density_forest.py 文件源码

def tune_entropy_threshold(self, n=5, depth=6, plot_debug=False):
        """
        Compute mean optimal entropy based on L-curve elbow method.
        """

        e_arr = []
        for i in range(n):

            var = Tree(self, rho=.5, depth=depth)
            e_arr += [pair + [i] for pair in var.entropy_gain_evol]

            var.domain_splits_plots(subpath='%s/'%i)

        entropy_evol = pd.DataFrame(e_arr, columns=['depth', 'entropy', 'tree'])
        entropy_evol = entropy_evol.groupby(['tree', 'depth'])[['entropy']].mean().reset_index().pivot(columns='tree', index='depth', values='entropy').fillna(0)
        entropy_elbow_cand = entropy_evol.apply(lambda x: opt_L_curve(np.array(x.index), np.array(x)))

        avg_opt_entropy = entropy_elbow_cand.mean()
        if plot_debug:

            fig = plt.figure(figsize=(10,10))
            ax = fig.add_subplot(111)
            entropy_evol.plot(ax=ax, kind='line', alpha=.6, lw=3., title='Avg. Opt. Entropy = %.2f'%avg_opt_entropy)
            plt.savefig('evol.png', format='png')
            plt.close()

        return avg_opt_entropy