Update app.py

app.py

@@ -1,5 +1,10 @@
 import streamlit as st
 from transformers import pipeline
+import nltk
+import numpy as np
+
+# Download NLTK data for sentence tokenization
+nltk.download('punkt')
 
 # Load the Hugging Face pipelines
 classifier = pipeline("zero-shot-classification", model="MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli")
@@ -15,6 +20,7 @@ st.markdown(
     This app uses Hugging Face models to detect the topics and intent of customer feedback
     and determine the sentiment (positive or negative) for each relevant category.
     A single feedback may belong to multiple categories, such as Pricing, Feature, and Customer Service.
+    The feedback is split into sentences, and each sentence is categorized and analyzed for sentiment.
     """
 )
 
@@ -22,7 +28,8 @@ st.markdown(
 feedback_input = st.text_area(
     "Enter customer feedback:",
     placeholder="Type your feedback here...",
-    height=200
+    height=200,
+    value="I was shocked to see the price tag on this new gadget—it’s way too expensive for what it offers, especially compared to competitors! Despite the issues I faced with my order, the customer service team's effort to rectify the situation was commendable, though their follow-up could have used some improvement for full satisfaction."
 )
 
 # Confidence threshold for zero-shot classification
@@ -32,7 +39,7 @@ threshold = st.slider(
     max_value=1.0,
     value=0.2,
     step=0.05,
-    help="Categories with scores above this threshold will be displayed."
+    help="Categories with confidence scores above this threshold will be displayed."
 )
 
 # Classify button
@@ -40,29 +47,51 @@ if st.button("Classify Feedback"):
     if not feedback_input.strip():
         st.error("Please provide valid feedback text.")
     else:
-        # Perform zero-shot classification
-        classification_result = classifier(feedback_input, CATEGORIES)
+        # Split the feedback into sentences
+        sentences = nltk.sent_tokenize(feedback_input)
+        if not sentences:
+            st.error("Could not split feedback into sentences.")
+            st.stop()
+
+        # Dictionary to store results for each category
+        category_results = {category: [] for category in CATEGORIES}
+
+        # Process each sentence
+        for sentence in sentences:
+            # Perform zero-shot classification on the sentence
+            classification_result = classifier(sentence, CATEGORIES, multi_label=True)
 
-        # Filter categories with scores above the threshold
-        relevant_categories = {
-            label: round(score, 4)
-            for label, score in zip(classification_result["labels"], classification_result["scores"])
-            if score >= threshold
-        }
+            # Get categories with scores above the threshold
+            for label, score in zip(classification_result["labels"], classification_result["scores"]):
+                if score >= threshold:
+                    # Perform sentiment analysis on the sentence
+                    sentiment_result = sentiment_analyzer(sentence)
+                    sentiment_label = sentiment_result[0]["label"]
+                    sentiment_score = round(sentiment_result[0]["score"], 4)
 
-        # Check if there are any relevant categories
-        if relevant_categories:
-            st.subheader("Categorized Feedback with Sentiment Analysis")
+                    # Store the result for the category
+                    category_results[label].append({
+                        "sentence": sentence,
+                        "confidence": round(score, 4),
+                        "sentiment": sentiment_label,
+                        "sentiment_score": sentiment_score
+                    })
 
-            for category, score in relevant_categories.items():
-                # Extract the part of feedback relevant to the category for sentiment analysis
-                sentiment_result = sentiment_analyzer(feedback_input)
-                sentiment_label = sentiment_result[0]["label"]
-                sentiment_score = round(sentiment_result[0]["score"], 4)
+        # Display the results
+        st.subheader("Categorized Feedback with Sentiment Analysis")
 
-                # Display the category, confidence score, and sentiment result
+        # Flag to check if any categories were found
+        found_categories = False
+
+        for category, results in category_results.items():
+            if results:  # If the category has any sentences
+                found_categories = True
                 st.write(f"### **{category}**")
-                st.write(f"- Confidence: {score}")
-                st.write(f"- Sentiment: {sentiment_label} (Score: {sentiment_score})")
-        else:
+                for result in results:
+                    st.write(f"- **Sentence**: {result['sentence']}")
+                    st.write(f"  - Confidence: {result['confidence']}")
+                    st.write(f"  - Sentiment: {result['sentiment']} (Score: {result['sentiment_score']})")
+                st.write("")  # Add a blank line for readability
+
+        if not found_categories:
             st.warning("No categories matched the selected confidence threshold.")