Add script to make digures.

import os

import json

import numpy as np

import pandas as pd

import matplotlib

matplotlib.use("agg")

import matplotlib.pyplot as plt

#matplotlib.rc("xtick", labelsize=14)

#matplotlib.rc("ytick", labelsize=14)

def heat_maps(dataset, depths, widths):

	dir = os.path.join("figs", dataset, "hm")

	os.makedirs(dir, exist_ok=True)

	quants = ["loss", "v_b", "v_w", "v_n"]

	titles = ["Loss", "$v_b$", "$v_w$", "$v_n$"]

	ims = {q: [] for q in quants}

	for d in depths:

		ims_d = {q: [] for q in quants}

		for w in widths:

			with open( os.path.join("../results", dataset, "depths1_{}_widths{}.json".format(d, w)), "r") as fp:

				results = json.load(fp)

			for q in quants:

				ims_d[q].append( results["test"][q] )

		for q in quants:

			ims[q].append( ims_d[q] )

	ims = {q: np.array(v) for (q, v) in ims.items()}

	for (q, title) in zip(quants, titles):

		plt.figure()

		plt.imshow(ims[q], cmap="YlGnBu_r")

		plt.colorbar()

		plt.xticks(np.arange(len(widths))+1, widths)

		plt.yticks(np.arange(len(depths))+1, depths)

		plt.xlabel("Width", fontsize=12)

		plt.ylabel("Depth", fontsize=12)

		plt.title(title, fontsize=16)

		plt.tight_layout()

		filename = os.path.join(dir, "{}.png".format(q))

		plt.savefig(filename, box_inches="tight")

		plt.close()

def learning_curves(dataset, depth, width):

	with open( os.path.join("../results", dataset, "depths1_{}_widths{}.json".format(depth, width)), "r") as fp:

		results = json.load(fp)

		dir = os.path.join("figs", dataset, "lc", "d{}w{}".format(depth, width))

	os.makedirs(dir, exist_ok=True)

	# loss

	iters = np.arange(1, len(results["train"]["loss"])+1)

	plt.figure()

	plt.plot(iters, results["train"]["loss"], color="red", label="Before update")

	plt.plot(iters, results["train"]["loss_new"], color="blue", label="After update")

	plt.legend(loc="upper right", bbox_to_anchor=(1, 1), fancybox=True, fontsize=10)

	plt.xlabel("Iteration", fontsize=12)

	plt.title("Loss", fontsize=16)

	plt.tight_layout()

	filename = os.path.join(dir, "loss.png")

	plt.savefig(filename, box_inches="tight")

	plt.close()

	# delta loss

	plt.figure()

	plt.plot(iters, results["train"]["delta_loss"], color="black")

	plt.xlabel("Iteration", fontsize=12)

	plt.ylabel("(%)", fontsize=12)

	plt.title("Change in loss", fontsize=16)

	plt.tight_layout()

	filename = os.path.join(dir, "delta_loss.png")

	plt.savefig(filename, box_inches="tight")

	plt.close()

	# parameters

	iters = np.arange(len(results["train"]["loss"])+1)

	plt.figure()

	for (param, color) in zip(["v_b", "v_w", "v_n"], ["red", "green", "blue"]):

		plt.plot(iters, results["train"][param], color=color, label="${}$".format(param))

	plt.legend(loc="upper right", bbox_to_anchor=(1, 1), fancybox=True, fontsize=10)

	plt.xlabel("Iteration", fontsize=12)

	plt.title("Hyperparameters", fontsize=16)

	plt.tight_layout()

	filename = os.path.join(dir, "params.png")

	plt.savefig(filename, box_inches="tight")

	plt.close()

if __name__ == "__main__":

	dataset = "boston"

	hm_depths = [10*i for i in range(1, 10)]

	hm_widths = [4, 16, 64, 256]

	heat_maps(dataset, hm_depths, hm_widths)

	lc_depths = [10, 30, 50, 70, 90]

	lc_widths = [4, 16, 64, 256]

	for d in lc_depths:

		for w in lc_widths:

			learning_curves(dataset, d, w)

	print("Done!")

 No newline at end of file