Update app.py

app.py

@@ -1,26 +1,71 @@
 import gradio as gr
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
+from transformers import PreTrainedTokenizerFast, PreTrainedModel
 import torch
+import re
 
-model_name = "alperugurcan/nlp-disaster"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
+# Model ve tokenizer'ı yükleyin
+model_name = "alperugurcan/nlp-disaster"  # Model dosyalarının bulunduğu dizini buraya yazın
+tokenizer = PreTrainedTokenizerFast.from_pretrained(model_name)  # Tokenizer'ı yükleyin
+model = PreTrainedModel.from_pretrained(model_name)  # Modeli yükleyin (modelin hangi sınıf olduğuna bağlı olarak değişebilir)
+
+def clean_text(text):
+    # URL'leri ve özel karakterleri kaldır
+    text = re.sub(r'http\S+|[^\w\s]', '', text)
+    return text.strip()
 
 def predict(text):
-    # Tokenize the input text
-    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
-    # Get model predictions
-    with torch.no_grad():
-        outputs = model(**inputs)
-    predictions = torch.argmax(outputs.logits, dim=-1)
-    return "Positive" if predictions.item() == 1 else "Negative"
+    if not text or len(text.strip()) == 0:
+        return "Please enter some text"
+    
+    try:
+        # Metni ön işleme tabi tut
+        text = clean_text(text)
+        
+        # Giriş metnini tokenize et
+        inputs = tokenizer(
+            text, 
+            return_tensors="pt", 
+            truncation=True, 
+            padding=True,
+            max_length=128
+        )
+        
+        # Model tahminlerini al
+        with torch.no_grad():
+            outputs = model(**inputs)
+            probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
+            prediction = torch.argmax(outputs.logits, dim=-1)
+            confidence = probabilities[0][prediction.item()].item()
+            
+        # Sonucu ve güven oranını döndür
+        result = "Disaster" if prediction.item() == 1 else "Not Disaster"
+        return f"{result} (Confidence: {confidence:.2%})"
+    
+    except Exception as e:
+        return f"Error in prediction: {str(e)}"
 
-# Create a Gradio interface
-iface = gr.Interface(fn=predict, 
-                     inputs="text", 
-                     outputs="text", 
-                     title="Sentiment Analysis",
-                     description="Enter text to analyze sentiment (Positive/Negative).")
+# Gradio arayüzü oluştur
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.Textbox(
+        label="Tweet Text",
+        placeholder="Enter a tweet to analyze...",
+        lines=3
+    ),
+    outputs=gr.Textbox(label="Prediction"),
+    title="🚨 Disaster Tweet Classifier",
+    description="Enter a tweet to determine if it's about a real disaster or not.",
+    examples=[
+        ["Just happened: Massive earthquake hits California"],
+        ["I'm dying to see the new Spider-Man movie!"],
+        ["Forest fire spreading rapidly near residential areas"],
+        ["This game is a complete disaster lol"]
+    ],
+    theme=gr.themes.Base(
+        primary_hue="red",
+        secondary_hue="yellow",
+    )
+)
 
-# Launch the app
-iface.launch()
+# Uygulamayı başlat
+iface.launch(share=True)