sklearn:TFIDF Transformer:如何获取文档中给定单词的tf-idf值

Question

我使用sklean使用命令as计算文档中术语的TFIDF值

from sklearn.feature_extraction.text import CountVectorizer
count_vect = CountVectorizer()
X_train_counts = count_vect.fit_transform(documents)
from sklearn.feature_extraction.text import TfidfTransformer
tf_transformer = TfidfTransformer(use_idf=False).fit(X_train_counts)
X_train_tf = tf_transformer.transform(X_train_counts)

X_train_tf是scipy稀疏形状矩阵

from sklearn.feature_extraction.text import CountVectorizer
count_vect = CountVectorizer()
X_train_counts = count_vect.fit_transform(documents)
from sklearn.feature_extraction.text import TfidfTransformer
tf_transformer = TfidfTransformer(use_idf=False).fit(X_train_counts)
X_train_tf = tf_transformer.transform(X_train_counts)

输出为(2257,35788).如何在特定文档中获取TF-IDF？更具体地说,如何在给定文档中获取具有最大TF-IDF值的单词？

Answer 1

你可以使用sklean的TfidfVectorizer

from sklearn.feature_extraction.text import TfidfVectorizer
import numpy as np
from scipy.sparse.csr import csr_matrix #need this if you want to save tfidf_matrix

tf = TfidfVectorizer(input='filename', analyzer='word', ngram_range=(1,6),
                     min_df = 0, stop_words = 'english', sublinear_tf=True)
tfidf_matrix =  tf.fit_transform(corpus)

上述tfidf_matix具有语料库中所有文档的TF-IDF值.这是一个很大的稀疏矩阵.现在,

feature_names = tf.get_feature_names()

这将为您提供所有令牌或n-gram或单词的列表.对于语料库中的第一个文档,

doc = 0
feature_index = tfidf_matrix[doc,:].nonzero()[1]
tfidf_scores = zip(feature_index, [tfidf_matrix[doc, x] for x in feature_index])

让我们打印,

for w, s in [(feature_names[i], s) for (i, s) in tfidf_scores]:
  print w, s

Answer 2

这是带有pandas库的Python 3中的另一个更简单的解决方案

from sklearn.feature_extraction.text import TfidfVectorizer
import pandas as pd

vect = TfidfVectorizer()
tfidf_matrix = vect.fit_transform(documents)
df = pd.DataFrame(tfidf_matrix.toarray(), columns = vect.get_feature_names())
print(df)

Answer 3

查找句子中每个单词的 tfidf 分数有助于执行搜索和语义匹配等下游任务。

我们可以得到以单词为键、以 tfidf_score 作为值的字典。

from sklearn.feature_extraction.text import TfidfVectorizer

tfidf = TfidfVectorizer(min_df=3)
tfidf.fit(list(subject_sentences.values()))
feature_names = tfidf.get_feature_names()

现在我们可以这样编写转换逻辑

def get_ifidf_for_words(text):
    tfidf_matrix= tfidf.transform([text]).todense()
    feature_index = tfidf_matrix[0,:].nonzero()[1]
    tfidf_scores = zip([feature_names[i] for i in feature_index], [tfidf_matrix[0, x] for x in feature_index])
    return dict(tfidf_scores)

例如对于输入

text = "increase post character limit"
get_ifidf_for_words(text)

输出将是

{
'character': 0.5478868741621505,
'increase': 0.5487092618866405,
'limit': 0.5329156819959756,
'post': 0.33873144956352985
}