CountVectorizer 中的令牌模式，scikit-learn [英] Token pattern in CountVectorizer, scikit-learn

问题描述

所以我有如下关键字列表，

So I have list of keywords as follows,

[u"ALZHEIMER'S DISEASE, OLFACTORY, AGING", 
 u"EEG, COGNITIVE CONTROL, FATIGUE", 
 u"AGING, OBESITY, GENDER", 
 u"AGING, COGNITIVE CONTROL, BRAIN IMAGING"]

然后我想使用 CountVectorizer 来标记化，以便我的模型具有以下字典:

Then I want to use CountVectorizer to tokenize so that my model has following dictionary:

[{'ALZHEIMER\'S DISEASE': 0, 'OLFACTORY': 1, 'AGING': 2, 'BRAIN IMAGING': 3, ...}]

基本上，我想将逗号视为我的标记化模式(最后一个除外).但是，请随意在每个列表的末尾连接 ,.这是我现在拥有的代码片段:

Basically, I want to treat comma as my tokenize pattern (except the last one). However, feel free to concat , at the end of each list. Here is a code snippet that I have right now:

from sklearn.feature_extraction.text import CountVectorizer
ls = [u"ALZHEIMER'S DISEASE, OLFACTORY, AGING", 
      u"EEG, COGNITIVE CONTROL, FATIGUE", 
      u"AGING, OBESITY, GENDER", 
      u"AGING, COGNITIVE CONTROL, BRAIN IMAGING"]
tfidf_model = CountVectorizer(min_df=1, max_df=1, token_pattern=r'(\w{1,}),')
tfidf_model.fit_transform(ls)
print tfidf_model.vocabulary_.keys()
>>> [u'obesity', u'eeg', u'olfactory', u'disease']

如果您想了解更多信息，请随时发表评论.

Feel free to comments if you want more information.

推荐答案

这是我的回答.我首先将每个文档转换为列表列表(每个都是术语).

Here is answer that I made. I first transform to each documents to list of list (each is terms).

docs = list(map(lambda s: s.lower().split(', '), ls)) # list of list

我创建了一个函数来从列表中的单词生成字典，然后将单词列表转换为稀疏矩阵

I created a function to generate dictionary from words in a list and then transform list of words to sparse matrix

import collections
from itertools import chain

def tag_to_sparse(docs):
    docs_list = list(chain(*docs))
    docs_list = [w for doc in docs for w in doc]
    counter = collections.Counter(docs_list)
    count_pairs = sorted(counter.items(), key=lambda x: -x[1])
    vocabulary = dict([(c[0], i) for i, c in enumerate(count_pairs)])

    row_ind = list()
    col_ind = list()
    for i, doc in enumerate(docs):
        for w in doc:
            row_ind.append(i)
            col_ind.append(vocabulary[w])
    value = [1]*len(row_ind)
    X = sp.csr_matrix((value, (row_ind, col_ind)))
    X.sum_duplicates()
    return X, vocabulary

我可以把它X,vocabulary = tag_to_sparse(docs) 得到稀疏矩阵和词汇字典.

I can just put it X, vocabulary = tag_to_sparse(docs) to get sparse matrix and vocabulary dictionary.

我刚刚找到了答案，以便您可以使用 tokenizer

I just found the answer so that you can trick scikit-learn to recognize , by using tokenizer

vocabulary = list(map(lambda x: x.lower().split(', '), ls))
vocabulary = list(np.unique(list(chain(*vocabulary))))

from sklearn.feature_extraction.text import CountVectorizer
model = CountVectorizer(vocabulary=vocabulary, tokenizer=lambda x: x.split(', '))
X = model.fit_transform(ls)

这篇关于CountVectorizer 中的令牌模式，scikit-learn的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！