text_visualization.py

from typing import Dict, Any, Iterable
from sklearn import TfIdfVectorizer
import wordcloud
from pydantic import BaseModel


class WordCloudExtractor:

    tfidf_params: Dict[str, Any]

    def extract_from_corpus(self, texts: Iterable[str], n_words: int) -> wordcloud.WordCloud:
        pass
from sklearn.feature_extraction.text import TfidfVectorizer
from wordcloud import WordCloud
import numpy as np

class TextVisualization:
    @staticmethod
    def extract_from_corpus(texts, max_features=100):
        """
        Extract word frequencies from a corpus using TF-IDF vectorization
        and generate word cloud frequencies.
        
        Args:
            texts: List of text documents
            max_features: Maximum number of words to include
            
        Returns:
            Dictionary of word frequencies suitable for WordCloud
        """
        # Initialize TF-IDF vectorizer
        tfidf = TfidfVectorizer(
            max_features=max_features,
            stop_words='english',
            lowercase=True
        )
        
        # Fit and transform the texts
        tfidf_matrix = tfidf.fit_transform(texts)
        
        # Get feature names (words)
        feature_names = tfidf.get_feature_names_out()
        
        # Calculate mean TF-IDF scores across documents
        mean_tfidf = np.array(tfidf_matrix.mean(axis=0)).flatten()
        
        # Create frequency dictionary
        frequencies = dict(zip(feature_names, mean_tfidf))
        
        return frequencies