Upload app.py with huggingface_hub

app.py

@@ -22,6 +22,9 @@ import pandas as pd
 from sklearn.manifold import TSNE
 from sklearn.decomposition import PCA
 import plotly.express as px
+import plotly.graph_objects as go
+import itertools
+from plotly.colors import qualitative
 
 # Load data
 def load_data():
@@ -125,20 +128,29 @@ def plot_tsne(tech_filter, snr_filter, mod_filter, mob_filter, representation, c
     x_pad = max(1e-3, (x_max - x_min) * 0.05)
     y_pad = max(1e-3, (y_max - y_min) * 0.05)
 
-    # Plot
-    fig = px.scatter(
-        filtered_df, 
-        x='x', 
-        y='y', 
-        color=color_by,
-        hover_data=['tech', 'snr', 'mod', 'mob'],
+    # Plot (explicit Scattergl to ensure points render)
+    palette = itertools.cycle(qualitative.Set2 + qualitative.Set3 + qualitative.D3)
+    fig = go.Figure()
+    for cls in sorted(filtered_df[color_by].unique()):
+        mask = filtered_df[color_by] == cls
+        color = next(palette)
+        fig.add_trace(go.Scattergl(
+            x=filtered_df.loc[mask, 'x'],
+            y=filtered_df.loc[mask, 'y'],
+            mode='markers',
+            name=str(cls),
+            marker=dict(size=6, opacity=0.8, color=color, line=dict(width=0)),
+            hovertext=filtered_df.loc[mask, ['tech', 'snr', 'mod', 'mob']].astype(str).agg('<br>'.join, axis=1),
+            hoverinfo='text'
+        ))
+    fig.update_layout(
         title=f"t-SNE of {representation} ({len(filtered_df)} samples)",
-        template="plotly_white"
+        template="plotly_white",
+        legend_title_text=color_by.capitalize(),
+        margin=dict(l=40, r=20, t=60, b=40),
     )
-    fig.update_layout(legend_title_text=color_by.capitalize())
-    fig.update_traces(mode='markers', marker=dict(size=6, opacity=0.8, line=dict(width=0)))
-    fig.update_xaxes(range=[x_min - x_pad, x_max + x_pad])
-    fig.update_yaxes(range=[y_min - y_pad, y_max + y_pad])
+    fig.update_xaxes(range=[x_min - x_pad, x_max + x_pad], zeroline=False)
+    fig.update_yaxes(range=[y_min - y_pad, y_max + y_pad], zeroline=False)
     
     coord_info = f"x[{x_min:.3f},{x_max:.3f}] y[{y_min:.3f},{y_max:.3f}]"
     return fig, f"{status_msg} | filtered samples: {len(filtered_df)} | {coord_info}"