figure using PyPlot.jl.
• If save_file=true, saves a PDF under the filename: figs_dir/heatmap_kurt_<overall_name>.pdf.