corpus.py 文件源码

def plot(self, filename="./corpus/model/blog.png"):
        tsne = TSNE(perplexity=30, n_components=2, init="pca", n_iter=5000)
        plot_only=500
        low_dim_embeddings = tsne.fit_transform(self.final_embeddings[:plot_only, :])
        reversed_dictionary = dict(zip(self.dictionary.values(), self.dictionary.keys()))
        labels = [reversed_dictionary[i] for i in range(plot_only)]

        plt.figure(figsize=(18, 18))
        for i, label in enumerate(labels):
            x, y = low_dim_embeddings[i, :]
            plt.scatter(x, y)
            plt.annotate(label,
                        xy=(x, y),
                        xytext=(5, 2),
                        textcoords="offset points",
                        ha="right",
                        va="bottom")
        plt.savefig(filename)
        print("Scatter plot was saved to", filename)