Update app.py

app.py

@@ -1,270 +1,192 @@
-import streamlit as st
+import streamlit as st 
 import numpy as np
 import re
 import emoji
-from textblob import TextBlob
-import spacy
 import nltk
+from nltk.tokenize import word_tokenize
 from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
 import tensorflow as tf
 import keras
 from keras.utils import pad_sequences
 import pickle
-# Page Config
-st.set_page_config(page_title="Newsense AI", page_icon="📰", layout="wide")
 
-# Custom HTML and CSS for center alignment
-st.markdown(
-    """
-    <style>
-        .center-title {
-            display: flex;
-            justify-content: center;
-            align-items: center;
-            gap: 10px;
-            font-size: 50px;
-            font-weight: bold;
-            color: white;
-            background: linear-gradient(135deg, #FF6B6B, #6B7EFF, #6BFF95, #FFDE59);
-            padding: 20px;
-            border-radius: 20px;
-            box-shadow: 0 10px 35px rgba(255, 107, 107, 0.7),
-                        0 5px 20px rgba(107, 126, 255, 0.7);
-            animation: fadeSlide 1.5s ease-out forwards;
-            width: fit-content;
-            margin: 30px auto;
-        }
+# Streamlit UI
+st.set_page_config(page_title="PressGuard", page_icon="🛡️")
 
-        @keyframes fadeSlide {
-            from {
-                opacity: 0;
-                transform: translateY(-50px);
-            }
-            to {
-                opacity: 1;
-                transform: translateY(0);
-            }
-        }
+# Radium color effect for the title
+st.markdown("""
+    <style>
+    .radium {
+        font-size: 60px;
+        font-weight: bold;
+        color: #f4ff81;  /* Radium-like light greenish-yellow color */
+        text-shadow: 0 0 5px #f4ff81, 0 0 10px #f4ff81, 0 0 20px #f4ff81, 0 0 30px #f4ff81;
+        text-align: center;
+    }
+    .tagline {
+        font-size: 20px;
+        color: #ffffff;
+        text-align: center;
+        margin-bottom: 30px;
+    }
     </style>
-    <div class="center-title">📰 Newsense AI</div>
-    """,
-    unsafe_allow_html=True
-)
-
-
-# # Download necessary resources
-# # nltk.download('stopwords')
-
-# # Load SpaCy model
-# nlp = spacy.load("en_core_web_sm")
-
-# # Stopwords
-# stop_words = set(stopwords.words('english')).union({"pm"})
-
-# # Pre-processing function (without parentheses extraction)
-# def pre_process(x):
-#     # Convert to lowercase
-#     x = x.lower()
-
-#     # Remove HTML tags
-#     x = re.sub(r"<.*?>", "", x)
-
-#     # Remove URLs
-#     x = re.sub(r"http[s]?://\S+", "", x)
-
-#     # Remove mentions (@, #)
-#     x = re.sub(r"[@#]\S+", "", x)
-
-#     # Remove emojis
-#     x = emoji.replace_emoji(x, replace="")
-
-#     # Remove special characters (-, ., :, \, ,)
-#     x = re.sub(r"[-.:,\\]", " ", x)
-
-#     # Remove single and double quotes
-#     x = re.sub(r"['\"](.*?)['\"]", r'\1', x)
-
-#     # Remove content inside parentheses
-#     x = re.sub(r"\(.*?\)", "", x)
-
-#     # Remove extra spaces
-#     x = re.sub(r"\s+", " ", x).strip()
-
-#     # Spell checking
-#     x = str(TextBlob(x).correct())
-
-#     # Lemmatization using SpaCy
-#     x = " ".join([token.lemma_ for token in nlp(x)])
-
-#     return " ".join(x)
-
-# @st.cache_resource
-# def load_model():
-#     model = keras.models.load_model("model_m3_new.keras")
-#     with open("label_encoder_m5.pkl", 'rb') as file:
-#         label_encoder = pickle.load(file)
-#     return model, label_encoder
-
-# model, label_encoder = load_model()
-
-# def predict_category(text):
-#     cleaned_text = pre_process(text)
-
-#     vectorizer = keras.models.load_model("vec_text_m3_new.keras")
-
-#     # Vectorizing the pre-processed text
-#     text_vectorized = pad_sequences(vectorizer.predict(np.array([cleaned_text])).numpy(), padding='pre', maxlen=128)
-
-#     # Model prediction
-#     prediction = model.predict(text_vectorized)
-#     category_idx = np.argmax(prediction, axis=1)[0]
-
-#     return label_encoder.inverse_transform([category_idx])[0], cleaned_text
-
+    <div class='radium'>🛡️ PressGuard</div>
+    <div class='tagline'>Classify and Filter Trustworthy News</div>
+""", unsafe_allow_html=True)
+
+# Download necessary resources
+nltk.download('punkt')
+nltk.download('stopwords')
+nltk.download('wordnet')
+
+# Initialize stopwords and lemmatizer
+stop_words = set(stopwords.words('english')).union({"pm"})
+lemmatizer = WordNetLemmatizer()
+
+def pre_process(x):
+    x = x.lower()
+    x = re.sub("<.*?>", "", x)
+    x = re.sub("http[s]?://.+?\\S+", "", x)
+    x = re.sub("[@#].+?\\S", "", x)
+    x = re.sub(r"\\_+", " ", x)
+    x = re.sub("^[A-Za-z.].*\\s-\\s", "", x)
+    x = emoji.demojize(x)
+    x = re.sub(":.*?:", "", x)
+    x = re.sub("[^a-zA-Z0-9\\s_]", "", x)
+    words = word_tokenize(x)
+    words = [word for word in words if word not in stop_words]
+    x = " ".join([lemmatizer.lemmatize(word) for word in words])
+    return x
+
+@st.cache_resource
+def load_model():
+    model = keras.models.load_model("model_m3_new.keras")
+    vectorizer = keras.models.load_model("vec_text_m3_new.keras")
+    with open("label_encoder_m5.pkl", 'rb') as file:
+        label_encoder = pickle.load(file)
+    return model, vectorizer, label_encoder
+
+model, vectorizer, label_encoder = load_model()
+
+def predict_category(text):
+    processed_text = [pre_process(text)]
+    text_vectorized = pad_sequences(vectorizer(processed_text).numpy().tolist(), padding='pre', maxlen=128)
+    prediction = model.predict(text_vectorized)
+    category_idx = np.argmax(prediction, axis=1)[0]
+    return label_encoder.inverse_transform([category_idx])[0]
+
+# Custom CSS with Radium Color Effect for the Prompt
 st.markdown(
     """
     <style>
         body {
-            background-image: url('https://cdn-uploads.huggingface.co/production/uploads/675fab3a2d0851e23d23cad3/WwOWG8MBGYxHnIeM2Dowo.webp');
+            background-image: url('https://cdn-uploads.huggingface.co/production/uploads/67441c51a784a9d15cb12871/4FFTjgkYjYUq6w-0gR15v.jpeg');
             background-size: cover;
             background-repeat: no-repeat;
             background-attachment: fixed;
         }
-        
-        /* Title Styling */
+        .centered-container { 
+            text-align: center; 
+        }
         .title {
             font-size: 60px; 
             font-weight: bold; 
             color: white;
-            background: linear-gradient(135deg, #FF6B6B, #6B7EFF, #6BFF95, #FFDE59);
+            background: linear-gradient(60deg, #880E4F, #4A235A, #311B92, #000000);
             padding: 20px; 
             border-radius: 20px;
-            box-shadow: 0 10px 35px rgba(255, 107, 107, 0.7),
-                        0 5px 20px rgba(107, 126, 255, 0.7);
+            box-shadow: 0 8px 25px rgba(136, 14, 79, 0.5),
+                        0 4px 15px rgba(74, 35, 90, 0.6),
+                        inset 0 2px 10px rgba(49, 27, 146, 0.4);
             display: inline-block;
-            margin-bottom: 30px;
-            text-align: center;
-            animation: fadeSlide 1.5s ease-out forwards;
+            margin-bottom: 20px;
+            animation: elegantFadeSlide 1.5s ease-out forwards;
         }
-
-        /* Input Box Styling */
-        .input-box { 
-            display: flex;
-            flex-direction: column;
-            align-items: center;
-            gap: 20px;
-            margin: 0 auto;
-            width: 80%;
-        }
-
-        .input-prompt {
-            font-size: 24px;
+        
+        /* Radium Effect for the Prompt */
+        .prompt-box {
+            font-size: 22px;
             font-weight: bold;
-            color: #ffffff;
+            color: white;
             text-align: center;
-            opacity: 0.9;
-            text-shadow: 0 0 8px #6BFF95;
+            background: linear-gradient(135deg, #33ccff, #ff99cc, #33ff99, #ffcc00);
+            background-size: 400% 400%;
+            animation: gradientAnimation 8s ease infinite;
+            padding: 15px;
+            border-radius: 15px;
+            box-shadow: 0 0 15px rgba(255, 255, 255, 0.7),
+                        0 0 25px rgba(136, 14, 79, 0.7),
+                        0 0 35px rgba(49, 27, 146, 0.7);
+            transition: all 0.4s ease-in-out;
         }
 
-        /* Text Area Styling */
-        div.stTextArea textarea {
-            width: 100%;
-            height: 200px;
-            padding: 20px;
-            border-radius: 15px;
-            background: rgba(0, 0, 0, 0.8);
-            color: #FFFFFF;
-            font-size: 18px;
-            outline: none;
-            box-shadow: 0 8px 25px rgba(107, 126, 255, 0.5);
-            transition: all 0.5s ease;
+        .prompt-box:hover {
+            transform: scale(1.05) rotate(1deg);
+            box-shadow: 0 0 25px rgba(255, 255, 255, 0.9),
+                        0 0 35px rgba(136, 14, 79, 0.9),
+                        0 0 45px rgba(49, 27, 146, 0.9);
         }
 
-        div.stTextArea textarea:hover {
-            transform: scale(1.05);
-            box-shadow: 0 12px 40px rgba(107, 126, 255, 0.8);
+        @keyframes gradientAnimation {
+            0% { background-position: 0% 50%; }
+            50% { background-position: 100% 50%; }
+            100% { background-position: 0% 50%; }
         }
 
-        /* Button Styling */
         .analyze-button {
-            width: 220px;
-            height: 65px;
-            border-radius: 35px;
-            background: linear-gradient(45deg, #FF6B6B, #6B7EFF, #6BFF95, #FFDE59);
-            font-size: 22px; 
+            width: 180px;
+            height: 60px;
+            border-radius: 50px;
+            background: linear-gradient(45deg, #880E4F, #4A235A, #311B92, #000000);
+            font-size: 20px; 
             font-weight: bold; 
-            color: #000000; 
+            color: white; 
             border: none;
+            box-shadow: 0 8px 25px rgba(136, 14, 79, 0.5),
+                        0 4px 15px rgba(74, 35, 90, 0.6),
+                        0 2px 10px rgba(49, 27, 146, 0.7),
+                        inset 0 1px 5px rgba(0, 0, 0, 0.4);
             cursor: pointer;
-            transition: all 0.4s ease;
-            box-shadow: 0 8px 25px rgba(255, 107, 107, 0.7);
+            transition: all 0.4s ease-in-out;
         }
-
+        
         .analyze-button:hover {
             transform: scale(1.1);
-            box-shadow: 0 14px 45px rgba(255, 222, 89, 0.8);
+            background: linear-gradient(225deg, #880E4F, #4A235A, #311B92, #000000);
+            box-shadow: 0 12px 35px rgba(49, 27, 146, 0.8),
+                        0 8px 25px rgba(74, 35, 90, 0.7),
+                        0 4px 15px rgba(136, 14, 79, 0.6);
         }
-
-        /* Result Box Styling */
+        
         .result-box {
             text-align: center; 
-            font-size: 30px; 
+            font-size: 28px; 
             font-weight: bold;
-            color: #ffffff; 
-            background: linear-gradient(135deg, #6B7EFF, #6BFF95, #FFDE59, #FF6B6B);
-            padding: 35px; 
-            border-radius: 25px;
-            box-shadow: 0 10px 30px rgba(107, 255, 107, 0.6);
-            margin-top: 40px;
-            animation: fadeIn 1.2s ease-in;
-        }
-
-        /* Animations */
-        @keyframes fadeSlide {
-            from {
-                opacity: 0;
-                transform: translateY(-50px);
-            }
-            to {
-                opacity: 1;
-                transform: translateY(0);
-            }
-        }
-
-        @keyframes fadeIn {
-            from {
-                opacity: 0;
-            }
-            to {
-                opacity: 1;
-            }
+            background: linear-gradient(60deg, #880E4F, #4A235A, #311B92, #000000);
+            color: white; 
+            padding: 30px; 
+            border-radius: 20px;
+            display: inline-block; 
+            margin-top: 30px;
+            box-shadow: 0 6px 20px rgba(74, 35, 90, 0.5),
+                        0 3px 15px rgba(136, 14, 79, 0.4),
+                        inset 0 2px 10px rgba(49, 27, 146, 0.3);
         }
-
     </style>
     """,
     unsafe_allow_html=True
 )
 
+st.markdown("<div class='centered-container'><h1 class='title'>"PressGuard</h1></div>", unsafe_allow_html=True)
+st.markdown("<div class='prompt-box'>Paste the article content below to analyze its category with Newsense AI</div>", unsafe_allow_html=True)
 
-st.markdown(
-    <div class="title">📰 Newsense AI - News Classification</div>,
-    unsafe_allow_html=True
-)
-
-
-# Input and button section
-st.markdown('<div class="input-box">', unsafe_allow_html=True)
-user_input = st.text_area("Enter your news article:", height=200)
+# User input
+input_text = st.text_area("Enter News Article:", height=200)
 
-# Predict button
-if st.button("Classify", key="analyze-button"):
-    if user_input:
-        category, cleaned_text = predict_category(user_input)
-        
-        # Display the prediction and cleaned text
-        st.markdown(f'<div class="result-box">Prediction: {category}</div>', unsafe_allow_html=True)
-        st.markdown(f'<div class="result-box">Cleaned Text: {cleaned_text}</div>', unsafe_allow_html=True)
+if st.button("Analyze", key="analyze-btn", help="Click to classify the news article"):
+    if input_text:
+        category = predict_category(input_text)
+        st.markdown(f"<div class='result-box'>Predicted Category: {category}</div>", unsafe_allow_html=True)
     else:
-        st.warning("Please enter some text to classify!")
-
-st.markdown('</div>', unsafe_allow_html=True)
+        st.warning("Please enter some text to analyze.")