Update app.py

app.py

@@ -50,8 +50,21 @@ def create_heatmap(embeddings, words):
     return fig
 
 def create_word_scatter(embeddings, words):
-    # Reduce dimensions for visualization
-    tsne = TSNE(n_components=2, random_state=42)
+    # Calculate appropriate perplexity value
+    n_samples = len(embeddings)
+    # Perplexity should be between 5 and 50, and less than n_samples
+    perplexity = min(30, n_samples - 1)  # Default is 30, but ensure it's less than n_samples
+    
+    # Reduce dimensions for visualization using t-SNE
+    tsne = TSNE(
+        n_components=2,
+        perplexity=perplexity,
+        random_state=42,
+        init='random',
+        learning_rate='auto'
+    )
+    
+    # Perform t-SNE dimensionality reduction
     embeddings_2d = tsne.fit_transform(embeddings)
     
     # Create scatter plot
@@ -59,11 +72,21 @@ def create_word_scatter(embeddings, words):
         x=embeddings_2d[:, 0],
         y=embeddings_2d[:, 1],
         text=words,
-        title='Word Embeddings in 2D Space'
+        title=f'Word Embeddings in 2D Space (perplexity={perplexity})'
+    )
+    
+    # Update layout for better visualization
+    fig.update_traces(
+        textposition='top center',
+        mode='markers+text'
+    )
+    fig.update_layout(
+        height=400,
+        showlegend=False,
+        xaxis_title="t-SNE dimension 1",
+        yaxis_title="t-SNE dimension 2"
     )
     
-    fig.update_traces(textposition='top center')
-    fig.update_layout(height=400)
     return fig
 
 def main():