tf-idf.py

from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer


data = open('./texto_aleatorio.txt')
custom_stop_words = frozenset(["palavra1", "palavra2","palavra3"])
vectorizer = CountVectorizer(stop_words=custom_stop_words)
vectorizer.fit(data)
print(vectorizer.vocabulary_)



data = open('./texto_aleatorio.txt')
custom_stop_words = frozenset(["palavra1", "palavra2","palavra3"])

vectorizer = TfidfVectorizer(stop_words=custom_stop_words)
vectorizer.fit(data)
print(vectorizer.vocabulary_)
print(vectorizer.idf_)

data = open('./texto_aleatorio.txt')
vector = vectorizer.transform([data.read()])
print(vector.shape)
print('\n')
print(vector.toarray())