Update app.py

app.py

@@ -1,15 +1,41 @@
 import streamlit as st
 from transformers import pipeline
 
-# Load the pre-trained sentiment analysis model from Hugging Face Hub
+# Load the sentiment analysis model
 classifier = pipeline("text-classification", model="Mpavan45/Telugu_Sentimental_Analysis")
 
-# Define the Streamlit interface
-st.title("Sentiment Analysis with BERT")
-st.write("This app uses a fine-tuned BERT model to classify text as positive, negative, or neutral sentiment.")
+# Custom CSS for radium glow effect
+st.markdown("""
+    <style>
+    .radium-title {
+        font-size: 40px;
+        text-align: center;
+        color: #fff;
+        padding: 10px;
+        border-radius: 10px;
+        background: linear-gradient(90deg, #ff416c, #ff4b2b);
+        box-shadow: 0 0 20px #ff416c, 0 0 30px #ff4b2b;
+    }
+    .radium-label {
+        font-size: 24px;
+        font-weight: bold;
+        color: white;
+        padding: 10px;
+        border-radius: 8px;
+        background: linear-gradient(90deg, #36d1dc, #5b86e5);
+        display: inline-block;
+        margin-top: 10px;
+    }
+    </style>
+""", unsafe_allow_html=True)
+
+# Display title
+st.markdown('<div class="radium-title">Sentiment Analysis with BERT</div>', unsafe_allow_html=True)
+st.write("This app uses a fine-tuned BERT model to classify Telugu text as Positive, Negative, or Neutral.")
 
 # Example test cases
 st.subheader("Try one of the following examples:")
+
 examples = [
     "ఈ song చాలా catchy గా ఉంది",
     "నీ attitude చాల బాగుంది",
@@ -19,41 +45,33 @@ examples = [
     "నేను ఈ వార్తలకు చాలా బాధపడ్డాను",
 ]
 
-for example in examples:
-    if st.button(f"Test: {example[:30]}..."):
-        result = classifier(example)
-        raw_label = result[0]['label']
-        confidence = result[0]['score']
-        
-        label_map = {
-            "LABEL_0": "Negative",
-            "LABEL_1": "Neutral",
-            "LABEL_2": "Positive"
-        }
-        sentiment = label_map.get(raw_label, raw_label)
-        
-        st.write(f"Sentiment: {sentiment}")
-        st.write(f"Confidence: {confidence:.4f}")
-        st.text_area("Analysis of your text", example, height=150)
-
-# Take input text from the user
-text_input = st.text_area("Enter text to analyze sentiment:")
-
-# When the user clicks the button, classify the sentiment
+# Show examples in 3 rows × 2 columns
+example_input = ""
+for i in range(0, len(examples), 2):
+    cols = st.columns(2)
+    for j in range(2):
+        if i + j < len(examples):
+            example = examples[i + j]
+            if cols[j].button(example[:30] + "..."):
+                example_input = example
+
+# Take input text
+text_input = st.text_area("Enter text to analyze sentiment:", value=example_input, height=150)
+
+# Sentiment label and emoji
+label_map = {
+    "LABEL_0": ("Negative", "😞"),
+    "LABEL_1": ("Neutral", "😐"),
+    "LABEL_2": ("Positive", "😊")
+}
+
+# On click, analyze sentiment
 if st.button("Analyze Sentiment"):
-    if text_input:
+    if text_input.strip():
         result = classifier(text_input)
         raw_label = result[0]['label']
-        confidence = result[0]['score']
-        
-        label_map = {
-            "LABEL_0": "Negative",
-            "LABEL_1": "Neutral",
-            "LABEL_2": "Positive"
-        }
-        sentiment = label_map.get(raw_label, raw_label)
-
-        st.write(f"Sentiment: {sentiment}")
-        st.write(f"Confidence: {confidence:.4f}")
+        sentiment, emoji = label_map.get(raw_label, (raw_label, ""))
+
+        st.markdown(f'<div class="radium-label">Sentiment: {sentiment} {emoji}</div>', unsafe_allow_html=True)
     else:
-        st.write("Please enter some text to analyze!")
+        st.warning("Please enter some text to analyze!")