这是使用scikit-learn的Tf- idf算法的实现。在应用之前，你可以word_tokenize()和干你的话。
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from nltk import word_tokenize
from nltk.stem.porter import Porterstemmer
def tokenize(text):
tokens = word_tokenize(text)
stems = []
for item in tokens: stems.append(Porterstemmer().stem(item))
return stems
# your corpus
text = ["This is your first text book", "This is the third text for analysis", "This is another text"]
# word tokenize and stem
text = [" ".join(tokenize(txt.lower())) for txt in text]
vectorizer = TfidfVectorizer()
matrix = vectorizer.fit_transform(text).todense()
# transform the matrix to a pandas df
matrix = pd.DataFrame(matrix, columns=vectorizer.get_feature_names())
# sum over each document (axis=0)
top_words = matrix.sum(axis=0).sort_values(ascending=False)
602392714
清零编程群