Method classify

pattern/vector/__init__.py:2068–2095

Returns the type with the highest probability for the given document. If the classifier has been trained on LSA concept vectors you need to supply LSA.transform(document).

(self, document, discrete=True)

        Classifier.train(self, document, type)
    
    def classify(self, document, discrete=True):
        """ Returns the type with the highest probability for the given document.
            If the classifier has been trained on LSA concept vectors
            you need to supply LSA.transform(document).
        """
        # Distance is calculated between the document vector and all training instances.
        # This will make KNN.test() slow in higher dimensions.
        classes = {}
        v1 = self._vector(document)[1]
        D = ((distance(v1, v2, method=self.distance), type) for type, v2 in self._vectors)
        D = ((d, type) for d, type in D if d < 1) # Nothing in common if distance=1.0.
        D = heapq.nsmallest(self.k, D)            # k-least distant.
        # Normalize probability estimates.
        s = sum(1 - d for d, type in D) or 1
        p = defaultdict(float)
        for d, type in D:
            p[type] += (1 - d) / s
        if not discrete:
            return p
        try:
            # Ties are broken in favor of the majority class
            # (random winner for majority ties).
            m = max(p.itervalues())
            p = sorted((self._classes[type], type) for type, w in p.iteritems() if w == m > 0)
            p = [type for frequency, type in p if frequency == p[0][0]]
            return choice(p)
        except:
            return self.baseline

NearestNeighbor = kNN = KNN