Update app.py

app.py

@@ -3,57 +3,62 @@ from transformers import pipeline
 import pandas as pd
 import io
 
-# Define available classification models
-models = {
-    "EN: deberta-v3-large-zeroshot": "MoritzLaurer/deberta-v3-large-zeroshot-v2.0",
-    "MULTI: mDeBERTa-v3-xnli": "MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7",
-    "MULTI: xlm-roberta-large-xnli": "joeddav/xlm-roberta-large-xnli"
-}
+# Load once
+classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
 
 response_table = []
 
-def classify(questions_text, labels_text, model_choice):
-    labels = [l.strip() for l in labels_text.split(",") if l.strip()]
-    questions = [q.strip() for q in questions_text.split("\n") if q.strip()]
+def classify_items(questions_text, labels_text):
+    questions = [q.strip() for q in questions_text.strip().split("\n") if q.strip()]
+    labels = [l.strip() for l in labels_text.strip().split(",") if l.strip()]
+    
     if not labels or not questions:
-        return "Please enter both questions and labels.", None
+        return "Please provide both items and at least two response options.", ""
 
-    classifier = pipeline("zero-shot-classification", model=models[model_choice])
     global response_table
     response_table = []
     output_lines = []
 
     for i, question in enumerate(questions, 1):
         result = classifier(question, labels, multi_label=False)
+        probs = dict(zip(result['labels'], result['scores']))
+
         output_lines.append(f"{i}. {question}")
-        row = {"Item #": i, "Item": question}
-        for label, score in zip(result["labels"], result["scores"]):
-            row[label] = round(score, 3)
-            output_lines.append(f"→ {label}: {round(score, 3)}")
+        for label in labels:
+            output_lines.append(f"→ {label}: {round(probs.get(label, 0.0), 3)}")
         output_lines.append("")
+
+        row = {"Item #": i, "Item": question}
+        row.update({label: round(probs.get(label, 0.0), 3) for label in labels})
         response_table.append(row)
 
     return "\n".join(output_lines), None
 
 def download_csv():
+    global response_table
+    if not response_table:
+        return None
     df = pd.DataFrame(response_table)
-    buffer = io.StringIO()
-    df.to_csv(buffer, index=False)
-    return buffer.getvalue()
+    csv_buffer = io.StringIO()
+    df.to_csv(csv_buffer, index=False)
+    return csv_buffer.getvalue()
 
+# Gradio UI
 with gr.Blocks() as demo:
-    gr.Markdown("## 🧠 Zero-Shot Classification Interface")
-    gr.Markdown("Enter questionnaire items and response options. The selected model will return probabilities for each label.")
-
-    model_dropdown = gr.Dropdown(choices=list(models.keys()), label="Choose Classification Model")
-    labels_input = gr.Textbox(label="Response Options (comma-separated)", placeholder="Strongly disagree, Disagree, Neutral, Agree, Strongly agree")
-    questions_input = gr.Textbox(label="Questionnaire Items (one per line)", lines=10)
-    output_box = gr.Textbox(label="Model Output", lines=20)
-    run_btn = gr.Button("Run Classification")
-    download_btn = gr.Button("📥 Download CSV")
-    csv_file = gr.File(label="CSV", visible=False)
-
-    run_btn.click(fn=classify, inputs=[questions_input, labels_input, model_dropdown], outputs=[output_box, csv_file])
-    download_btn.click(fn=download_csv, inputs=[], outputs=csv_file)
+    gr.Markdown("# 🧠 Zero-Shot Classification for Questionnaire Responses")
+    gr.Markdown("Paste questionnaire items (one per line), and provide your own response labels (comma-separated).")
+
+    with gr.Row():
+        with gr.Column():
+            questions_input = gr.Textbox(label="Questionnaire Items", lines=10, placeholder="e.g.\nI feel in control of my life.\nI enjoy being around others.")
+            labels_input = gr.Textbox(label="Response Options (comma-separated)", placeholder="Strongly disagree, Disagree, Neutral, Agree, Strongly agree")
+            submit_btn = gr.Button("Classify Items")
+            csv_btn = gr.Button("📥 Download CSV")
+        with gr.Column():
+            output_box = gr.Textbox(label="Classification Output", lines=20)
+            file_output = gr.File(label="Download CSV", visible=False)
+
+    submit_btn.click(fn=classify_items, inputs=[questions_input, labels_input], outputs=[output_box, file_output])
+    csv_btn.click(fn=download_csv, inputs=[], outputs=file_output)
 
 demo.launch()