def tfidf_basic(self):
vectorizer = CountVectorizer()
transformer = TfidfTransformer()
X = vectorizer.fit_transform(self.corpus)
print("\nTransform Matric: ")
print(X.toarray())
print("\nTransform Matric shape: ")
print (X.shape)
words = vectorizer.get_features() #所有文章的關鍵字
print ("\nAll feature(keywords)所有文章的字: ")
print (words)
# Matrix with one row per document and one column per token (e.g. word) occurring in the corpus.
# tfidf_matrix: [n_samples, n_features_new]
tfidf_matrix = transformer.fit_transform(X)
tfidf_weight = tfidf_matrix.toarray() #對應的tfidf矩陣
print ("\ntf-idf Matric: ")
print (tfidf_weight)
print (tfidf_weight.shape) # 4 * 9
return [words, tfidf_weight]