Update app.py

app.py

@@ -8,40 +8,67 @@ sentiment_model = AutoModelForSequenceClassification.from_pretrained("dnzblgn/Se
 sarcasm_tokenizer = AutoTokenizer.from_pretrained("microsoft/deberta-v3-base", use_fast=False)
 sentiment_tokenizer = AutoTokenizer.from_pretrained("FacebookAI/roberta-base", use_fast=False)
 
-def process_text_pipeline(user_input):
-    sentences = user_input.split("\n")
-    results = []
+# Function to analyze sentiment
+def analyze_sentiment(sentence):
+    inputs = sentiment_tokenizer(sentence, return_tensors="pt", truncation=True, padding=True, max_length=512)
+    with torch.no_grad():
+        outputs = sentiment_model(**inputs)
+    logits = outputs.logits
+    predicted_class = torch.argmax(logits, dim=-1).item()
+    sentiment_mapping = {1: "Negative", 0: "Positive"}
+    return sentiment_mapping[predicted_class]
+
+# Function to detect sarcasm
+def detect_sarcasm(sentence):
+    inputs = sarcasm_tokenizer(sentence, return_tensors="pt", truncation=True, padding=True, max_length=512)
+    with torch.no_grad():
+        outputs = sarcasm_model(**inputs)
+    logits = outputs.logits
+    predicted_class = torch.argmax(logits, dim=-1).item()
+    return "Sarcasm" if predicted_class == 1 else "Not Sarcasm"
+
+# Combined function for text file pipeline
+def process_text_pipeline(text):
+    sentences = text.split("\n")  # Split text into multiple sentences
+    processed_sentences = []
+    
     for sentence in sentences:
-        # Sentiment analysis
-        sentiment_inputs = sentiment_tokenizer(sentence, return_tensors="pt", truncation=True, padding=True, max_length=512)
-        with torch.no_grad():
-            sentiment_outputs = sentiment_model(**sentiment_inputs)
-            sentiment_logits = sentiment_outputs.logits
-            sentiment_class = torch.argmax(sentiment_logits, dim=-1).item()
-            sentiment = "Positive" if sentiment_class == 0 else "Negative"
-        
-        # Sarcasm detection for positive sentences
+        sentiment = analyze_sentiment(sentence.strip())
         if sentiment == "Positive":
-            sarcasm_inputs = sarcasm_tokenizer(sentence, return_tensors="pt", truncation=True, padding=True, max_length=512)
-            with torch.no_grad():
-                sarcasm_outputs = sarcasm_model(**sarcasm_inputs)
-                sarcasm_logits = sarcasm_outputs.logits
-                sarcasm_class = torch.argmax(sarcasm_logits, dim=-1).item()
-                if sarcasm_class == 1:  # Sarcasm detected
-                    sentiment = "Negative (Sarcasm detected)"
-        
-        results.append(f"{sentence}: {sentiment}")
-    return "\n".join(results)
+            sarcasm_result = detect_sarcasm(sentence.strip())
+            if sarcasm_result == "Sarcasm":
+                processed_sentences.append(f"'{sentence}' -> Sentiment: Negative (due to sarcasm)")
+            else:
+                processed_sentences.append(f"'{sentence}' -> Sentiment: Positive")
+        else:
+            processed_sentences.append(f"'{sentence}' -> Sentiment: Negative")
+    
+    return "\n".join(processed_sentences)
+
+# Simple user interface for sarcasm detection
+def sarcasm_detection_interface(input_text):
+    sentences = input_text.split("\n")
+    predictions = []
+    
+    for sentence in sentences:
+        sentiment = analyze_sentiment(sentence.strip())
+        if sentiment == "Negative":
+            predictions.append(f"'{sentence}' -> Not Sarcastic (Direct Negative Sentiment)")
+        else:
+            sarcasm_result = detect_sarcasm(sentence.strip())
+            predictions.append(f"'{sentence}' -> {sarcasm_result}")
+    
+    return "\n".join(predictions)
 
 # Gradio UI
 interface = gr.Interface(
-    fn=process_text_pipeline,
+    fn=sarcasm_detection_interface,
     inputs=gr.Textbox(lines=10, placeholder="Enter one or more sentences, each on a new line."),
     outputs="text",
     title="Sarcasm Detection for Customer Reviews",
-    description="This web app analyzes the sentiment of customer reviews and detects sarcasm for positive reviews.",
+    description="This web app analyzes customer reviews for sentiment and detects sarcasm for positive reviews.",
 )
 
-# Run interface
+# Run the interface
 if __name__ == "__main__":
-    interface.launch()
+    interface.launch()