我试图使用sklearn在NLP中添加词干到我的管道。
from nltk.stem.snowball import FrenchStemmer
stop = stopwords.words('french')
stemmer = FrenchStemmer()
class StemmedCountVectorizer(CountVectorizer):
def __init__(self, stemmer):
super(StemmedCountVectorizer, self).__init__()
self.stemmer = stemmer
def build_analyzer(self):
analyzer = super(StemmedCountVectorizer, self).build_analyzer()
return lambda doc:(self.stemmer.stem(w) for w in analyzer(doc))
stem_vectorizer = StemmedCountVectorizer(stemmer)
text_clf = Pipeline([('vect', stem_vectorizer), ('tfidf', TfidfTransformer()), ('clf', SVC(kernel='linear', C=1)) ])
将此管道与sklearn的CountVectorizer一起使用时,它可以正常工作。如果我手动创建这样的功能,它也可以。
vectorizer = StemmedCountVectorizer(stemmer)
vectorizer.fit_transform(X)
tfidf_transformer = TfidfTransformer()
X_tfidf = tfidf_transformer.fit_transform(X_counts)
修改:
如果我在我的IPython笔记本上尝试这个管道,它会显示[*]并且没有任何反应。当我看到我的终端时,它会出现这个错误:
Process PoolWorker-12:
Traceback (most recent call last):
File "C:\Anaconda2\lib\multiprocessing\process.py", line 258, in _bootstrap
self.run()
File "C:\Anaconda2\lib\multiprocessing\process.py", line 114, in run
self._target(*self._args, **self._kwargs)
File "C:\Anaconda2\lib\multiprocessing\pool.py", line 102, in worker
task = get()
File "C:\Anaconda2\lib\site-packages\sklearn\externals\joblib\pool.py", line 360, in get
return recv()
AttributeError: 'module' object has no attribute 'StemmedCountVectorizer'
实施例
这是完整的例子
from sklearn.pipeline import Pipeline
from sklearn import grid_search
from sklearn.svm import SVC
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from nltk.stem.snowball import FrenchStemmer
stemmer = FrenchStemmer()
analyzer = CountVectorizer().build_analyzer()
def stemming(doc):
return (stemmer.stem(w) for w in analyzer(doc))
X = ['le chat est beau', 'le ciel est nuageux', 'les gens sont gentils', 'Paris est magique', 'Marseille est tragique', 'JCVD est fou']
Y = [1,0,1,1,0,0]
text_clf = Pipeline([('vect', CountVectorizer()), ('tfidf', TfidfTransformer()), ('clf', SVC())])
parameters = { 'vect__analyzer': ['word', stemming]}
gs_clf = grid_search.GridSearchCV(text_clf, parameters, n_jobs=-1)
gs_clf.fit(X, Y)
如果你从参数中删除了它,那么它就可以工作。
更新:
问题似乎出现在并行化过程中,因为当删除 n_jobs = -1 时,问题就会消失。
答案 0 :(得分:23)
您可以将可调用的analyzer
传递给CountVectorizer
构造函数,以提供自定义分析器。这似乎对我有用。
from sklearn.feature_extraction.text import CountVectorizer
from nltk.stem.snowball import FrenchStemmer
stemmer = FrenchStemmer()
analyzer = CountVectorizer().build_analyzer()
def stemmed_words(doc):
return (stemmer.stem(w) for w in analyzer(doc))
stem_vectorizer = CountVectorizer(analyzer=stemmed_words)
print(stem_vectorizer.fit_transform(['Tu marches dans la rue']))
print(stem_vectorizer.get_feature_names())
打印出来:
(0, 4) 1
(0, 2) 1
(0, 0) 1
(0, 1) 1
(0, 3) 1
[u'dan', u'la', u'march', u'ru', u'tu']
答案 1 :(得分:14)
我知道我发布答案时迟到了。 但在这里,如果有人仍然需要帮助。
以下是通过覆盖build_analyser()
from sklearn.feature_extraction.text import CountVectorizer
import nltk.stem
french_stemmer = nltk.stem.SnowballStemmer('french')
class StemmedCountVectorizer(CountVectorizer):
def build_analyzer(self):
analyzer = super(StemmedCountVectorizer, self).build_analyzer()
return lambda doc: ([french_stemmer.stem(w) for w in analyzer(doc)])
vectorizer_s = StemmedCountVectorizer(min_df=3, analyzer="word", stop_words='french')
您可以在fit
对象上自由调用CountVectorizer类的transform
和vectorizer_s
个函数
答案 2 :(得分:1)
您可以尝试:
def build_analyzer(self):
analyzer = super(CountVectorizer, self).build_analyzer()
return lambda doc:(stemmer.stem(w) for w in analyzer(doc))
并删除__init__
方法。