app.py

import streamlit as st



# Sidebar for navigation
sidebar = st.sidebar

# Sidebar header
sidebar.header('NLP Navigation')

# Sidebar options for NLP Overview, Lifecycle, and Techniques
sidebar_option = sidebar.radio('Choose a section to explore:', ['What is NLP?', 'NLP Lifecycle', 'NLP Techniques'])

# Store the selected page in session state
if 'selected_page' not in st.session_state:
    st.session_state.selected_page = sidebar_option

# Update the selected page if the user selects a different option
if sidebar_option != st.session_state.selected_page:
    st.session_state.selected_page = sidebar_option
    
# Dynamically update the title based on the selected option
if st.session_state.selected_page == 'What is NLP?':
    st.title('What is Natural Language Processing (NLP)?')
elif st.session_state.selected_page == 'NLP Lifecycle':
    st.title('Natural Language Processing (NLP) Lifecycle')
    if st.session_state.selected_page == 'Problem Definition':
        st.title('Steps in the Natural Language Processing (NLP) lifecycle:')
    elif st.session_state.selected_page == 'NLP Techniques':
        st.title('Natural Language Processing (NLP) Lifecycle')
elif st.session_state.selected_page == 'NLP Techniques':
    st.title('Techniques in Natural Language Processing (NLP)')
    
    
# Content for "What is NLP?"
if st.session_state.selected_page == 'What is NLP?':
    st.write("""
    ### What is NLP?
    Natural Language Processing (NLP) is a subfield of artificial intelligence (AI) that focuses on the interaction between computers and human (natural) languages. The goal of NLP is to enable machines to understand, interpret, and generate human language in a way that is meaningful.
    
    NLP is essential for enabling computers to process and analyze large amounts of natural language data, such as:
    - Text from documents
    - Speech from conversations
    - Images with textual descriptions

    #### Key Components of NLP:
    - **Syntax**: Refers to the arrangement of words in a sentence.
    - **Semantics**: Focuses on the meaning of the words and sentences.
    - **Pragmatics**: Involves the context and intent behind language.
    - **Discourse**: Studies how previous sentences and context influence meaning.

    #### Example Applications of NLP:
    - **Machine Translation**: Automatic translation of text from one language to another (e.g., Google Translate).
    - **Speech Recognition**: Converting spoken language into text (e.g., Siri, Alexa).
    - **Sentiment Analysis**: Analyzing text to determine the sentiment (positive, negative, neutral) (e.g., analyzing customer reviews).
    - **Text Summarization**: Creating a short summary of a long text (e.g., summarizing articles).

    NLP is used across multiple domains like healthcare, finance, and customer service to automate and improve various tasks.
    """)

# Content for NLP Lifecycle
elif st.session_state.selected_page == "NLP Lifecycle":
    lifecycle_option = sidebar.radio("Select NLP Lifecycle Step:", [
        "Overview of the NLP Life Cycle",
        "Problem Definition",
        "Data Collection",
        "Text Preprocessing",
        "Text Representation",
        "Model Training",
        "Evaluation",
        "Deployment"
    ])

    if lifecycle_option == "Overview of the NLP Life Cycle":
        st.write("""
        #### Overview of the NLP Life Cycle
        The NLP life cycle is a structured process for building, using, and maintaining systems that work with human language. It turns unstructured text into meaningful insights or automated actions. This process ensures continuous improvement and adapts to real-world needs.
    
        - **How It Flows**:
            - The process starts with identifying the problem and collecting the required text data.
            - Then, the data is cleaned and prepared for analysis.
            - Models are built and tested before being deployed for use.
            - Regular checks and updates ensure the solution keeps working well.
    
        - **Flexible and Adaptive**:
            - Since languages and data change (e.g., new words, trends), the process is repeated as needed.
            - Models may need updates or retraining to stay accurate.
    
        - **Combines Different Fields**:
            - The process involves skills from language studies, programming, and data analysis to make sure language is understood effectively.
    
        - **Designed for Practical Use**:
            - The goal is to create solutions that can handle tasks like analyzing text, identifying emotions, powering chatbots, or translating languages accurately and efficiently.
    
        - **Key Challenges Solved**:
            - Managing the complexity of language (e.g., meaning, structure).
            - Working with large and messy datasets.
            - Handling multiple languages and specific industries.
            - Ensuring solutions are fast and efficient.
    
        #### Steps in the NLP Life Cycle
        1. Problem Definition
        2. Data Collection
        3. Data Preprocessing
        4. Feature Engineering
        5. Model Selection and Training
        6. Model Evaluation
        7. Model Tuning
        8. Deployment
        9. Monitoring and Maintenance
        """)
    elif lifecycle_option == "Problem Definition":
        st.write("""
        #### 1. Problem Definition
        Problem definition is the first stage of the NLP lifecycle. It involves identifying the goal and understanding the problem that NLP can solve.
        - **Key Questions**:
            - What is the main objective of the analysis?
            - What type of text data is being handled (e.g., reviews, social media, documents)?
            - What output is expected (e.g., sentiment score, summary, classification)?
        **Example**: Define whether the goal is to classify customer reviews as positive or negative or to extract key topics from product reviews.
        """)

    
    elif lifecycle_option == "Data Collection":
        st.write("""
        #### 1. Data Collection
        Data collection is the first stage of the NLP lifecycle. It involves gathering relevant text data from various sources to analyze and process.
        - **Sources**:
            - Social media posts (e.g., tweets, Facebook status updates)
            - News articles (e.g., for summarization or sentiment analysis)
            - Customer reviews (e.g., on e-commerce platforms)
            - Books and research papers (e.g., for topic modeling or classification)

        **Example**: Scraping customer reviews from Amazon to analyze sentiment and feedback about a product.
        """)

    elif lifecycle_option == "Text Preprocessing":
        st.write("""
        #### 2. Text Preprocessing
        Text preprocessing prepares raw text for further analysis. This stage involves cleaning and transforming the data into a structured format that machine learning models can understand.
        - **Tokenization**: Splitting text into smaller units (e.g., words, phrases).
        - **Stop Words Removal**: Removing common words that don’t contribute much information.
        - **Lemmatization**: Converting words into their base or dictionary form.
        - **Stemming**: Cutting off prefixes or suffixes from words.
        - **Lowercasing**: Converting all characters in the text to lowercase.

        **Example**: For the sentence "The quick brown fox is running fast", after preprocessing:
        - Tokenization: ["The", "quick", "brown", "fox", "is", "running", "fast"]
        - Stop Words Removal: ["quick", "brown", "fox", "running", "fast"]
        - Lemmatization: ["quick", "brown", "fox", "run", "fast"]
        """)

    elif lifecycle_option == "Text Representation":
        st.write("""
        #### 3. Text Representation
        After preprocessing, the text data needs to be converted into a numerical format for use in machine learning models. There are several methods for text representation:
        - **Bag of Words (BoW)**: Converts text into a matrix of word frequencies.
        - **TF-IDF**: Weighs words based on their frequency in a specific document relative to their frequency across the entire dataset.
        - **Word Embeddings**: Transforms words into dense vectors that capture semantic meaning.

        **Example**: Using BoW to convert the sentence "I love NLP" into a vector representation:
        - Vocabulary: ["I", "love", "NLP"]
        - Vector: [1, 1, 1] (word frequency representation)
        """)

    elif lifecycle_option == "Model Training":
        st.write("""
        #### 4. Model Training
        In the model training stage, machine learning algorithms are trained on the preprocessed and represented text data. The choice of model depends on the task:
        - **Text Classification**: Naive Bayes, Support Vector Machines (SVM), or neural networks.
        - **Named Entity Recognition (NER)**: Conditional Random Fields (CRF), LSTMs, or transformers.
        - **Sentiment Analysis**: Logistic regression, Naive Bayes, or transformer-based models like BERT.

        **Example**: Training a Naive Bayes classifier to categorize news articles into topics such as "Sports", "Politics", etc.
        """)

    elif lifecycle_option == "Evaluation":
        st.write("""
        #### 5. Evaluation
        After training the model, it's important to evaluate its performance. Common evaluation metrics include:
        - **Accuracy**: The percentage of correctly classified samples.
        - **Precision**: The proportion of true positive predictions among all positive predictions.
        - **Recall**: The proportion of true positive predictions among all actual positive cases.
        - **F1-Score**: The harmonic mean of precision and recall.
        - **ROC and AUC**: Metrics used to evaluate classification models.

        **Example**: Using a confusion matrix to evaluate the performance of a sentiment analysis model.
        """)

    elif lifecycle_option == "Deployment":
        st.write("""
        #### 6. Deployment
        Once the model is trained and evaluated, it is deployed to production for real-world use. This might include integration with applications like chatbots, recommendation systems, or text summarization tools.
        - **Monitoring**: Continuous monitoring to ensure that the model performs well over time.
        - **Retraining**: The model might need to be retrained periodically as new data becomes available.

        **Example**: Deploying a chatbot powered by an NLP model to assist users on a website.
        """)

# Content for "NLP Techniques"
elif st.session_state.selected_page == "NLP Techniques":
    technique_option = sidebar.radio("Select NLP Technique:", [
        "Tokenization",
        "Stop Words Removal",
        "Lemmatization",
        "Stemming",
        "Bag of Words (BoW)",
        "TF-IDF",
        "Word Embeddings",
        "Named Entity Recognition (NER)",
        "Part-of-Speech (POS) Tagging",
        "Sentiment Analysis"
    ])
    
    if technique_option == "Tokenization":
        st.write("""
        #### 1. Tokenization
        Tokenization is the process of splitting text into smaller units, such as words, sentences, or subwords. This is a key preprocessing step for many NLP tasks.
        - **Example**: 
          - Sentence: "Natural Language Processing is awesome!"
          - Tokenized words: ["Natural", "Language", "Processing", "is", "awesome"]
        """)

    elif technique_option == "Stop Words Removal":
        st.write("""
        #### 2. Stop Words Removal
        Stop words are commonly used words like "the", "is", "at", etc., that do not carry much information in many NLP tasks. Removing stop words helps reduce the dimensionality and noise in the data.
        - **Example**: Removing "is" from the sentence "NLP is amazing!"
        """)

    elif technique_option == "Lemmatization":
        st.write("""
        #### 3. Lemmatization
        Lemmatization is the process of converting words into their root or base form based on context. It is more sophisticated than stemming, as it considers the meaning of words.
        - **Example**: "better" → "good", "running" → "run".
        """)

    elif technique_option == "Stemming":
        st.write("""
        #### 4. Stemming
        Stemming is the process of reducing words to their root form by removing prefixes or suffixes. This technique may result in non-dictionary words.
        - **Example**: "running" → "run", "happiness" → "happi".
        """)

    elif technique_option == "Bag of Words (BoW)":
        st.write("""
        #### 5. Bag of Words (BoW)
        The Bag of Words model represents text as a set of individual words, disregarding grammar and word order but keeping multiplicity. It is a simple and widely used method for text representation.
        - **Example**:
          - Text: "I love NLP"
          - BoW: {"I": 1, "love": 1, "NLP": 1}
        """)

    elif technique_option == "TF-IDF":
        st.write("""
        #### 6. TF-IDF (Term Frequency-Inverse Document Frequency)
        TF-IDF helps determine the importance of a word in a document relative to the entire dataset. It reduces the weight of common words and increases the weight of rare but important words.
        - **Example**: The word "data" might have a high TF-IDF score in a document about data analysis but a low score in a document about cooking.
        """)

    elif technique_option == "Word Embeddings":
        st.write("""
        #### 7. Word Embeddings
        Word embeddings are vector representations of words that capture semantic relationships. Words with similar meanings have similar vectors. Common word embedding models include:
        - **Word2Vec**
        - **GloVe**
        - **FastText**

        **Example**: The words "king" and "queen" would have similar vector representations because they share semantic relationships.
        """)

    elif technique_option == "Named Entity Recognition (NER)":
        st.write("""
        #### 8. Named Entity Recognition (NER)
        NER is the task of identifying named entities such as persons, organizations, locations, and dates in text. This technique is commonly used for information extraction.
        - **Example**: "Barack Obama was born in Hawaii."
          - Entities: ["Barack Obama" (Person), "Hawaii" (Location)]
        """)

    elif technique_option == "Part-of-Speech (POS) Tagging":
        st.write("""
        #### 9. Part-of-Speech (POS) Tagging
        POS tagging involves assigning grammatical labels (such as noun, verb, adjective) to each word in a sentence.
        - **Example**: "The cat sat on the mat."
          - POS Tags: [("The", "DT"), ("cat", "NN"), ("sat", "VBD"), ("on", "IN"), ("the", "DT"), ("mat", "NN")]
        """)

    elif technique_option == "Sentiment Analysis":
        st.write("""
        #### 10. Sentiment Analysis
        Sentiment analysis involves determining the sentiment of a piece of text, typically categorizing it as positive, negative, or neutral. This is commonly used for customer feedback and social media monitoring.
        - **Example**: "I love this product!" → Positive Sentiment
        """)