Update app.py

app.py

@@ -1,7 +1,7 @@
 import streamlit as st
 from gensim.models import Word2Vec
 
-# Apply custom styles
+# Apply custom styles using Streamlit's markdown
 st.markdown("""
     <style>
     .main-title { color: #FF5733; font-size: 40px; font-weight: bold; text-align: center; }
@@ -17,32 +17,29 @@ st.markdown('<p class="main-title">Introduction to NLP</p>', unsafe_allow_html=T
 # Section: What is NLP?
 st.markdown('<p class="section-title">What is NLP?</p>', unsafe_allow_html=True)
 st.markdown("""
-<p class="text">
 Natural Language Processing (NLP) is a subfield of artificial intelligence that enables computers to process, understand, and generate human language.
-</p>
-
-<p class="sub-title">Applications of NLP:</p>
-✅ Chatbots & Virtual Assistants (e.g., Siri, Alexa)  
-✅ Sentiment Analysis (e.g., Product reviews, Social Media monitoring)  
-✅ Machine Translation (e.g., Google Translate)  
-✅ Text Summarization (e.g., News article summaries)  
-✅ Speech Recognition (e.g., Voice commands)  
-""", unsafe_allow_html=True)
+""")
+st.markdown("""
+**Applications of NLP:**
+- ✅ Chatbots & Virtual Assistants (e.g., Siri, Alexa)  
+- ✅ Sentiment Analysis (e.g., Product reviews, Social Media monitoring)  
+- ✅ Machine Translation (e.g., Google Translate)  
+- ✅ Text Summarization (e.g., News article summaries)  
+- ✅ Speech Recognition (e.g., Voice commands)  
+""")
 
 # Section: NLP Terminologies
 st.markdown('<p class="section-title">NLP Terminologies</p>', unsafe_allow_html=True)
 st.markdown("""
-<p class="text">
-🔹 **Corpus**: A collection of text documents used for NLP tasks.  
-🔹 **Tokenization**: Splitting text into individual words or phrases.  
-🔹 **Stop Words**: Common words (e.g., "the", "is") that are often removed.  
-🔹 **Stemming**: Reducing words to their base form (e.g., "running" → "run").  
-🔹 **Lemmatization**: More advanced than stemming; converts words to their dictionary form.  
-🔹 **NER (Named Entity Recognition)**: Identifies entities like names, dates, and locations.  
-🔹 **Sentiment Analysis**: Determines the sentiment (positive, negative, neutral) of a text.  
-🔹 **n-grams**: Sequences of 'n' consecutive words (e.g., "New York" is a bi-gram).  
-</p>
-""", unsafe_allow_html=True)
+**Corpus**: A collection of text documents used for NLP tasks.  
+**Tokenization**: Splitting text into individual words or phrases.  
+**Stop Words**: Common words (e.g., "the", "is") that are often removed.  
+**Stemming**: Reducing words to their base form (e.g., "running" → "run").  
+**Lemmatization**: More advanced than stemming; converts words to their dictionary form.  
+**NER (Named Entity Recognition)**: Identifies entities like names, dates, and locations.  
+**Sentiment Analysis**: Determines the sentiment (positive, negative, neutral) of a text.  
+**n-grams**: Sequences of 'n' consecutive words (e.g., "New York" is a bi-gram).  
+""")
 
 # Section: Text Representation Methods
 st.markdown('<p class="section-title">Text Representation Methods</p>', unsafe_allow_html=True)
@@ -57,85 +54,81 @@ selected_method = st.radio("Select a text representation method:", methods)
 if selected_method == "Bag of Words":
     st.markdown('<p class="sub-title">Bag of Words (BoW)</p>', unsafe_allow_html=True)
     st.markdown("""
-    <p class="text">
     **Definition**: Represents text as a collection of word counts, ignoring grammar and word order.
-    </p>
-
-    <p class="sub-title">Uses:</p>
-    ✅ Sentiment analysis  
-    ✅ Document classification  
-    ✅ Information retrieval  
+    """)
+    st.markdown("""
+    **Uses:**
+    - ✅ Sentiment analysis  
+    - ✅ Document classification  
+    - ✅ Information retrieval  
 
-    <p class="sub-title">Advantages:</p>
-    ✅ Simple and easy to implement  
-    ✅ Works well with traditional ML models  
+    **Advantages:**
+    - ✅ Simple and easy to implement  
+    - ✅ Works well with traditional ML models  
 
-    <p class="sub-title">Disadvantages:</p>
-    ❌ Ignores word order and context  
-    ❌ High-dimensionality for large vocabularies  
-    """, unsafe_allow_html=True)
+    **Disadvantages:**
+    - ❌ Ignores word order and context  
+    - ❌ High-dimensionality for large vocabularies  
+    """)
 
 elif selected_method == "TF-IDF":
     st.markdown('<p class="sub-title">Term Frequency-Inverse Document Frequency (TF-IDF)</p>', unsafe_allow_html=True)
     st.markdown("""
-    <p class="text">
     **Definition**: Weighs words based on their frequency in a document and across all documents.
-    </p>
-
-    <p class="sub-title">Uses:</p>
-    ✅ Information retrieval (e.g., search engines)  
-    ✅ Text classification  
-    ✅ Keyword extraction  
+    """)
+    st.markdown("""
+    **Uses:**
+    - ✅ Information retrieval (e.g., search engines)  
+    - ✅ Text classification  
+    - ✅ Keyword extraction  
 
-    <p class="sub-title">Advantages:</p>
-    ✅ Reduces the impact of common words  
-    ✅ Highlights important words  
+    **Advantages:**
+    - ✅ Reduces the impact of common words  
+    - ✅ Highlights important words  
 
-    <p class="sub-title">Disadvantages:</p>
-    ❌ Still ignores word order  
-    ❌ Does not capture deep semantics  
-    """, unsafe_allow_html=True)
+    **Disadvantages:**
+    - ❌ Still ignores word order  
+    - ❌ Does not capture deep semantics  
+    """)
 
 elif selected_method == "One-Hot Encoding":
     st.markdown('<p class="sub-title">One-Hot Encoding</p>', unsafe_allow_html=True)
     st.markdown("""
-    <p class="text">
     **Definition**: Represents words as binary vectors where each word has a unique position in a vocabulary.
-    </p>
-
-    <p class="sub-title">Uses:</p>
-    ✅ Simple NLP tasks  
-    ✅ Word-level feature engineering  
+    """)
+    st.markdown("""
+    **Uses:**
+    - ✅ Simple NLP tasks  
+    - ✅ Word-level feature engineering  
 
-    <p class="sub-title">Advantages:</p>
-    ✅ Simple to understand  
-    ✅ Works well with small vocabulary sizes  
+    **Advantages:**
+    - ✅ Simple to understand  
+    - ✅ Works well with small vocabulary sizes  
 
-    <p class="sub-title">Disadvantages:</p>
-    ❌ Inefficient for large vocabularies  
-    ❌ No information on word meaning  
-    """, unsafe_allow_html=True)
+    **Disadvantages:**
+    - ❌ Inefficient for large vocabularies  
+    - ❌ No information on word meaning  
+    """)
 
 elif selected_method == "Word Embeddings (Word2Vec)":
     st.markdown('<p class="sub-title">Word Embeddings (Word2Vec)</p>', unsafe_allow_html=True)
     st.markdown("""
-    <p class="text">
     **Definition**: Converts words into dense numerical vectors capturing semantic relationships.
-    </p>
-
-    <p class="sub-title">Uses:</p>
-    ✅ Machine translation  
-    ✅ Speech recognition  
-    ✅ Sentiment analysis  
+    """)
+    st.markdown("""
+    **Uses:**
+    - ✅ Machine translation  
+    - ✅ Speech recognition  
+    - ✅ Sentiment analysis  
 
-    <p class="sub-title">Advantages:</p>
-    ✅ Captures semantic relationships  
-    ✅ Works well for deep learning models  
+    **Advantages:**
+    - ✅ Captures semantic relationships  
+    - ✅ Works well for deep learning models  
 
-    <p class="sub-title">Disadvantages:</p>
-    ❌ Requires large datasets to train  
-    ❌ Computationally expensive  
-    """, unsafe_allow_html=True)
+    **Disadvantages:**
+    - ❌ Requires large datasets to train  
+    - ❌ Computationally expensive  
+    """)
 
     # Sample texts
     texts = [
@@ -147,10 +140,10 @@ elif selected_method == "Word Embeddings (Word2Vec)":
     word_vectors = model.wv
     word = 'natural'
     if word in word_vectors:
-        st.markdown(f'<p class="text">Word2Vec Representation of "{word}":</p>', unsafe_allow_html=True)
+        st.markdown(f'Word2Vec Representation of "{word}":')
         st.write(word_vectors[word])
     else:
-        st.markdown(f'<p class="text">Word "{word}" not found in the vocabulary.</p>', unsafe_allow_html=True)
+        st.markdown(f'Word "{word}" not found in the vocabulary.')
 
 # Footer
 st.markdown('<hr>', unsafe_allow_html=True)