Create code.py

code.py

@@ -0,0 +1,37 @@
+import gradio as gr
+from transformers import pipeline
+
+# Load the sentiment analysis pipeline using your fine-tuned model
+model_name = "Abduuu/ArabReview-Sentiment"
+sentiment_pipeline = pipeline("text-classification", model=model_name, tokenizer=model_name)
+
+# Define label mapping for better readability
+label_mapping = {"LABEL_0": "Negative 😞", "LABEL_1": "Positive 😊"}
+
+# Define a function for sentiment prediction
+def predict_sentiment(review):
+    result = sentiment_pipeline(review)[0]
+    sentiment_label = label_mapping[result["label"]]
+    confidence = f"{result['score']:.2f}"
+    return f"Sentiment: {sentiment_label} | Confidence: {confidence}"
+
+# Define Gradio interface
+iface = gr.Interface(
+    fn=predict_sentiment,  # Function for sentiment prediction
+    inputs=gr.Textbox(label="Enter Your Restaurant Review", placeholder="اكتب مراجعتك هنا..."),
+    outputs=gr.Textbox(label="Predicted Sentiment", interactive=False),
+    title="🍽️ Arabic Restaurant Review Sentiment Analysis 🚀",
+    description="Enter an Arabic restaurant review, and the model will predict whether it's **Positive 😊** or **Negative 😞**.",
+    examples=[
+        ["الطعام لذيذ جدًا والخدمة رائعة!"],  # Positive
+        ["التجربة كانت مريعة، الطعام كان سيئًا جدًا!"],  # Negative
+        ["السعر مرتفع جدًا مقابل الجودة المتوسطة."],  # Neutral
+        ["لن أعود إلى هذا المكان أبدًا، أسوأ تجربة لي!"],  # Negative
+        ["أفضل مطعم زرته في حياتي!"],  # Positive
+    ],
+    allow_flagging="never"  # Disables user flagging for simplicity
+)
+
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()