Update app.py

app.py

@@ -1,32 +1,32 @@
-import gradio as gr
-from transformers import pipeline, BertForSequenceClassification, BertTokenizer
-import torch
-
-# Load the model and tokenizer
-model_path = 'D:\Study\university\Fourth Year\second semster\NLP\final exam\saved_model'
-model = BertForSequenceClassification.from_pretrained(model_path)
-tokenizer = BertTokenizer.from_pretrained(model_path)
-
-# Create a pipeline for inference
-nlp_pipeline = pipeline('text-classification', model=model, tokenizer=tokenizer)
-
-# Gradio app function
-def classify_text(input_text):
-    if input_text.strip() == "":
-        return "Please enter some text."
-    result = nlp_pipeline(input_text)
-    label = result[0]['label']
-    score = result[0]['score']
-
-    # Map labels to 1 for positive and 0 for negative
-    label_map = {'LABEL_0': " Negative ", 'LABEL_1': "  Postive "}
-    mapped_label = label_map[label]
-
-    return f"Prediction: {mapped_label}, Confidence Score: {score:.4f}"
-
-# Gradio interface
-iface = gr.Interface(fn=classify_text, inputs="text", outputs="text", title="Text Classification App",
-                     description="Classify text as Positive (1) or Negative (0)")
-
-# Launch the Gradio app
-iface.launch()
+import gradio as gr
+from transformers import pipeline
+
+# Load the model from Hugging Face Hub
+model_repo = "Ahmed-El-Sharkawy/my-sentiment-model"  # Replace with your actual repo name
+nlp_pipeline = pipeline("text-classification", model=model_repo)
+
+# Gradio app function
+def classify_text(input_text):
+    if input_text.strip() == "":
+        return "Please enter some text."
+    result = nlp_pipeline(input_text)
+    label = result[0]['label']
+    score = result[0]['score']
+
+    # Map Hugging Face labels to readable format
+    label_map = {'LABEL_0': "Negative", 'LABEL_1': "Positive"}
+    mapped_label = label_map.get(label, label)
+
+    return f"Prediction: {mapped_label}, Confidence Score: {score:.4f}"
+
+# Gradio interface
+iface = gr.Interface(
+    fn=classify_text,
+    inputs="text",
+    outputs="text",
+    title="Text Classification App",
+    description="Classify text as Positive (1) or Negative (0)"
+)
+
+# Launch the app
+iface.launch()