easy_lda.py 文件源码

def __init__(self, num_topics=6, num_iterations=500, random_state=None, clean_text=True, vectorizer=None):
        """
        Init for LDA estimator
        :param num_topics: Number of topics to model (generally 3-10)
        :type num_topics: int
        :param num_iterations: Number of iterations to allow before locking in topics
        :type num_iterations: int
        :param random_state: Random seed, for consistent topics
        :type random_state: int
        :param clean_text: Whether to clean text using self.preprocess(). Recommended if you have not preprocessed
        the text already
        :type clean_text: bool
        :param vectorizer: Word vectorizer to use. The word vectorizer should convert a collection of text documents
        to a matrix of token counts
        """
        self.num_topics = num_topics
        self.num_iterations = num_iterations
        self.random_state = random_state
        self.lda_model = lda.LDA(n_topics=self.num_topics, n_iter=self.num_iterations, random_state=self.random_state)
        self.clean_text = clean_text
        self.get_topic_description_df = None
        if vectorizer is not None:
            self.vectorizer = vectorizer
        else:
            self.vectorizer = CountVectorizer()

        # Make sure nltk has required data sets
        nltk.download('punkt')
        nltk.download('stopwords')
        nltk.download('wordnet')