Update app.py

app.py

@@ -34,8 +34,8 @@ st.title('Biryani, Pizza, or Neither Classifier')
 df = pd.read_csv("embeddings_receipes_final.csv")
 
 # Check if the DataFrame is loaded correctly
-if df.shape[1] < 383:  # 384 embeddings + 1 label + 1 recipe_id
-    st.error(f"Expected DataFrame with 385 columns, but got {df.shape[1]}. Please check your CSV file.")
+if df.shape[1] < 385:  # 384 embeddings + 1 label + 1 recipe_id
+    st.error(f"Expected DataFrame with 385 columns, but got less than that. Please check your CSV file.")
 else:
     # Input text
     input_text = st.text_area("Enter text to classify")
@@ -55,7 +55,7 @@ else:
                 # Display the result
                 st.write(f"The predicted label is: **{predicted_label}**")
 
-                # Visualization using t-SNE (example)
+                # Visualization using t-SNE
                 embeddings = df.iloc[:, 1:-1].values  # Exclude 'recipe_id' and 'label'
                 labels = df['label']
 
@@ -68,9 +68,11 @@ else:
                     indices = labels == label
                     plt.scatter(tsne_embeddings[indices, 0], tsne_embeddings[indices, 1], label=label)
 
-                # Plotting the input text embedding separately (if needed)
-                input_tsne_embedding = tsne.fit_transform([embedding])
-                plt.scatter(input_tsne_embedding[0, 0], input_tsne_embedding[0, 1], label='input text', c='red')
+                # Project the input text embedding into the existing t-SNE space
+                tsne_input = TSNE(n_components=2, init='pca', random_state=42)
+                tsne_input_embedding = tsne_input.fit_transform(np.vstack([embeddings, embedding]))[-1]
+
+                plt.scatter(tsne_input_embedding[0], tsne_input_embedding[1], label='input text', c='red', marker='x', s=100)
 
                 plt.legend()
                 plt.title('2D t-SNE Visualization of Embeddings')
@@ -80,5 +82,3 @@ else:
 
         else:
             st.write("Please enter text to classify.")
-
-