pipeline for figures

src/common/leaderboard.py

@@ -536,7 +536,12 @@ def render_leaderboard(
             bf = bf[bf[target_str_col] == selected_target]
         bf = bf[bf["abbreviation"].isin(selected_methods)]
 
-        iters_df = bf[["abbreviation", "ensemble_size", "mean_iters"]].dropna(subset=["mean_iters"])
+        iters_df = (
+            bf[["abbreviation", "ensemble_size", "mean_iters"]]
+            .dropna(subset=["mean_iters"])
+            .groupby(["abbreviation", "ensemble_size"], as_index=False)
+            .agg(mean_iters=("mean_iters", "mean"))
+        )
         all_ens_combos_iters = bf[["abbreviation", "ensemble_size"]].drop_duplicates()
         if not all_ens_combos_iters.empty:
             iters_ticks = sorted(all_ens_combos_iters["ensemble_size"].unique().tolist())

src/streamlit_app.py

@@ -1,4 +1,5 @@
 import streamlit as st
+from pathlib import Path
 
 st.set_page_config(page_title="Calibration Benchmark", page_icon="🏠", layout="wide")
 
@@ -48,14 +49,31 @@ st.markdown(
     "data-assimilation and calibration algorithms:"
 )
 
-benchmarks = {
-    "L63": "Lorenz-63 — 3-parameter chaotic attractor; low-dimensional, strongly nonlinear.",
-    "L96": "Lorenz-96 — 40-variable atmospheric toy model; moderate dimension.",
-    "L96_NN_FORCING": "Lorenz-96 with a neural-network forcing term; tests emulator-based methods.",
-    "L96_SPATIAL_FORCING": "Lorenz-96 with spatially-varying forcing; higher heterogeneity.",
-}
-for name, desc in benchmarks.items():
-    st.markdown(f"- **{name}** — {desc}")
+_media = Path(__file__).parent / "media"
+
+st.markdown("- **L63** — Lorenz-63 — 3-variable chaotic attractor; learn 2 parameters, strongly nonlinear.")
+
+st.markdown("- **L96** — Lorenz-96 (40-variable); learn 1-parameter constant forcing.")
+st.image(
+    str(_media / "posterior_ribbons_const-force_12_1_k3.png"),
+    caption="Example prior-posterior & truth. L: Difference to true parameter. C: parameter-induced forcing of the L96 system. R: data-sample/output predictived distribution ([1:40] state-mean [41:80] state-std)",
+    width=1200,
+)
+
+st.markdown("- **L96_SPATIAL_FORCING** — Lorenz-96 (40-variable) with spatially-varying forcing; learn 40 parameters; moderately correlated prior.")
+st.image(
+    str(_media / "posterior_ribbons_vec-force_65_1_k3.png"),
+    caption="Example prior-posterior & truth. L: Difference to true parameters. C: parameter-induced forcing of the L96 system. R: data-sample/output predictived distribution ([1:40] state-mean [41:80] state-std)",
+    width=1200,
+)
+
+
+st.markdown("- **L96_NN_FORCING** — Lorenz-96 (100-variable) with a neural-network forcing; Learn 61 parameters (weights and biases of the network). Reasonable prior given.")
+st.image(
+    str(_media / "posterior_ribbons_flux-force_80_1_k3.png"),
+    caption="Example prior-posterior & truth. L: Difference to true parameters (weights). C: parameter-induced forcing of the L96 system. R: data-sample/output predictived distribution ([1:100] state-mean [101:200] state-std)",
+    width=1200,
+)
 
 st.subheader("Method families")
 st.markdown(