import nltk
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.decomposition import TruncatedSVD

# Create and fit model with TfidfVectorizer
svd = TruncatedSVD(n_components = 4, n_iter=100)
svd.fit(X)

# Get concept words
concept_words = {}
terms = vectorizer.get_feature_names()
for i, comp in enumerate(svd.components_):
    componentTerms = zip(terms, comp)
    sortedTerms = sorted(componentTerms, key=lambda x: x[1], reverse=True)
    sortedTerms = sortedTerms[:10]
    concept_words[f'Concept {str(i)}'] = sortedTerms

# Get scored relevance of corpus to concepts
svd_scores = {}
for key in concept_words.keys():
    sentence_scores = []
    for sentence in dataset:
        words = nltk.word_tokenize(sentence)
        score = 0
        for word in words:
            for word_with_score in concept_words[key]:
                if word == word_with_score[0]:
                    score += word_with_score[1]
                    
        sentence_scores.append(score)    
        
    svd_scores[key] = [score for score in sentence_scores]
    concept_map = {'Concept 0': 'Topic 1', 'Concept 1': 'Topic 2', 'Concept 2': 'Topic 3', 'Concept 3': 'Topic 4'}
    print(f'\n{key} {concept_map[key]}:')
    for i in range(len(sentence_scores)):
        print(f'{sentence_scores[i]}: {dataset[i]}')