Method __init__

pattern/vector/__init__.py:770–787

A model is a bag-of-word representation of a corpus of documents, where each document vector is a bag of (word, relevance)-items. Vectors can then be compared for similarity using a distance metric. The weighting scheme can be: relative TF, TFIDF (default), BINA

(self, documents=[], weight=TFIDF)

class Model(object):
    
    def __init__(self, documents=[], weight=TFIDF):
        """ A model is a bag-of-word representation of a corpus of documents, 
            where each document vector is a bag of (word, relevance)-items.
            Vectors can then be compared for similarity using a distance metric.
            The weighting scheme can be: relative TF, TFIDF (default), BINARY, None,
            where None means that the original weights are used.
        """
        self.description = ""             # Description of the dataset: author e-mail, etc.
        self._documents  = readonlylist() # List of documents (read-only).
        self._index      = {}             # Document.name => Document
        self._df         = {}             # Cache of document frequency per word.
        self._cos        = {}             # Cache of ((d1.id, d2.id), relevance)-items (cosine similarity).
        self._ig         = {}             # Cache of (word, information gain)-items.
        self._vector     = None           # Cache of model vector with all the features in the model.
        self._lsa        = None           # LSA matrix with reduced dimensionality.
        self._weight     = weight         # Weight used in Document.vector (TF, TFIDF, BINARY or None).
        self._update()
        self.extend(documents)
    
    @property
    def documents(self):