Update app.py

app.py

@@ -2,46 +2,96 @@ import streamlit as st
 import transformers
 from transformers import pipeline
 import re
+import base64
 
-# Title and Description
+# Set page config
 st.set_page_config(page_title="Telugu Sentiment Analysis", layout="centered")
-st.title("📊 Telugu Sentiment Analysis")
-st.markdown("Analyze the sentiment (Positive, Negative, Neutral) of a given **Telugu** sentence using a fine-tuned BERT model.")
 
-# Load the model pipeline
+# Set background image
+def set_background(image_file):
+    with open(image_file, "rb") as file:
+        encoded = base64.b64encode(file.read()).decode()
+    st.markdown(
+        f"""
+        <style>
+        .stApp {{
+            background-image: url("data:image/jpg;base64,{encoded}");
+            background-size: cover;
+            background-position: center;
+            background-repeat: no-repeat;
+        }}
+        textarea {{
+            background-color: #f8f8f8 !important;
+            font-size: 18px !important;
+        }}
+        .custom-button {{
+            display: inline-block;
+            padding: 10px 25px;
+            font-size: 18px;
+            font-weight: bold;
+            color: white;
+            background-color: #ff4b4b;
+            border-radius: 10px;
+            text-align: center;
+        }}
+        </style>
+        """,
+        unsafe_allow_html=True
+    )
+
+set_background("New3.jpg")
+
+# Title and Description
+st.markdown("<h1 style='text-align: center;'>📊 Telugu Sentiment Analysis</h1>", unsafe_allow_html=True)
+st.markdown(
+    "<div style='text-align:center;'>"
+    "Analyze the sentiment (Positive, Negative, Neutral) of a given <strong>Telugu</strong> sentence using a fine-tuned BERT model."
+    "</div><br>", unsafe_allow_html=True
+)
+
+# Load pipeline
 @st.cache_resource
 def load_pipeline():
     return pipeline("text-classification", model="Adityaganesh/Telugu_Sentiment_Analysis")
 
 pipe = load_pipeline()
 
-# Optional: Text Preprocessing (basic cleaning)
+# Preprocess text
 def preprocess_text(text):
     text = text.strip()
     text = re.sub(r"\s+", " ", text)
     return text
 
-# User Input
-user_input = st.text_area("Enter Telugu Text:", height=200, placeholder="ఇక్కడ మీ తెలుగు వాక్యాన్ని నమోదు చేయండి...")
+# Telugu validation
+def is_telugu(text):
+    return bool(re.fullmatch(r"[\u0C00-\u0C7F\s]+", text))
+
+# Input
+user_input = st.text_area("✍️ Enter Telugu Text:", height=200, placeholder="ఇక్కడ మీ తెలుగు వాక్యాన్ని నమోదు చేయండి...")
 
-if st.button("🔍 Analyze Sentiment"):
+# Button
+if st.button("🔍 Predict"):
     if user_input.strip() == "":
         st.warning("దయచేసి కొన్ని తెలుగు వాక్యాలు నమోదు చేయండి.")
+    elif not is_telugu(user_input):
+        st.error("దయచేసి కేవలం తెలుగు వాక్యాలు మాత్రమే నమోదు చేయండి.")
     else:
         clean_text = preprocess_text(user_input)
-        with st.spinner("Analyzing sentiment..."):
+        with st.spinner("విశ్లేషణ జరుగుతోంది..."):
             result = pipe(clean_text)[0]
             idx = int(result['label'].split('_')[1])
             
             if idx == 0:
                 sentiment = "😐 Neutral"
-                color = "gray"
+                color = "#808080"
             elif idx == 1:
                 sentiment = "😊 Positive"
-                color = "green"
+                color = "#28a745"
             else:
                 sentiment = "😠 Negative"
-                color = "red"
+                color = "#dc3545"
 
-            st.markdown(f"### Prediction: <span style='color:{color}'>{sentiment}</span>", unsafe_allow_html=True)
-            st.markdown(f"**Confidence:** `{result['score']:.2f}`") 
+            st.markdown(
+                f"<h3 style='color:{color}; text-align:center;'>📢 Prediction: {sentiment}</h3>",
+                unsafe_allow_html=True
+            )