Update app.py

app.py

@@ -166,7 +166,20 @@ def predict(text):
 
     combined_prediction = f"Level1: {predicted_label_level1} - Level2: {predicted_label_level2}"
     return combined_prediction
-   
+    
+def classify_csv(file_obj):
+    # Read the CSV file
+    df = pd.read_csv(file_obj)
+    
+    # Assuming you have a column 'text' in your CSV that you want to classify
+    predictions = []
+    for _, row in df.iterrows():
+        prediction = predict(row['text'])
+        predictions.append(prediction)
+    
+    # Convert the predictions to a DataFrame
+    results_df = pd.DataFrame(predictions, columns=["Prediction"])
+    return results_df
 
 # Define the markdown text with bullet points
 markdown_text = """
@@ -174,6 +187,12 @@ markdown_text = """
 - Input one budget line per time with min 2 words.
 - Accuracy of the model is ~88%.
 """
+markdown_text_file_upload = """
+- Trained with ~1500 rows of data on bert-base-uncased, English.
+- Upload CSV ONLY and name your column with budget line item as **text**.
+- Added RAG (Retrieval-augmented generation) to feed context into classifier using preceing lines of budget.
+- Accuracy of the model is ~88%.
+"""
 html_table = """
   <h2 style="text-align: center;">COFOG Budget AutoClassification</h2>
    <p style="text-align: justify; margin-left: 30px; margin-right: 30px;">
@@ -237,8 +256,8 @@ html_table = """
   </table>
 </div>
 """
-
-iface = gr.Interface(
+# First interface for single line input
+iface1 = gr.Interface(
     fn=predict, 
     inputs=gr.components.Textbox(lines=1, placeholder="Enter Budget line here...", label="Budget Input"), 
     outputs=gr.components.Label(label="Classification Output"), 
@@ -251,6 +270,23 @@ iface = gr.Interface(
     
 )
 
+
+# Second interface (for CSV file upload)
+iface2 = gr.Interface(
+    fn=classify_csv,
+    inputs=gr.components.File(label="Upload CSV File"),
+    outputs=gr.components.DataFrame(label="Classification Results"),
+    description=markdown_text_file_upload,
+    article=html_table,
+    title="Batch Classification"
+)
+
+# Combine the interfaces in a tabbed interface
+tabbed_interface = gr.TabbedInterface(
+    [iface1, iface2],
+    ["Single Prediction", "Batch Prediction"]
+)
+
 # Run the interface
 if __name__ == "__main__":
-    iface.launch()
+    tabbed_interface.launch()