run.py 文件源码

def visualize_data(self):
        """
        Transform the DataFrame to the 2-dimensional case and visualizes the data. The first tags are used as labels.
        :return:
        """
        logging.debug("Preparing visualization of DataFrame")
        # Reduce dimensionality to 2 features for visualization purposes
        X_visualization = self.reduce_dimensionality(self.X, n_features=2)
        df = self.prepare_dataframe(X_visualization)
        # Set X and Y coordinate for each articles
        df['X coordinate'] = df['coordinates'].apply(lambda x: x[0])
        df['Y coordinate'] = df['coordinates'].apply(lambda x: x[1])
        # Create a list of markers, each tag has its own marker
        n_tags_first = len(self.df['tags_first'].unique())
        markers_choice_list = ['o', 's', '^', '.', 'v', '<', '>', 'D']
        markers_list = [markers_choice_list[i % 8] for i in range(n_tags_first)]
        # Create scatter plot
        sns.lmplot("X coordinate",
                   "Y coordinate",
                   hue="tags_first",
                   data=df,
                   fit_reg=False,
                   markers=markers_list,
                   scatter_kws={"s": 150})
        # Adjust borders and add title
        sns.set(font_scale=2)
        sns.plt.title('Visualization of TMT articles in a 2-dimensional space')
        sns.plt.subplots_adjust(right=0.80, top=0.90, left=0.12, bottom=0.12)
        # Show plot
        sns.plt.show()

    # Train recommender