Upload 2 files

app.py

@@ -6,6 +6,7 @@ import matplotlib.pyplot as plt
 from sklearn import datasets
 from sklearn.preprocessing import StandardScaler
 from sklearn.decomposition import PCA
+import os, time
 
 FEATURE_LABELS = {
     "age": "Leeftijd",
@@ -63,7 +64,7 @@ def compute_overview_table(df: pd.DataFrame):
         if vals.size == 0:
             continue
         mean = float(vals.mean())
-        pct_above = float((vals > 0).mean() * 100.0)
+        pct_above = float((vals > 0).mean() * 100.0)  # standardized: 0 ~ mean
         pct_below = float((vals < 0).mean() * 100.0)
         rows.append({
             "Meting": FEATURE_LABELS.get(k, k),
@@ -72,68 +73,92 @@ def compute_overview_table(df: pd.DataFrame):
             "% onder gemiddelde": round(pct_below, 1),
         })
     table = pd.DataFrame(rows)
-    note = (
-        "Let op: waarden in deze dataset zijn **gestandaardiseerd**. "
-        "`0` betekent ongeveer het **algemene gemiddelde**. "
-        "Positief = hoger dan gemiddeld, negatief = lager dan gemiddeld."
-    )
+    note = ("Let op: waarden in deze dataset zijn **gestandaardiseerd**. "
+            "`0` betekent ongeveer het **algemene gemiddelde**. "
+            "Positief = hoger dan gemiddeld, negatief = lager dan gemiddeld.")
     return table, note
 
-def pca_biplot(color_label="BMI (Body Mass Index)", arrow_scale=2.0, point_size=32, alpha=0.85, n_components=10, standardize=True):
-    df = load_diabetes_df()
-    overview_df, overview_note = compute_overview_table(df)
-
-    feature_keys = [c for c in df.columns if c != "target"]
-    color_key = LABEL_TO_KEY.get(color_label, "bmi")
+def compute_top_correlations(df: pd.DataFrame, top_n: int = 6):
+    feats = [c for c in df.columns if c != "target"]
+    corr = pd.DataFrame(df[feats]).corr()
+    pairs = []
+    for i, a in enumerate(feats):
+        for j, b in enumerate(feats):
+            if j <= i:
+                continue
+            pairs.append({
+                "Combinatie": f"{FEATURE_LABELS.get(a,a)} ↔ {FEATURE_LABELS.get(b,b)}",
+                "Correlatie": corr.loc[a, b]
+            })
+    out = pd.DataFrame(pairs)
+    out["Sterkte (|r|)"] = out["Correlatie"].abs()
+    out = out.sort_values("Sterkte (|r|)", ascending=False).head(top_n).reset_index(drop=True)
+    out["Correlatie"] = out["Correlatie"].round(3)
+    out["Sterkte (|r|)"] = out["Sterkte (|r|)"].round(3)
+    return out[["Combinatie", "Correlatie", "Sterkte (|r|)"]]
 
-    X = df[feature_keys].values
+def compute_pca(df: pd.DataFrame, n_components: int, standardize: bool):
+    feats = [c for c in df.columns if c != "target"]
+    X = df[feats].values
     if standardize:
         scaler = StandardScaler(with_mean=True, with_std=True)
         Xs = scaler.fit_transform(X)
     else:
         Xs = X
-
     pca = PCA(n_components=min(int(n_components), Xs.shape[1]))
     Z = pca.fit_transform(Xs)
     loadings = pca.components_.T
     expl = pca.explained_variance_ratio_
+    return feats, Z, loadings, expl
 
-    cvals = df[color_key].values
-
-    fig1 = plt.figure(figsize=(7.8, 5.6))
-    ax = fig1.add_subplot(111)
-    sc = ax.scatter(Z[:, 0], Z[:, 1], c=cvals, s=point_size, alpha=alpha)
+def build_biplot(Z, loadings, feats, color_vals, arrow_scale, point_size, alpha, color_label_nl):
+    fig = plt.figure(figsize=(7.8, 5.6))
+    ax = fig.add_subplot(111)
+    sc = ax.scatter(Z[:, 0], Z[:, 1], c=color_vals, s=point_size, alpha=alpha)
     cbar = plt.colorbar(sc, ax=ax, pad=0.02)
-    cbar.set_label(f"Kleur: {FEATURE_LABELS.get(color_key, color_key)}")
-    ax.set_xlabel("PC1")
-    ax.set_ylabel("PC2")
+    cbar.set_label(f"Kleur: {color_label_nl}")
+    ax.set_xlabel("PC1"); ax.set_ylabel("PC2")
     ax.set_title("PCA-biplot — punten (patiënten) + pijlen (belangrijkste metingen)")
-
-    for i, key in enumerate(feature_keys):
+    for i, key in enumerate(feats):
         x_arrow = loadings[i, 0] * arrow_scale
         y_arrow = loadings[i, 1] * arrow_scale
         ax.arrow(0, 0, x_arrow, y_arrow, head_width=0.05, head_length=0.08, fc="k", ec="k", length_includes_head=True)
         ax.text(x_arrow * 1.08, y_arrow * 1.08, FEATURE_LABELS.get(key, key), fontsize=9, ha="center", va="center")
-
     ax.axhline(0, color="grey", linewidth=0.6, linestyle=":")
     ax.axvline(0, color="grey", linewidth=0.6, linestyle=":")
     ax.grid(True, linestyle=":", linewidth=0.6)
     plt.tight_layout()
+    return fig
 
-    fig2 = plt.figure(figsize=(7.8, 3.8))
-    ax2 = fig2.add_subplot(111)
+def build_variance_plot(expl):
+    fig = plt.figure(figsize=(7.8, 3.8))
+    ax = fig.add_subplot(111)
     xs = np.arange(1, len(expl) + 1)
-    ax2.bar(xs, expl, width=0.8, align="center")
-    ax2.plot(xs, np.cumsum(expl), marker="o")
-    ax2.set_xticks(xs)
-    ax2.set_xlabel("Principal Component")
-    ax2.set_ylabel("Explained variance ratio")
-    ax2.set_title("Uitlegvariantie per component (balken) + cumulatief (lijn)")
-    ax2.grid(True, linestyle=":", linewidth=0.6)
+    ax.bar(xs, expl, width=0.8, align="center")
+    ax.plot(xs, np.cumsum(expl), marker="o")
+    ax.set_xticks(xs)
+    ax.set_xlabel("Principal Component")
+    ax.set_ylabel("Explained variance ratio")
+    ax.set_title("Uitlegvariantie per component (balken) + cumulatief (lijn)")
+    ax.grid(True, linestyle=":", linewidth=0.6)
     plt.tight_layout()
+    return fig
+
+def pca_biplot(color_label="BMI (Body Mass Index)", arrow_scale=2.0, point_size=32, alpha=0.85, n_components=10, standardize=True):
+    df = load_diabetes_df()
+    overview_df, overview_note = compute_overview_table(df)
+    corr_tbl = compute_top_correlations(df)
+
+    feats, Z, loadings, expl = compute_pca(df, n_components, standardize)
+    color_key = LABEL_TO_KEY.get(color_label, "bmi")
+    color_label_nl = FEATURE_LABELS.get(color_key, color_key)
+    color_vals = df[color_key].values
+
+    fig1 = build_biplot(Z, loadings, feats, color_vals, arrow_scale, point_size, alpha, color_label_nl)
+    fig2 = build_variance_plot(expl)
 
     load_df = pd.DataFrame({
-        "feature_key": feature_keys,
+        "feature_key": feats,
         "PC1_loading": loadings[:, 0],
         "PC2_loading": loadings[:, 1],
         "PC1_abs": np.abs(loadings[:, 0]),
@@ -141,15 +166,12 @@ def pca_biplot(color_label="BMI (Body Mass Index)", arrow_scale=2.0, point_size=
     })
     load_df["Feature (PC1)"] = load_df["feature_key"].map(lambda k: FEATURE_LABELS.get(k, k))
     load_df["Feature (PC2)"] = load_df["feature_key"].map(lambda k: FEATURE_LABELS.get(k, k))
-
     top_pc1 = load_df.sort_values("PC1_abs", ascending=False)[["Feature (PC1)", "PC1_loading"]].head(6).reset_index(drop=True)
     top_pc2 = load_df.sort_values("PC2_abs", ascending=False)[["Feature (PC2)", "PC2_loading"]].head(6).reset_index(drop=True)
     max_len = max(len(top_pc1), len(top_pc2))
-    top_pc1 = top_pc1.reindex(range(max_len))
-    top_pc2 = top_pc2.reindex(range(max_len))
+    top_pc1 = top_pc1.reindex(range(max_len)); top_pc2 = top_pc2.reindex(range(max_len))
     table = pd.concat([top_pc1, top_pc2], axis=1)
 
-    color_label_nl = FEATURE_LABELS.get(color_key, color_key)
     summary_md = f"""
 ### Wat zie je hier?
 - **Punten (patiënten)** geprojecteerd in 2D met **PCA**. Dicht bij elkaar = **lijken op elkaar** over meerdere metingen.
@@ -157,45 +179,139 @@ def pca_biplot(color_label="BMI (Body Mass Index)", arrow_scale=2.0, point_size=
 - **Pijlen** = bijdrage van **metingen** aan de richting van **PC1/PC2**. **Langere pijlen** wegen zwaarder.
 - **Balkgrafiek** = per component hoeveel variatie hij uitlegt; **lijn** = cumulatief.
 """
+    return fig1, fig2, table, summary_md, overview_df, overview_note, corr_tbl
 
-    return fig1, fig2, table, summary_md, overview_df, overview_note
+def animate_pca(color_label="BMI (Body Mass Index)", point_size=32, alpha=0.85, n_components=10, standardize=True, frames=40, pause=0.0):
+    df = load_diabetes_df()
+    feats, Z, loadings, expl = compute_pca(df, n_components, standardize)
+
+    color_key = LABEL_TO_KEY.get(color_label, "bmi")
+    color_vals = df[color_key].values
 
-with gr.Blocks(title="PCA Biplot — Diabetes (NL labels)") as demo:
+    for i in range(frames):
+        t = i / max(1, frames-1)  # 0..1
+        w1 = min(1.0, t * 2.0)
+        w2 = max(0.0, (t - 0.5) * 2.0)
+        coords = np.column_stack([Z[:, 0] * w1, Z[:, 1] * w2])
+
+        fig = plt.figure(figsize=(7.8, 5.6))
+        ax = fig.add_subplot(111)
+        ax.scatter(coords[:, 0], coords[:, 1], c=color_vals, s=point_size, alpha=alpha)
+        ax.set_xlabel("PC1 (opbouw)"); ax.set_ylabel("PC2 (opbouw)")
+        title = "PCA-projectie (animatie) — " + ("PC1 →" if w2 == 0 else "PC1 + PC2")
+        ax.set_title(f"{title} — frame {i+1}/{frames}")
+        ax.axhline(0, color="grey", linewidth=0.6, linestyle=":")
+        ax.axvline(0, color="grey", linewidth=0.6, linestyle=":")
+        ax.grid(True, linestyle=":", linewidth=0.6)
+        plt.tight_layout()
+        yield fig
+        if pause > 0:
+            time.sleep(pause)
+
+def export_biplot_png(color_label="BMI (Body Mass Index)", arrow_scale=2.0, point_size=32, alpha=0.85, n_components=10, standardize=True):
+    df = load_diabetes_df()
+    feats, Z, loadings, expl = compute_pca(df, n_components, standardize)
+    color_key = LABEL_TO_KEY.get(color_label, "bmi")
+    color_label_nl = FEATURE_LABELS.get(color_key, color_key)
+    color_vals = df[color_key].values
+    fig = build_biplot(Z, loadings, feats, color_vals, arrow_scale, point_size, alpha, color_label_nl)
+    path = f"/mnt/data/biplot_{int(time.time())}.png"
+    fig.savefig(path, dpi=150, bbox_inches="tight")
+    plt.close(fig)
+    return path
+
+def export_variance_png(n_components=10, standardize=True):
+    df = load_diabetes_df()
+    feats, Z, loadings, expl = compute_pca(df, n_components, standardize)
+    fig = build_variance_plot(expl)
+    path = f"/mnt/data/variance_{int(time.time())}.png"
+    fig.savefig(path, dpi=150, bbox_inches="tight")
+    plt.close(fig)
+    return path
+
+with gr.Blocks(title="PCA Biplot — Diabetes (Dashboard)") as demo:
     gr.HTML("""
     <style>
-      .callout {padding:12px 14px; border-left:4px solid #2563eb; background:#f1f5f9; border-radius:6px; margin: 8px 0 18px;}
+      .card {background:#fff; border:1px solid #e5e7eb; border-radius:12px; padding:14px; box-shadow: 0 1px 4px rgba(0,0,0,0.06);}
+      .callout {padding:12px 14px; border-left:4px solid #2563eb; background:#f1f5f9; border-radius:8px; margin: 8px 0 18px;}
       .smallnote {font-size: 0.92em; opacity: 0.85;}
     </style>
     """)
 
-    gr.Markdown("# PCA Biplot — Diabetes (NL labels)")
+    gr.Markdown("# PCA Biplot — Diabetes (Dashboard)")
     gr.Markdown(MEDICAL_MD)
 
     with gr.Row():
         with gr.Column(scale=1):
-            color_choices = [FEATURE_LABELS[k] for k in ["bmi","bp","s1","s2","s3","s4","s5","s6","age","sex","target"]]
-            color_feat = gr.Dropdown(choices=color_choices, value=FEATURE_LABELS["bmi"], label="Kleur op meting")
-            arrow_scale = gr.Slider(0.5, 5.0, value=2.0, step=0.1, label="Pijl-schaal (loadings)")
-            point_size = gr.Slider(8, 80, value=32, step=2, label="Puntgrootte")
-            alpha = gr.Slider(0.2, 1.0, value=0.85, step=0.05, label="Transparantie (punten)")
-            n_components = gr.Slider(2, 10, value=10, step=1, label="Aantal PCA-componenten (voor variatieplot)")
-            standardize = gr.Checkbox(value=True, label="Standaardiseer metingen (aanbevolen)")
-            run_btn = gr.Button("Update visualisaties")
-            gr.HTML('<div class="callout smallnote">💡 <b>Tip:</b> kies links een meting (bijv. BMI of cholesterol) en klik daarna op <b>Update visualisaties</b>.</div>')
+            with gr.Group():
+                gr.Markdown("### Instellingen")
+                color_choices = [FEATURE_LABELS[k] for k in ["bmi","bp","s1","s2","s3","s4","s5","s6","age","sex","target"]]
+                color_feat = gr.Dropdown(choices=color_choices, value=FEATURE_LABELS["bmi"], label="Kleur op meting")
+                arrow_scale = gr.Slider(0.5, 5.0, value=2.0, step=0.1, label="Pijl-schaal (loadings)")
+                point_size = gr.Slider(8, 80, value=32, step=2, label="Puntgrootte")
+                alpha = gr.Slider(0.2, 1.0, value=0.85, step=0.05, label="Transparantie (punten)")
+                n_components = gr.Slider(2, 10, value=10, step=1, label="Aantal PCA-componenten")
+                standardize = gr.Checkbox(value=True, label="Standaardiseer metingen (aanbevolen)")
+                run_btn = gr.Button("Update visualisaties")
+                gr.HTML('<div class="callout smallnote">💡 <b>Tip:</b> Kies links een meting (bijv. BMI of cholesterol) en klik daarna op <b>Update visualisaties</b>.</div>')
+            with gr.Group():
+                gr.Markdown("### Animatie")
+                animate_btn = gr.Button("▶ Animate PCA (PC1 → PC2)")
+                anim_plot = gr.Plot(label="Animatie van projectie")
+
+            with gr.Group():
+                gr.Markdown("### Downloads")
+                dl_biplot = gr.DownloadButton("Download biplot (PNG)")
+                dl_var = gr.DownloadButton("Download variatieplot (PNG)")
+                file_biplot = gr.File(label="Biplot PNG", visible=False)
+                file_var = gr.File(label="Variatieplot PNG", visible=False)
+
         with gr.Column(scale=2):
-            plot_biplot = gr.Plot(label="PCA-biplot — punten + pijlen")
-            plot_expl = gr.Plot(label="Uitlegvariantie per component")
-            table = gr.Dataframe(headers=["Feature (PC1)", "Loading PC1", "Feature (PC2)", "Loading PC2"], row_count=6)
-            summary = gr.Markdown()
-            gr.Markdown("### Overzicht (gemiddelden & verdeling)")
-            overview_tbl = gr.Dataframe(interactive=False)
-            overview_note_md = gr.Markdown()
+            with gr.Row():
+                with gr.Column():
+                    gr.Markdown("### Biplot")
+                    plot_biplot = gr.Plot()
+                with gr.Column():
+                    gr.Markdown("### Uitlegvariantie")
+                    plot_expl = gr.Plot()
+            with gr.Row():
+                with gr.Column():
+                    gr.Markdown("### Top-features (PC1 / PC2)")
+                    table = gr.Dataframe(headers=["Feature (PC1)", "Loading PC1", "Feature (PC2)", "Loading PC2"], row_count=6)
+                with gr.Column():
+                    gr.Markdown("### Overzicht (gemiddelden & verdeling)")
+                    overview_tbl = gr.Dataframe(interactive=False)
+                    overview_note_md = gr.Markdown()
+            with gr.Row():
+                with gr.Column():
+                    gr.Markdown("### Samenvatting")
+                    summary = gr.Markdown()
+                with gr.Column():
+                    gr.Markdown("### Top correlaties (features)")
+                    topcorr_tbl = gr.Dataframe(interactive=False)
 
     inputs = [color_feat, arrow_scale, point_size, alpha, n_components, standardize]
     run_btn.click(fn=pca_biplot, inputs=inputs,
-                  outputs=[plot_biplot, plot_expl, table, summary, overview_tbl, overview_note_md])
+                  outputs=[plot_biplot, plot_expl, table, summary, overview_tbl, overview_note_md, topcorr_tbl])
     demo.load(fn=pca_biplot, inputs=inputs,
-              outputs=[plot_biplot, plot_expl, table, summary, overview_tbl, overview_note_md])
+              outputs=[plot_biplot, plot_expl, table, summary, overview_tbl, overview_note_md, topcorr_tbl])
+
+    animate_btn.click(fn=animate_pca,
+                      inputs=[color_feat, point_size, alpha, n_components, standardize],
+                      outputs=anim_plot)
+
+    dl_biplot.click(fn=export_biplot_png,
+                    inputs=[color_feat, arrow_scale, point_size, alpha, n_components, standardize],
+                    outputs=[dl_biplot])
+    dl_biplot.click(fn=export_biplot_png,
+                    inputs=[color_feat, arrow_scale, point_size, alpha, n_components, standardize],
+                    outputs=[file_biplot])
+    dl_var.click(fn=export_variance_png,
+                 inputs=[n_components, standardize],
+                 outputs=[dl_var])
+    dl_var.click(fn=export_variance_png,
+                 inputs=[n_components, standardize],
+                 outputs=[file_var])
 
 if __name__ == "__main__":
     demo.queue().launch(server_name="0.0.0.0", server_port=7860, ssr_mode=False, show_api=False)