Upload 2 files

app.py

@@ -6,7 +6,8 @@ import matplotlib.pyplot as plt
 from sklearn import datasets
 from sklearn.preprocessing import StandardScaler
 from sklearn.decomposition import PCA
-import os, time
+import plotly.graph_objects as go
+import time
 
 FEATURE_LABELS = {
     "age": "Leeftijd",
@@ -109,7 +110,7 @@ def compute_pca(df: pd.DataFrame, n_components: int, standardize: bool):
     Z = pca.fit_transform(Xs)
     loadings = pca.components_.T
     expl = pca.explained_variance_ratio_
-    return feats, Z, loadings, expl
+    return feats, Xs, Z, loadings, expl
 
 def build_biplot(Z, loadings, feats, color_vals, arrow_scale, point_size, alpha, color_label_nl):
     fig = plt.figure(figsize=(7.8, 5.6))
@@ -144,12 +145,27 @@ def build_variance_plot(expl):
     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):
+def build_pca3d(Z3, color_vals, color_label_nl, point_size, alpha):
+    # Plotly 3D scatter for real rotation/drag
+    fig = go.Figure(data=[go.Scatter3d(
+        x=Z3[:, 0], y=Z3[:, 1], z=Z3[:, 2],
+        mode="markers",
+        marker=dict(size=max(2, int(point_size/2)), color=color_vals, opacity=alpha)
+    )])
+    fig.update_layout(
+        title="PCA 3D — PC1 · PC2 · PC3",
+        scene=dict(xaxis_title="PC1", yaxis_title="PC2", zaxis_title="PC3"),
+        margin=dict(l=0, r=0, t=40, b=0),
+        height=520
+    )
+    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, show_3d=False):
     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)
+    feats, Xs, 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
@@ -179,21 +195,32 @@ 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
+
+    # 3D
+    if show_3d:
+        # Zorg dat we minstens 3 componenten hebben
+        if Z.shape[1] < 3:
+            pca3 = PCA(n_components=3)
+            Z3 = pca3.fit_transform(Xs)
+        else:
+            Z3 = Z[:, :3]
+        fig3 = build_pca3d(Z3, color_vals, color_label_nl, point_size, alpha)
+        pca3d_out = gr.update(value=fig3, visible=True)
+    else:
+        pca3d_out = gr.update(value=None, visible=False)
+
+    return fig1, fig2, table, summary_md, overview_df, overview_note, corr_tbl, pca3d_out
 
 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)
-
+    feats, Xs, Z, loadings, expl = compute_pca(df, n_components, standardize)
     color_key = LABEL_TO_KEY.get(color_label, "bmi")
     color_vals = df[color_key].values
-
     for i in range(frames):
-        t = i / max(1, frames-1)  # 0..1
+        t = i / max(1, frames-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)
@@ -210,7 +237,7 @@ def animate_pca(color_label="BMI (Body Mass Index)", point_size=32, alpha=0.85,
 
 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)
+    feats, Xs, 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
@@ -222,7 +249,7 @@ def export_biplot_png(color_label="BMI (Body Mass Index)", arrow_scale=2.0, poin
 
 def export_variance_png(n_components=10, standardize=True):
     df = load_diabetes_df()
-    feats, Z, loadings, expl = compute_pca(df, n_components, standardize)
+    feats, Xs, 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")
@@ -252,6 +279,7 @@ with gr.Blocks(title="PCA Biplot — Diabetes (Dashboard)") as demo:
                 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)")
+                show_3d = gr.Checkbox(value=True, label="Toon 3D PCA (PC1–PC3)")
                 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():
@@ -269,7 +297,7 @@ with gr.Blocks(title="PCA Biplot — Diabetes (Dashboard)") as demo:
         with gr.Column(scale=2):
             with gr.Row():
                 with gr.Column():
-                    gr.Markdown("### Biplot")
+                    gr.Markdown("### Biplot (2D)")
                     plot_biplot = gr.Plot()
                 with gr.Column():
                     gr.Markdown("### Uitlegvariantie")
@@ -289,12 +317,16 @@ with gr.Blocks(title="PCA Biplot — Diabetes (Dashboard)") as demo:
                 with gr.Column():
                     gr.Markdown("### Top correlaties (features)")
                     topcorr_tbl = gr.Dataframe(interactive=False)
+            with gr.Row():
+                with gr.Column():
+                    gr.Markdown("### 3D PCA (PC1–PC3 — sleep om te draaien)")
+                    plot3d = gr.Plot(visible=True)
 
-    inputs = [color_feat, arrow_scale, point_size, alpha, n_components, standardize]
+    inputs = [color_feat, arrow_scale, point_size, alpha, n_components, standardize, show_3d]
     run_btn.click(fn=pca_biplot, inputs=inputs,
-                  outputs=[plot_biplot, plot_expl, table, summary, overview_tbl, overview_note_md, topcorr_tbl])
+                  outputs=[plot_biplot, plot_expl, table, summary, overview_tbl, overview_note_md, topcorr_tbl, plot3d])
     demo.load(fn=pca_biplot, inputs=inputs,
-              outputs=[plot_biplot, plot_expl, table, summary, overview_tbl, overview_note_md, topcorr_tbl])
+              outputs=[plot_biplot, plot_expl, table, summary, overview_tbl, overview_note_md, topcorr_tbl, plot3d])
 
     animate_btn.click(fn=animate_pca,
                       inputs=[color_feat, point_size, alpha, n_components, standardize],

requirements.txt

@@ -3,3 +3,4 @@ matplotlib>=3.7.0
 numpy>=1.23.0
 scikit-learn>=1.2.0
 pandas>=1.5.0
+plotly>=5.15.0