def _run(input_file_name, output_dir_name):
"""Plots mean example created by average_examples.py.
This is effectively the main method.
:param input_file_name: See documentation at top of file.
:param output_dir_name: Same.
"""
file_system_utils.mkdir_recursive_if_necessary(
directory_name=output_dir_name)
pickle_file_handle = open(input_file_name, 'rb')
mean_example_dict = pickle.load(pickle_file_handle)
pickle_file_handle.close()
# Plot predictors with liquid-water content (LWC).
figure_object = profile_plotting.plot_predictors(
example_dict=mean_example_dict,
example_index=0,
plot_ice=False,
use_log_scale=True)[0]
panel_file_names = ['foo'] * 3
panel_file_names[0] = '{0:s}/predictors_with_lwc.jpg'.format(
output_dir_name)
print('Saving figure to: "{0:s}"...'.format(panel_file_names[0]))
figure_object.savefig(panel_file_names[0],
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close(figure_object)
# Plot predictors with ice-water content (IWC).
figure_object = profile_plotting.plot_predictors(
example_dict=mean_example_dict,
example_index=0,
plot_ice=True,
use_log_scale=True)[0]
panel_file_names[1] = '{0:s}/predictors_with_iwc.jpg'.format(
output_dir_name)
print('Saving figure to: "{0:s}"...'.format(panel_file_names[1]))
figure_object.savefig(panel_file_names[1],
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close(figure_object)
# Plot targets.
figure_object = profile_plotting.plot_targets(
example_dict=mean_example_dict, example_index=0, use_log_scale=True)[0]
panel_file_names[2] = '{0:s}/targets.jpg'.format(output_dir_name)
print('Saving figure to: "{0:s}"...'.format(panel_file_names[2]))
figure_object.savefig(panel_file_names[2],
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close(figure_object)
# Concatenate panels.
concat_figure_file_name = '{0:s}/predictors_and_targets.jpg'.format(
output_dir_name)
print(
'Concatenating panels to: "{0:s}"...'.format(concat_figure_file_name))
imagemagick_utils.concatenate_images(
input_file_names=panel_file_names,
output_file_name=concat_figure_file_name,
num_panel_rows=2,
num_panel_columns=2,
border_width_pixels=50)
imagemagick_utils.resize_image(input_file_name=concat_figure_file_name,
output_file_name=concat_figure_file_name,
output_size_pixels=CONCAT_FIGURE_SIZE_PX)
def _plot_results_one_example(bwo_dict, example_index, model_metadata_dict,
use_log_scale, output_dir_name):
"""Plots results for one example.
:param bwo_dict: Dictionary read by
`backwards_optimization.read_file`.
:param example_index: Will plot results for example with this array index.
:param model_metadata_dict: Dictionary read by `neural_net.read_metafile`.
:param use_log_scale: See documentation at top of file.
:param output_dir_name: Name of output directory. Figure will be saved
here.
"""
# Housekeeping.
example_id_string = bwo_dict[bwo.EXAMPLE_IDS_KEY][example_index]
generator_option_dict = model_metadata_dict[
neural_net.TRAINING_OPTIONS_KEY]
base_example_dict = {
example_utils.SCALAR_PREDICTOR_NAMES_KEY:
generator_option_dict[neural_net.SCALAR_PREDICTOR_NAMES_KEY],
example_utils.VECTOR_PREDICTOR_NAMES_KEY:
generator_option_dict[neural_net.VECTOR_PREDICTOR_NAMES_KEY],
example_utils.HEIGHTS_KEY:
generator_option_dict[neural_net.HEIGHTS_KEY]
}
init_example_dict = copy.deepcopy(base_example_dict)
init_example_dict[example_utils.SCALAR_PREDICTOR_VALS_KEY] = (
bwo_dict[bwo.INIT_SCALAR_PREDICTORS_KEY][[example_index], ...])
init_example_dict[example_utils.VECTOR_PREDICTOR_VALS_KEY] = (
bwo_dict[bwo.INIT_VECTOR_PREDICTORS_KEY][[example_index], ...])
final_example_dict = copy.deepcopy(base_example_dict)
final_example_dict[example_utils.SCALAR_PREDICTOR_VALS_KEY] = (
bwo_dict[bwo.FINAL_SCALAR_PREDICTORS_KEY][[example_index], ...])
final_example_dict[example_utils.VECTOR_PREDICTOR_VALS_KEY] = (
bwo_dict[bwo.FINAL_VECTOR_PREDICTORS_KEY][[example_index], ...])
diff_example_dict = copy.deepcopy(base_example_dict)
diff_example_dict[example_utils.SCALAR_PREDICTOR_VALS_KEY] = (
final_example_dict[example_utils.SCALAR_PREDICTOR_VALS_KEY] -
init_example_dict[example_utils.SCALAR_PREDICTOR_VALS_KEY])
diff_example_dict[example_utils.VECTOR_PREDICTOR_VALS_KEY] = (
final_example_dict[example_utils.VECTOR_PREDICTOR_VALS_KEY] -
init_example_dict[example_utils.VECTOR_PREDICTOR_VALS_KEY])
predictor_names = (
diff_example_dict[example_utils.VECTOR_PREDICTOR_NAMES_KEY])
if example_utils.TEMPERATURE_NAME in predictor_names:
temperature_index = predictor_names.index(
example_utils.TEMPERATURE_NAME)
diff_predictor_matrix = (
diff_example_dict[example_utils.VECTOR_PREDICTOR_VALS_KEY])
diff_predictor_matrix[..., temperature_index] = (
temperature_conv.celsius_to_kelvins(
diff_predictor_matrix[..., temperature_index]))
diff_example_dict[example_utils.VECTOR_PREDICTOR_VALS_KEY] = (
diff_predictor_matrix)
num_predictor_sets = len(PREDICTOR_NAMES_BY_SET)
for k in range(num_predictor_sets):
these_flags = numpy.array([
n in base_example_dict[example_utils.VECTOR_PREDICTOR_NAMES_KEY]
for n in PREDICTOR_NAMES_BY_SET[k]
],
dtype=bool)
these_indices = numpy.where(these_flags)[0]
if len(these_indices) == 0:
continue
predictor_names = [PREDICTOR_NAMES_BY_SET[k][i] for i in these_indices]
predictor_colours = [
PREDICTOR_COLOURS_BY_SET[k][i] for i in these_indices
]
# Plot initial and final values on the same set of axes.
handle_dict = profile_plotting.plot_predictors(
example_dict=init_example_dict,
example_index=0,
predictor_names=predictor_names,
predictor_colours=predictor_colours,
predictor_line_widths=numpy.full(len(these_indices),
SOLID_LINE_WIDTH),
predictor_line_styles=['solid'] * len(these_indices),
use_log_scale=use_log_scale,
handle_dict=None)
profile_plotting.plot_predictors(
example_dict=final_example_dict,
example_index=0,
predictor_names=predictor_names,
predictor_colours=predictor_colours,
predictor_line_widths=numpy.full(len(these_indices),
DASHED_LINE_WIDTH),
predictor_line_styles=['dashed'] * len(these_indices),
use_log_scale=use_log_scale,
handle_dict=handle_dict)
output_file_name = '{0:s}/{1:s}_predictor-set-{2:d}.jpg'.format(
output_dir_name, example_id_string.replace('_', '-'), k)
figure_object = handle_dict[profile_plotting.FIGURE_HANDLE_KEY]
print('Saving figure to: "{0:s}"...'.format(output_file_name))
figure_object.savefig(output_file_name,
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close(figure_object)
# Plot differences (final minus initial).
handle_dict = profile_plotting.plot_predictors(
example_dict=diff_example_dict,
example_index=0,
predictor_names=predictor_names,
predictor_colours=predictor_colours,
predictor_line_widths=numpy.full(len(these_indices),
SOLID_LINE_WIDTH),
predictor_line_styles=['solid'] * len(these_indices),
use_log_scale=use_log_scale,
handle_dict=None)
output_file_name = '{0:s}/{1:s}_predictor-set-{2:d}_diffs.jpg'.format(
output_dir_name, example_id_string.replace('_', '-'), k)
figure_object = handle_dict[profile_plotting.FIGURE_HANDLE_KEY]
print('Saving figure to: "{0:s}"...'.format(output_file_name))
figure_object.savefig(output_file_name,
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close(figure_object)
def _plot_one_example(example_dict, example_index, use_log_scale,
output_dir_name):
"""Plots data for one example.
:param example_dict: See doc for `example_io.read_file`.
:param example_index: Will plot results for example with this array index.
:param use_log_scale: See documentation at top of file.
:param output_dir_name: Name of output directory. Figures will be saved
here.
"""
example_id_string = (
example_dict[example_utils.EXAMPLE_IDS_KEY][example_index])
num_predictor_sets = len(PREDICTOR_NAMES_BY_SET)
for k in range(num_predictor_sets):
these_flags = numpy.array([
n in example_dict[example_utils.VECTOR_PREDICTOR_NAMES_KEY]
for n in PREDICTOR_NAMES_BY_SET[k]
],
dtype=bool)
these_indices = numpy.where(these_flags)[0]
if len(these_indices) == 0:
continue
predictor_names = [PREDICTOR_NAMES_BY_SET[k][i] for i in these_indices]
predictor_colours = [
PREDICTOR_COLOURS_BY_SET[k][i] for i in these_indices
]
handle_dict = profile_plotting.plot_predictors(
example_dict=example_dict,
example_index=example_index,
predictor_names=predictor_names,
predictor_colours=predictor_colours,
predictor_line_widths=numpy.full(len(these_indices), LINE_WIDTH),
predictor_line_styles=['solid'] * len(these_indices),
use_log_scale=use_log_scale)
output_file_name = '{0:s}/{1:s}_predictor-set-{2:d}.jpg'.format(
output_dir_name, example_id_string.replace('_', '-'), k)
figure_object = handle_dict[profile_plotting.FIGURE_HANDLE_KEY]
print('Saving figure to: "{0:s}"...'.format(output_file_name))
figure_object.savefig(output_file_name,
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close(figure_object)
handle_dict = profile_plotting.plot_targets(example_dict=example_dict,
example_index=example_index,
use_log_scale=use_log_scale,
line_width=LINE_WIDTH,
line_style='solid')
output_file_name = '{0:s}/{1:s}_targets.jpg'.format(
output_dir_name, example_id_string.replace('_', '-'))
figure_object = handle_dict[profile_plotting.FIGURE_HANDLE_KEY]
print('Saving figure to: "{0:s}"...'.format(output_file_name))
figure_object.savefig(output_file_name,
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close(figure_object)
def _plot_saliency_one_example(saliency_dict, example_index,
model_metadata_dict, use_log_scale,
legend_suffix, output_dir_name):
"""Plots saliency map for one example.
:param saliency_dict: Dictionary read by `saliency.read_file`.
:param example_index: Will plot saliency map for example with this array
index.
:param model_metadata_dict: Dictionary read by `neural_net.read_metafile`.
:param use_log_scale: See documentation at top of file.
:param legend_suffix: End of figure legend.
:param output_dir_name: Name of output directory. Figure will be saved
here.
"""
# Housekeeping.
example_id_string = saliency_dict[saliency.EXAMPLE_IDS_KEY][example_index]
generator_option_dict = model_metadata_dict[
neural_net.TRAINING_OPTIONS_KEY]
example_dict = {
example_utils.SCALAR_PREDICTOR_NAMES_KEY:
generator_option_dict[neural_net.SCALAR_PREDICTOR_NAMES_KEY],
example_utils.VECTOR_PREDICTOR_NAMES_KEY:
generator_option_dict[neural_net.VECTOR_PREDICTOR_NAMES_KEY],
example_utils.HEIGHTS_KEY:
generator_option_dict[neural_net.HEIGHTS_KEY],
example_utils.SCALAR_PREDICTOR_VALS_KEY:
saliency_dict[saliency.SCALAR_SALIENCY_KEY][[example_index], ...],
example_utils.VECTOR_PREDICTOR_VALS_KEY:
saliency_dict[saliency.VECTOR_SALIENCY_KEY][[example_index], ...]
}
scalar_predictor_names = (
example_dict[example_utils.SCALAR_PREDICTOR_NAMES_KEY])
scalar_saliency_matrix = saliency_dict[saliency.SCALAR_SALIENCY_KEY]
num_scalar_dim = len(scalar_saliency_matrix.shape) - 1
num_scalar_predictors = len(scalar_predictor_names)
legend_string = ''
if num_scalar_dim == 1:
for k in range(num_scalar_predictors):
if k > 0:
legend_string += '\n'
legend_string += '{0:s}: {1:.2f}'.format(
PREDICTOR_NAME_TO_VERBOSE[scalar_predictor_names[k]],
scalar_saliency_matrix[0, k])
if legend_suffix != '':
legend_string += '\n' + legend_suffix
else:
legend_string = legend_suffix
num_predictor_sets = len(VECTOR_PREDICTOR_NAMES_BY_SET)
for k in range(num_predictor_sets):
these_flags = numpy.array([
n in example_dict[example_utils.VECTOR_PREDICTOR_NAMES_KEY]
for n in VECTOR_PREDICTOR_NAMES_BY_SET[k]
],
dtype=bool)
these_indices = numpy.where(these_flags)[0]
if len(these_indices) == 0:
continue
predictor_names = [
VECTOR_PREDICTOR_NAMES_BY_SET[k][i] for i in these_indices
]
predictor_colours = [
VECTOR_PREDICTOR_COLOURS_BY_SET[k][i] for i in these_indices
]
handle_dict = profile_plotting.plot_predictors(
example_dict=example_dict,
example_index=0,
predictor_names=predictor_names,
predictor_colours=predictor_colours,
predictor_line_widths=numpy.full(len(these_indices), 2),
predictor_line_styles=['solid'] * len(these_indices),
use_log_scale=use_log_scale,
include_units=False,
handle_dict=None)
axes_object = handle_dict[profile_plotting.AXES_OBJECTS_KEY][0]
if legend_string != '':
axes_object.text(0.01,
0.99,
legend_string,
fontsize=LEGEND_FONT_SIZE,
color='k',
bbox=LEGEND_BOUNDING_BOX_DICT,
horizontalalignment='left',
verticalalignment='top',
transform=axes_object.transAxes,
zorder=1e10)
output_file_name = '{0:s}/{1:s}_vector-predictor-set-{2:d}.jpg'.format(
output_dir_name, example_id_string.replace('_', '-'), k)
figure_object = handle_dict[profile_plotting.FIGURE_HANDLE_KEY]
print('Saving figure to: "{0:s}"...'.format(output_file_name))
figure_object.savefig(output_file_name,
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close(figure_object)
if num_scalar_dim == 1:
return
num_predictor_sets = len(SCALAR_PREDICTOR_NAMES_BY_SET)
for k in range(num_predictor_sets):
these_flags = numpy.array([
n in example_dict[example_utils.SCALAR_PREDICTOR_NAMES_KEY]
for n in SCALAR_PREDICTOR_NAMES_BY_SET[k]
],
dtype=bool)
these_indices = numpy.where(these_flags)[0]
if len(these_indices) == 0:
continue
predictor_names = [
SCALAR_PREDICTOR_NAMES_BY_SET[k][i] for i in these_indices
]
predictor_colours = [
SCALAR_PREDICTOR_COLOURS_BY_SET[k][i] for i in these_indices
]
handle_dict = profile_plotting.plot_predictors(
example_dict=example_dict,
example_index=0,
predictor_names=predictor_names,
predictor_colours=predictor_colours,
predictor_line_widths=numpy.full(len(these_indices), 2),
predictor_line_styles=['solid'] * len(these_indices),
use_log_scale=use_log_scale,
include_units=False,
handle_dict=None)
output_file_name = '{0:s}/{1:s}_scalar-predictor-set-{2:d}.jpg'.format(
output_dir_name, example_id_string.replace('_', '-'), k)
figure_object = handle_dict[profile_plotting.FIGURE_HANDLE_KEY]
print('Saving figure to: "{0:s}"...'.format(output_file_name))
figure_object.savefig(output_file_name,
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close(figure_object)
def _do_plotting(example_dict, example_index, output_dir_name):
"""Does the plotting.
:param example_dict: See doc for `example_io.read_file`.
:param example_index: Will plot predictors and targets for [k]th example in
dictionary, where k = `example_index`.
:param output_dir_name: Name of output directory. Figures will be saved
here.
"""
example_id_string = (
example_dict[example_utils.EXAMPLE_IDS_KEY][example_index])
num_predictor_sets = len(PREDICTOR_NAMES_BY_SET)
letter_label = None
panel_file_names = []
for k in range(num_predictor_sets):
these_flags = numpy.array([
n in example_dict[example_utils.VECTOR_PREDICTOR_NAMES_KEY]
for n in PREDICTOR_NAMES_BY_SET[k]
],
dtype=bool)
these_indices = numpy.where(these_flags)[0]
if len(these_indices) == 0:
continue
predictor_names = [PREDICTOR_NAMES_BY_SET[k][i] for i in these_indices]
predictor_colours = [
PREDICTOR_COLOURS_BY_SET[k][i] for i in these_indices
]
handle_dict = profile_plotting.plot_predictors(
example_dict=example_dict,
example_index=example_index,
predictor_names=predictor_names,
predictor_colours=predictor_colours,
predictor_line_widths=numpy.full(len(these_indices), LINE_WIDTH),
predictor_line_styles=['solid'] * len(these_indices),
use_log_scale=True)
if letter_label is None:
letter_label = 'a'
else:
letter_label = chr(ord(letter_label) + 1)
plotting_utils.label_axes(
axes_object=handle_dict[profile_plotting.AXES_OBJECTS_KEY][0],
label_string='({0:s})'.format(letter_label),
font_size=LETTER_LABEL_FONT_SIZE,
x_coord_normalized=LETTER_LABEL_X_COORD,
y_coord_normalized=LETTER_LABEL_Y_COORD)
this_file_name = '{0:s}/{1:s}_predictor-set-{2:d}.jpg'.format(
output_dir_name, example_id_string.replace('_', '-'), k)
panel_file_names.append(this_file_name)
print('Saving figure to: "{0:s}"...'.format(this_file_name))
figure_object = handle_dict[profile_plotting.FIGURE_HANDLE_KEY]
figure_object.savefig(this_file_name,
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close(figure_object)
imagemagick_utils.trim_whitespace(input_file_name=this_file_name,
output_file_name=this_file_name)
imagemagick_utils.resize_image(input_file_name=this_file_name,
output_file_name=this_file_name,
output_size_pixels=int(2.5e6))
handle_dict = profile_plotting.plot_targets(example_dict=example_dict,
example_index=example_index,
use_log_scale=True,
line_width=LINE_WIDTH,
line_style='solid')
letter_label = chr(ord(letter_label) + 1)
plotting_utils.label_axes(
axes_object=handle_dict[profile_plotting.HEATING_RATE_HANDLE_KEY],
label_string='({0:s})'.format(letter_label),
font_size=LETTER_LABEL_FONT_SIZE,
x_coord_normalized=LETTER_LABEL_X_COORD,
y_coord_normalized=LETTER_LABEL_Y_COORD)
this_file_name = '{0:s}/{1:s}_targets.jpg'.format(
output_dir_name, example_id_string.replace('_', '-'))
panel_file_names.append(this_file_name)
print('Saving figure to: "{0:s}"...'.format(this_file_name))
figure_object = handle_dict[profile_plotting.FIGURE_HANDLE_KEY]
figure_object.savefig(this_file_name,
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close(figure_object)
imagemagick_utils.trim_whitespace(input_file_name=this_file_name,
output_file_name=this_file_name)
imagemagick_utils.resize_image(input_file_name=this_file_name,
output_file_name=this_file_name,
output_size_pixels=int(2.5e6))
concat_file_name = '{0:s}/{1:s}_concat.jpg'.format(
output_dir_name, example_id_string.replace('_', '-'))
print('Concatenating panels to: "{0:s}"...'.format(concat_file_name))
imagemagick_utils.concatenate_images(input_file_names=panel_file_names,
output_file_name=concat_file_name,
num_panel_rows=2,
num_panel_columns=2,
border_width_pixels=25)
imagemagick_utils.trim_whitespace(input_file_name=concat_file_name,
output_file_name=concat_file_name)