def __plot_signals(self, signals, output_test, output_training,
channel_labels, distance):
"""
Args:
signals:
channel_labels:
Returns:
object:
"""
colors = list(CSS4_COLORS.keys())
i = 0
fig = plt.figure(figsize=(40, 40))
print(f"Distance Between Signals {distance}")
ax = fig.add_subplot(4, 4, i + 1)
i += 1
color_index = 0
ax.set_title("Interpreted Signal with Output Class " +
str(output_test))
for channel, label in zip(signals[0], channel_labels):
ax.plot(channel, color=colors[color_index + 20], label=label)
color_index += 1
plt.legend()
ax = fig.add_subplot(4, 4, i + 1)
i += 1
color_index = 0
ax.set_title("Example Signal with Output Class " +
str(output_training))
for channel, label in zip(signals[1], channel_labels):
ax.plot(channel, color=colors[color_index + 20], label=label)
color_index += 1
plt.legend()
plt.show()
return plt
def __plot_signals(self, signals, attribution, output_test, output_training, channel_labels):
"""
Args:
signals:
channel_labels:
Returns:
object:
"""
colors = list(CSS4_COLORS.keys())
i = 0
fig = plt.figure(figsize=(40, 40))
ax = fig.add_subplot(4, 4, i + 1)
i += 1
color_index = 0
ax.set_title("Interpreted Signal with Output Class "+str(output_test))
# for channel, label in zip(signals[0], channel_labels):
ax.plot(sum(signals[0]).detach().cpu())
ax.plot(sum(attribution[0]), color="r")
# color_index += 1
# plt.legend()
ax = fig.add_subplot(4, 4, i + 1)
i += 1
color_index = 0
ax.set_title("Example Signal with Output Class "+str(output_training))
# for channel, label in zip(signals[1], channel_labels):
# ax.plot(channel, color=colors[color_index + 20], label=label)
# color_index += 1
ax.plot(sum(signals[1]))
ax.plot(sum(attribution[1]), color="r")
# plt.legend()
plt.show()
return plt
def get_xkcd_palette():
from matplotlib._color_data import XKCD_COLORS as color_dict
return ColorPalette.from_mcd(color_dict.values())
def get_tableau_palette():
from matplotlib._color_data import TABLEAU_COLORS as color_dict
return ColorPalette.from_mcd(color_dict.values())
def get_css4_palette():
from matplotlib._color_data import CSS4_COLORS as color_dict
return ColorPalette.from_mcd(color_dict.values())
draw.line([tuple(prev), tuple(point)], fill=1, width=3)
prev = point
annotation_images.append(np.asarray(annotation_img))
return annotation_images
def load_annotations_as_lists(csv_filename):
df = pd.read_csv(csv_filename)
annotations = get_annotation_points(df, 2, 2)
return annotations
if __name__ == '__main__':
from matplotlib._color_data import CSS4_COLORS
colors = list(CSS4_COLORS.keys())
BORDER_WIDTH = 0.5
WRITE_FOLDER = '../../projects/nuclear/resources/figures/'
if not os.path.exists(WRITE_FOLDER):
os.makedirs(WRITE_FOLDER)
raw_stack_location = f"../../projects/nuclear/resources/images/backup-stacks/{roi}.tiff"
csv_location = f"../../projects/nuclear/resources/csv/processed/{roi}_z{pad(str(Z_SLICE))}.csv"
raw_stack = imread(raw_stack_location)
# 1) raw image
raw_image = raw_stack[Z_SLICE, :, :]
plt.imshow(raw_image, cmap='gray')