pages/The NLP Basic_Terminologies.py

import streamlit as st

# Streamlit App Title and Introduction
st.title("Basic Terminology in NLP")

st.write(
    """
    Before diving deep into the concepts of NLP, it's crucial to understand the basic terminologies frequently used in this domain.
    These terms lay the foundation for exploring more advanced NLP topics.
    """
)

# Section: Key Terminologies in NLP
st.header("1. Key Terminologies in NLP")
st.write(
    """
    - **Corpus**: A collection of text documents.
      Example: {d1, d2, d3, ...}
    - **Document**: A single unit of text (e.g., a sentence, paragraph, or article).
    - **Paragraph**: A collection of sentences.
    - **Sentence**: A collection of words forming a meaningful expression.
    - **Word**: A collection of characters.
    - **Character**: A basic unit like an alphabet, number, or special symbol.
    """
)

# Section: Tokenization
st.header("2. Tokenization")
st.write(
    """
    Tokenization is the process of splitting text into smaller units, called tokens.
    
    Types of Tokenization:
    - **Sentence Tokenization**: Splitting text into sentences.
      Example: "I love ice-cream. I love chocolate." → ["I love ice-cream", "I love chocolate"]
    - **Word Tokenization**: Splitting sentences into words.
      Example: "I love biryani" → ["I", "love", "biryani"]
    - **Character Tokenization**: Splitting words into characters.
      Example: "Love" → ["L", "o", "v", "e"]
    """
)

if st.button("Try Tokenization Example"):
    text = "Streamlit makes NLP visualization interactive."
    st.write(f"Original Text: {text}")
    st.write(f"Word Tokens: {text.split()}")

# Section: Stop Words
st.header("3. Stop Words")
st.write(
    """
    Stop words are commonly used words in a language that are ignored during text processing as they contribute little to the overall meaning.
    
    Example:
    - Sentence: "In Hyderabad, we can eat famous biryani."
    - Stop words: ["in", "we", "can"]
    """
)

if st.button("View Processed Text without Stop Words"):
    text = "In Hyderabad, we can eat famous biryani."
    stop_words = ["in", "we", "can"]
    filtered_text = " ".join([word for word in text.split() if word.lower() not in stop_words])
    st.write(f"Processed Text: {filtered_text}")

# Section: Vectorization
st.header("4. Vectorization")
st.write(
    """
    Vectorization converts text data into numerical formats for machine learning models, enabling text processing and analysis.
    
    Types of Vectorization:
    - **One-Hot Encoding**: Represents each word as a binary vector.
    - **Bag of Words (BoW)**: Represents text based on word frequencies.
    - **TF-IDF (Term Frequency-Inverse Document Frequency)**: Adjusts word frequency by importance.
    - **Word2Vec**: Embeds words in a vector space using deep learning.
    - **GloVe**: Uses global co-occurrence statistics for embedding.
    - **FastText**: Similar to Word2Vec but includes subword information.
    """
)

# Section: Stemming
st.header("5. Stemming")
st.write(
    """
    Stemming reduces words to their base or root form by chopping off prefixes or suffixes. It is a rule-based heuristic process 
    and can produce words that may not be valid in the language.
    
    Example:
    - Original Words: "running", "runner", "runs"
    - Stemmed Form: "run"
    """
)

if st.button("Try Stemming Example"):
    words = ["running", "runner", "runs"]
    stemmed_words = [word[:-3] if word.endswith("ing") else word[:-2] if word.endswith("er") else word for word in words]
    st.write("Original Words:", words)
    st.write("Stemmed Words:", stemmed_words)

# Section: Lemmatization
st.header("6. Lemmatization")
st.write(
    """
    Lemmatization reduces words to their dictionary or base form, called a lemma, while considering the context of the word in a sentence.
    
    Example:
    - Original Words: "studying", "better", "carrying"
    - Lemmatized Form: "study", "good", "carry"
    
    Lemmatization is more accurate than stemming but computationally more intensive as it requires a language dictionary.
    """
)

if st.button("Try Lemmatization Example"):
    words = ["studying", "better", "carrying"]
    lemmatized_words = ["study" if word == "studying" else "good" if word == "better" else "carry" if word == "carrying" else word for word in words]
    st.write("Original Words:", words)
    st.write("Lemmatized Words:", lemmatized_words)