Method train

numpy_ml/lda/lda.py:206–247

Train the LDA model on a corpus of documents (bags of words). Parameters ---------- corpus : list of length `D` A list of lists, with each sublist containing the tokenized text of a single document. verbose : bool Whether

(self, corpus, verbose=False, max_iter=1000, tol=5)

        self.gamma = np.tile(self.alpha, (D, 1)) + np.tile(N / T, (T, 1)).T

    def train(self, corpus, verbose=False, max_iter=1000, tol=5):
        """
        Train the LDA model on a corpus of documents (bags of words).

        Parameters
        ----------
        corpus : list of length `D`
            A list of lists, with each sublist containing the tokenized text of
            a single document.
        verbose : bool
            Whether to print the VLB at each training iteration. Default is
            True.
        max_iter : int
            The maximum number of training iterations to perform before
            breaking. Default is 1000.
        tol : int
            Break the training loop if the difference betwen the VLB on the
            current iteration and the previous iteration is less than `tol`.
            Default is 5.
        """
        self.D = len(corpus)
        self.V = len(set(np.concatenate(corpus)))
        self.N = np.array([len(d) for d in corpus])
        self.corpus = corpus

        self.initialize_parameters()
        vlb = -np.inf

        for i in range(max_iter):
            old_vlb = vlb

            self._E_step()
            self._M_step()

            vlb = self.VLB()
            delta = vlb - old_vlb

            if verbose:
                print("Iteration {}: {:.3f} (delta: {:.2f})".format(i + 1, vlb, delta))

            if delta < tol:
                break


#######################################################################