Update app.py

app.py

@@ -3,71 +3,64 @@ from transformers import pipeline
 import requests
 import json
 
-# Model name on Hugging Face
+# Model name on Hugging Face Hub
 model_name = "Woolv7007/egyptian-text-classification"
 
-# Load label names from labels.json
+# Load labels.json from Hugging Face
 labels_url = f"https://huggingface.co/{model_name}/resolve/main/labels.json"
 try:
     response = requests.get(labels_url)
     response.raise_for_status()
     labels = response.json()
-
-    # Convert to list if it's a dictionary
     if isinstance(labels, dict):
         labels = list(labels.values())
-
     print("Labels loaded:", labels)
-
 except requests.exceptions.RequestException as e:
     print("Failed to load labels.json:", e)
     labels = None
 
-# Load the text classification pipeline
+# Load the model pipeline
 pipe = pipeline("text-classification", model=model_name)
-print("Model pipeline loaded.")
+print("Model loaded.")
 
-# Define the prediction function
+# Prediction function
 def predict(text):
-    print("Input text:", text)
-
+    print("Input:", text)
     try:
-        # Run prediction
         result = pipe(text)[0]
-        print("Model output:", result)
+        print("Raw result:", result)
 
-        # Extract label index from format like "LABEL_3"
         label_id = int(result['label'].replace("LABEL_", ""))
-        print("Label ID:", label_id)
-
-        # Get the label name using the index
         label_text = labels[label_id] if labels and label_id < len(labels) else result['label']
-        print("Final label:", label_text)
+        print("Mapped label:", label_text)
+
+        # Define which labels are considered "True"
+        true_labels = ["ads", "neutral"]
+        prediction_bool = label_text.lower() in true_labels
 
-        # Get the confidence score
         confidence = round(result['score'], 3)
-        print("Confidence:", confidence)
 
-        # Build JSON result
         json_output = {
-            "prediction": label_text,
+            "prediction": prediction_bool,
+            "original_label": label_text,
             "confidence": confidence
         }
 
-        return label_text, json.dumps(json_output, indent=4, ensure_ascii=False)
+        return str(prediction_bool), json.dumps(json_output, indent=4, ensure_ascii=False)
 
     except Exception as e:
-        print("Error:", e)
-        return "Error", json.dumps({"error": str(e)}, indent=4, ensure_ascii=False)
+        error_msg = str(e)
+        print("Prediction error:", error_msg)
+        return "Error", json.dumps({"error": error_msg}, indent=4, ensure_ascii=False)
 
-# Create the Gradio interface
+# Gradio interface
 gr.Interface(
     fn=predict,
-    inputs=gr.Textbox(lines=3, placeholder="Enter a sentence in Egyptian Arabic..."),
+    inputs=gr.Textbox(lines=3, placeholder="Enter Egyptian Arabic text..."),
     outputs=[
-        gr.Label(label="Predicted Category"),
-        gr.Textbox(label="JSON Output")
+        gr.Textbox(label="Prediction (True/False)"),
+        gr.Textbox(label="Full JSON Output")
     ],
-    title="Egyptian Arabic Text Classifier",
-    description="This model classifies Egyptian Arabic text into categories such as Neutral, Offensive, Racist, Religious Discrimination, Ads, etc."
+    title="Egyptian Text Classification",
+    description="This model classifies Egyptian Arabic text. Only 'ads' and 'neutral' are considered True; all other labels are considered False."
 ).launch()