pages/Statistical NLP.py

import streamlit as st
import numpy as np
import nltk
from nltk import pos_tag, word_tokenize
from sklearn_crfsuite import CRF
from sklearn.model_selection import train_test_split
from sklearn.datasets import fetch_20newsgroups
from collections import Counter
import random

# Download necessary NLTK data
nltk.download('punkt')
nltk.download('averaged_perceptron_tagger')


# Page title with emoji
st.title('📖 Statistical NLP 📖')

# Language Models: n-grams and smoothing techniques
st.markdown('<h2 style="color:#4CAF50">1️⃣ Language Models</h2>', unsafe_allow_html=True)

st.markdown('### 📖 Definition:')
st.write("""
Language models are statistical models that assign probabilities to sequences of words. 
They help us predict the next word in a sentence or assess the likelihood of a sentence.
- **n-grams**: A language model based on n-grams uses sequences of 'n' consecutive words to predict the next word.
- **Smoothing Techniques**: Smoothing techniques like Kneser-Ney are used to handle cases where a particular n-gram has not been seen in the training data, thus preventing zero probabilities.
""")

# Interactive example for n-grams
st.markdown('### 🎯 n-gram Model Example:')
ngram_input = st.text_area("✍️ Enter a sentence to see n-grams", "I love programming in Python")

n = st.slider("🔢 Choose n for n-grams:", 1, 4, 2)

if st.button('✨ Generate n-grams'):
    tokens = word_tokenize(ngram_input.lower())
    ngrams = [tuple(tokens[i:i+n]) for i in range(len(tokens)-n+1)]
    st.success(f"{n}-grams in the input sentence: {ngrams}")

# Perplexity
st.markdown('<h2 style="color:#FF5733">2️⃣ Perplexity</h2>', unsafe_allow_html=True)

st.markdown('### 📖 Definition:')
st.write("""
Perplexity is a measurement of how well a probability model predicts a sample. 
It’s often used to evaluate language models. A lower perplexity means the model is better at predicting the next word.
It’s calculated as the inverse probability of the test set normalized by the number of words.
""")

# Interactive example for calculating Perplexity
st.markdown('### 📊 Perplexity Calculation Example:')
sample_sentence = st.text_area("✍️ Enter sentence to calculate perplexity", "This is an example sentence")

if st.button('📉 Calculate Perplexity'):
    # Simple approximation of perplexity for demonstration
    word_count = len(sample_sentence.split())
    word_freq = Counter(sample_sentence.split())
    vocab_size = len(word_freq)
    perplexity = np.exp(sum(-np.log(word_freq[word] / word_count) for word in sample_sentence.split()) / word_count)
    st.success(f"Perplexity of the sentence: {perplexity:.2f}")

# Hidden Markov Models (HMM): Part-of-Speech (POS) tagging
st.markdown('<h2 style="color:#3E7FCB">3️⃣ Hidden Markov Models (HMM)</h2>', unsafe_allow_html=True)

st.markdown('### 📖 Definition:')
st.write("""
Hidden Markov Models (HMMs) are statistical models that represent sequences of observations with underlying hidden states. 
In NLP, they are commonly used for tasks like Part-of-Speech (POS) tagging, where each word is assigned a grammatical category (e.g., noun, verb).
""")

# Interactive POS Tagging example using HMM
st.markdown('### 🔍 POS Tagging with HMM:')
sentence_to_tag = st.text_area("✍️ Enter sentence for POS tagging", "I love programming in Python")

if st.button('📝 Tag POS'):
    tokens = word_tokenize(sentence_to_tag)
    tagged = pos_tag(tokens)
    st.success(f"POS Tagging result: {tagged}")

# Conditional Random Fields (CRF): Sequence labeling tasks like NER
st.markdown('<h2 style="color:#E67E22">4️⃣ Conditional Random Fields (CRF)</h2>', unsafe_allow_html=True)

st.markdown('### 📖 Definition:')
st.write("""
Conditional Random Fields (CRF) are used for sequence labeling tasks, where each element in the sequence is assigned a label. 
They are particularly useful for tasks like Named Entity Recognition (NER), where we want to identify entities such as people, organizations, or locations in text.
""")

# Sample data for Named Entity Recognition (NER) using CRF
st.markdown('### 🏷️ NER Example using CRF:')
sample_sentence = st.text_area("✍️ Enter sentence for NER (Named Entity Recognition)", "Barack Obama was born in Hawaii.")

# Sample NER prediction using a simple CRF model (a toy example)
ner_examples = [
    (["Barack", "Obama", "was", "born", "in", "Hawaii"], ["B-PER", "I-PER", "O", "O", "O", "B-LOC"]),
    (["Apple", "is", "based", "in", "California"], ["B-ORG", "O", "O", "O", "B-LOC"])
]

# Training a simple CRF model with toy data
X_train = [x[0] for x in ner_examples]
y_train = [x[1] for x in ner_examples]

# Initialize CRF
crf = CRF(algorithm='lbfgs')
crf.fit(X_train, y_train)

# Simple prediction for demonstration
if st.button('🔎 Perform NER'):
    tokens = word_tokenize(sample_sentence)
    predicted_tags = crf.predict([tokens])[0]
    entities = [(tokens[i], predicted_tags[i]) for i in range(len(tokens))]
    st.success(f"NER result: {entities}")