ClasteringCalculator.py 文件源码

def make_mean_shift_clustering(self, short_filenames, input_texts):

        output_dir = self.output_dir + 'mean_shift/'
        if not os.path.exists(output_dir):
            os.makedirs(output_dir)

        if self.need_tf_idf:
            self.signals.PrintInfo.emit("?????? TF-IDF...")
            idf_filename = output_dir + 'tf_idf.csv'
            msg = self.calculate_and_write_tf_idf(idf_filename, input_texts)
            self.signals.PrintInfo.emit(msg)

        vectorizer = CountVectorizer()
        X = vectorizer.fit_transform(input_texts)

        svd = TruncatedSVD(2)
        normalizer = Normalizer(copy=False)
        lsa = make_pipeline(svd, normalizer)
        X = lsa.fit_transform(X)

        if (len(input_texts) * self.mean_shift_quantile) < 1.0:
            self.mean_shift_quantile = (1.0 / len(input_texts)) + 0.05

        bandwidth = estimate_bandwidth(X, quantile=self.mean_shift_quantile)
        if bandwidth == 0:
            bandwidth = 0.1

        ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
        predict_result = ms.fit_predict(X)
        self.signals.PrintInfo.emit('\n??????? ?? ??????????:\n')

        clasters_output = ''
        for claster_index in range(max(predict_result) + 1):
            clasters_output += ('??????? ' + str(claster_index) + ':\n')
            for predict, document in zip(predict_result, short_filenames):
                if predict == claster_index:
                    clasters_output += ('  ' + str(document) + '\n')
            clasters_output += '\n'
        self.signals.PrintInfo.emit(clasters_output)
        self.signals.PrintInfo.emit('????????? ?:' + str(output_dir + 'clusters.txt'))
        writeStringToFile(clasters_output, output_dir + 'clusters.txt')

        self.draw_clusters_plot(X, predict_result, short_filenames)