Scikit learn 使用TfidfVectorizer，是否可以使用一个语料库获取idf信息，另一个语料库获取实际索引？

使用sklearn.feature\u extraction.text.tfidf矢量器

我想用一包单词tf idf数据来训练分类器

我有一个大的未标记语料库和一个小的标记语料库

我计划使用标记的语料库构建一个基于tf idf模型的单词包的分类器。 然而，我更喜欢使用完整的语料库（包括未标记的数据）来计算idf统计数据

在使用sklearn时，这可能吗

---

我想到的一个解决方案是建立所有语料库的模型，然后删除属于未标记数据的行。但是，语料库可能太大，无法存储在ram中。

如果我理解正确的话。您可以将TFIDF模型与所有数据相匹配，然后在较小的标记语料库上调用

transform

：

vec =TfidfVectorizer()
model = vec.fit(alldata)
tagged_data_tfidf = vec.transform(tagged_data)

---

谢谢@JAB，这就是我要找的

关于不适合RAM的数据，可以使用迭代器，如果数据分布在不同的源中，则可以使用多个迭代器。在我的例子中，带标签的数据存储在文件中，而我的数据存储在mongoDB中： 文件迭代器：

class File2Doc(object):
    def __init__(self, top_dir):
        self.top_dir = top_dir

    def __iter__(self):
        for root, dirs, files in os.walk(self.top_dir):
            for fname in filter(lambda fname: fname.endswith('.txt'), files):
                with open(os.path.join(root, fname), encoding='utf8', errors='ignore') as file:
                    document = file.read()
                    yield document

class Mongo2Doc(object):
        """
        an iterator that builds a find pymongo cursor and saves the text field in the mongodb collection
        """
    def __init__(self, query):
        self.cur = query.cur
        self.text_field = query.text_field

    def __iter__(self):
        for document in self.cur:
            yield document[self.text_field]

class MyDocIterator(object):
    '''
    Expects a list of [folders] (paths) and/or a list of mongoDB [queries]
    mongoDB queries have the form (collection_name, {find_query}, {projection: or text_field})
    example:
    mongo_query = [mongo_client.db.collection, {'optional_query': 'some_value'}, {'text':1}]
    '''

    def __init__(self, folders=None, mongo_query=None):
        self.folders = folders
        self.mongo_query = mongo_query
        if self.folders is not None:
            assert isinstance(self.folders, list), 'folders should be a list'
        if self.mongo_query is not None:
            assert isinstance(self.mongo_query,
                              list), 'Mongo query should be a list'
        if self.folders is None and self.mongo_query is None:
            raise TypeError(
                'Please specify at least one folder or one mongo query')

    def __iter__(self):
        k = []
        if self.folders is not None:
            f = [File2Doc(folder) for folder in self.folders]
            k.extend(f)
        if self.mongo_query is not None:
            m = [Mongo2Doc(query) for query in self.mongo_query]
            k.extend(m)
        return chain.from_iterable(k)

mongoDB迭代器：

class File2Doc(object):
    def __init__(self, top_dir):
        self.top_dir = top_dir

    def __iter__(self):
        for root, dirs, files in os.walk(self.top_dir):
            for fname in filter(lambda fname: fname.endswith('.txt'), files):
                with open(os.path.join(root, fname), encoding='utf8', errors='ignore') as file:
                    document = file.read()
                    yield document

class Mongo2Doc(object):
        """
        an iterator that builds a find pymongo cursor and saves the text field in the mongodb collection
        """
    def __init__(self, query):
        self.cur = query.cur
        self.text_field = query.text_field

    def __iter__(self):
        for document in self.cur:
            yield document[self.text_field]

class MyDocIterator(object):
    '''
    Expects a list of [folders] (paths) and/or a list of mongoDB [queries]
    mongoDB queries have the form (collection_name, {find_query}, {projection: or text_field})
    example:
    mongo_query = [mongo_client.db.collection, {'optional_query': 'some_value'}, {'text':1}]
    '''

    def __init__(self, folders=None, mongo_query=None):
        self.folders = folders
        self.mongo_query = mongo_query
        if self.folders is not None:
            assert isinstance(self.folders, list), 'folders should be a list'
        if self.mongo_query is not None:
            assert isinstance(self.mongo_query,
                              list), 'Mongo query should be a list'
        if self.folders is None and self.mongo_query is None:
            raise TypeError(
                'Please specify at least one folder or one mongo query')

    def __iter__(self):
        k = []
        if self.folders is not None:
            f = [File2Doc(folder) for folder in self.folders]
            k.extend(f)
        if self.mongo_query is not None:
            m = [Mongo2Doc(query) for query in self.mongo_query]
            k.extend(m)
        return chain.from_iterable(k)

在一个迭代器中组合这两个元素：

class File2Doc(object):
    def __init__(self, top_dir):
        self.top_dir = top_dir

    def __iter__(self):
        for root, dirs, files in os.walk(self.top_dir):
            for fname in filter(lambda fname: fname.endswith('.txt'), files):
                with open(os.path.join(root, fname), encoding='utf8', errors='ignore') as file:
                    document = file.read()
                    yield document

class Mongo2Doc(object):
        """
        an iterator that builds a find pymongo cursor and saves the text field in the mongodb collection
        """
    def __init__(self, query):
        self.cur = query.cur
        self.text_field = query.text_field

    def __iter__(self):
        for document in self.cur:
            yield document[self.text_field]

class MyDocIterator(object):
    '''
    Expects a list of [folders] (paths) and/or a list of mongoDB [queries]
    mongoDB queries have the form (collection_name, {find_query}, {projection: or text_field})
    example:
    mongo_query = [mongo_client.db.collection, {'optional_query': 'some_value'}, {'text':1}]
    '''

    def __init__(self, folders=None, mongo_query=None):
        self.folders = folders
        self.mongo_query = mongo_query
        if self.folders is not None:
            assert isinstance(self.folders, list), 'folders should be a list'
        if self.mongo_query is not None:
            assert isinstance(self.mongo_query,
                              list), 'Mongo query should be a list'
        if self.folders is None and self.mongo_query is None:
            raise TypeError(
                'Please specify at least one folder or one mongo query')

    def __iter__(self):
        k = []
        if self.folders is not None:
            f = [File2Doc(folder) for folder in self.folders]
            k.extend(f)
        if self.mongo_query is not None:
            m = [Mongo2Doc(query) for query in self.mongo_query]
            k.extend(m)
        return chain.from_iterable(k)

用法示例：

my_docs = MyDocIterator(['path_to_data'])
bow_vectorizer = CountVectorizer(preprocessor=custom_text_preprocessor, tokenizer=str.split)
bow_vectorizer.fit(my_docs)

类似于TFIDF矢量器