Update app.py

app.py

@@ -1,89 +1,100 @@
 import streamlit as st
-from transformers import pipeline
+import re
+from collections import Counter
 
 # Custom CSS for styling
 st.markdown(
     """
     <style>
     .stApp {
-        background: linear-gradient(120deg, #2C5364, #203A43, #0F2027);
-        color: #F0F0F0;
+        background-color: #f4f4f9;
+        color: #333333;
     }
     .stTitle {
         text-align: center;
-        color: #FFD700;
+        color: #4CAF50;
     }
-    .css-1d391kg p, .css-1v0mbdj p {
-        color: #F0F0F0;
-    }
-    .stButton > button:hover {
-        background-color: #FFD700;
-        color: #0F2027;
-        transform: scale(1.05);
+    .section-title {
+        font-size: 24px;
+        color: #FF5722;
+        text-decoration: underline;
     }
     </style>
     """,
     unsafe_allow_html=True,
 )
 
-st.title("🧠 NLP Tool with Hugging Face", anchor=False)
-
-st.sidebar.subheader("🔍 Explore NLP Features")
+st.title("🔎 Explore Natural Language Processing")
 
-# Dropdown to select NLP task
-nlp_task = st.sidebar.selectbox(
-    "Select an NLP Task:",
-    ["Text Classification", "Sentiment Analysis", "Question Answering", "Summarization", "Text Generation"]
+# Sidebar navigation
+menu = st.sidebar.radio(
+    "Explore Topics",
+    ["Introduction to NLP", "Tokenization", "Word Frequency Analysis", "Stop Words"]
 )
 
-# Input text area
-user_input = st.text_area("Enter your text here:", "", height=150)
-
-# Functionality for each task
-if user_input:
-    if nlp_task == "Text Classification":
-        st.subheader("📋 Text Classification")
-        classifier = pipeline("text-classification")
-        result = classifier(user_input)
-        st.write("**Classification Results:**")
-        for res in result:
-            st.write(f"- **Label**: {res['label']}, **Score**: {res['score']:.2f}")
-
-    elif nlp_task == "Sentiment Analysis":
-        st.subheader("😊 Sentiment Analysis")
-        sentiment_analyzer = pipeline("sentiment-analysis")
-        result = sentiment_analyzer(user_input)
-        st.write("**Sentiment Analysis Results:**")
-        for res in result:
-            st.write(f"- **Label**: {res['label']}, **Score**: {res['score']:.2f}")
-
-    elif nlp_task == "Question Answering":
-        st.subheader("❓ Question Answering")
-        question = st.text_input("Ask a question about the provided text:")
-        if question:
-            qa_pipeline = pipeline("question-answering")
-            result = qa_pipeline(question=question, context=user_input)
-            st.write(f"**Answer:** {result['answer']}")
+# Introduction to NLP
+if menu == "Introduction to NLP":
+    st.header("🌟 What is NLP?")
+    st.write(
+        """
+        Natural Language Processing (NLP) is a field of artificial intelligence that focuses on the interaction
+        between computers and human language. The goal is to enable machines to understand, interpret, and generate
+        human language in a way that is meaningful.
+        
+        NLP has a wide range of applications, including:
+        - **Text Classification:** Categorizing text into predefined categories (e.g., spam detection).
+        - **Sentiment Analysis:** Determining the sentiment (positive, negative, neutral) of a piece of text.
+        - **Machine Translation:** Translating text from one language to another (e.g., Google Translate).
+        - **Named Entity Recognition (NER):** Identifying entities like names, dates, or locations in text.
+        - **Question Answering:** Answering questions based on input text or documents.
+        """
+    )
 
-    elif nlp_task == "Summarization":
-        st.subheader("✂️ Summarization")
-        summarizer = pipeline("summarization")
-        summary = summarizer(user_input, max_length=50, min_length=25, do_sample=False)
-        st.write("**Summary:**")
-        st.write(summary[0]['summary_text'])
+# Tokenization
+elif menu == "Tokenization":
+    st.header("🔠 Tokenization")
+    st.write(
+        """
+        Tokenization is the process of breaking a text into smaller units, called tokens. These tokens can be words,
+        phrases, or characters.
+        """
+    )
+    text_input = st.text_area("Enter some text to tokenize:", "Natural Language Processing is fascinating!")
+    if text_input:
+        tokens = text_input.split()
+        st.write("**Tokens:**", tokens)
 
-    elif nlp_task == "Text Generation":
-        st.subheader("📝 Text Generation")
-        generator = pipeline("text-generation")
-        generated_text = generator(user_input, max_length=50, num_return_sequences=1)
-        st.write("**Generated Text:**")
-        st.write(generated_text[0]['generated_text'])
+# Word Frequency Analysis
+elif menu == "Word Frequency Analysis":
+    st.header("📊 Word Frequency Analysis")
+    st.write(
+        """
+        Word frequency analysis involves counting the occurrences of each word in a text. This is useful for 
+        understanding the most common words in a document or dataset.
+        """
+    )
+    text_input = st.text_area("Enter some text to analyze:", "NLP is fun. NLP can help with many applications.")
+    if text_input:
+        words = re.findall(r'\w+', text_input.lower())
+        word_counts = Counter(words)
+        st.write("**Word Frequency:**")
+        st.write(word_counts)
 
-# Space for connecting this app to another space
-st.sidebar.markdown("---")
-st.sidebar.subheader("🔗 Connect to Other Spaces")
-other_space_url = st.sidebar.text_input("Enter the URL of another Streamlit app or Hugging Face space:")
-if other_space_url:
-    st.sidebar.markdown(f"[Go to Connected Space]({other_space_url})")
+# Stop Words
+elif menu == "Stop Words":
+    st.header("🚫 Stop Words")
+    st.write(
+        """
+        Stop words are common words that usually carry less meaning and are often removed from text analysis
+        (e.g., 'is', 'and', 'the'). This helps in focusing on the meaningful parts of the text.
+        """
+    )
+    text_input = st.text_area("Enter some text to remove stop words:", "The quick brown fox jumps over the lazy dog.")
+    stop_words = {"the", "is", "and", "in", "to", "a", "of", "on", "for"}
+    if text_input:
+        words = text_input.split()
+        filtered_words = [word for word in words if word.lower() not in stop_words]
+        st.write("**Filtered Text:**", " ".join(filtered_words))
 
-st.sidebar.success("Explore NLP tasks or connect to another space!")
+# Footer
+st.sidebar.info("Select a topic to learn about NLP!")