def picture_prosess(features, targeted_column, classifier):
"""
Calls upon data.diabetes_dataset() and fitting.fit() to predict and calculate
accuracy to be displayed on the web-page. Visualize.visualizer() will also be
called if only two checkboxes are checked.
The scatterplots are saved in buffers to avoid problems with matplotlib, flask,
and python. There has been some problems occurring testing (Mac) with all
the latest updates to the packages. Without the buffers the scatterplots would not
be updated in real time when checking new checkboxes without having to restart
the page. Since the scatterplots should only be displayed when 2 checkboxes are
marked, the whole buffer and scatter-plot action is inside an if-statement.
args:
features (list:String): list containing names of features(columns)
targeted_column (String): name of column
classifier (String): name of classifier
returns:
t_ac (float):
v_ac (float):
img1 (string): scatter plot object 1
img2 (string): scatter plot object 2
"""
data_frame, training_set, validation_set = data.diabetes_dataset()
trained_classifier = fitting.fit(training_set, classifier, features, targeted_column)
img1 = None
img2 = None
prediction1 = trained_classifier.predict(training_set[features])
t_ac = metrics.accuracy_score(training_set[targeted_column], prediction1)
prediction2 = trained_classifier.predict(validation_set[features])
v_ac = metrics.accuracy_score(validation_set[targeted_column], prediction2)
if(len(features) == 2):
buf = BytesIO()
#add to buffer
(visualize.visualizer(prediction1, training_set, features)).savefig(buf, format="png")
img1 = base64.b64encode(buf.getbuffer()).decode("ascii")
buf = BytesIO()
#add to buffer
(visualize.visualizer(prediction2, validation_set, features)).savefig(buf, format="png")
img2 = base64.b64encode(buf.getbuffer()).decode("ascii")
return t_ac, v_ac, img1, img2
plt.figure(figsize=(10,7))
sn.heatmap(df.corr(),annot=True,cmap = 'Blues',vmin=-1,vmax=1,center=0,linewidths=2, linecolor='black')
plt.xticks(fontsize=15,rotation=90)
plt.yticks(fontsize=15,rotation=0)
plt.title('Correlation HeatMap')
#plt.show()
# Instead of plt.show(), do the following:
viz = visualizer()
viz.jumbocard('Jumbocard Heading', plt,'My Description: This is An Important Graph')
df.groupby(['Target']).mean()
df.groupby(['Target']).median()
formatter_class=argparse.RawTextHelpFormatter,
)
parser.add_argument("--vis", help="Will display the tree", dest='vis')
parser.add_argument(
"--get",
help="Will get a desired component from a desired person",
choices=['siblings', 'parents', 'spouse', 'children', 'cousins'],
dest='get')
t = text_reader('stark_family_tree.txt')
args = parser.parse_args()
if args.vis:
visualizer('stark_family_tree.txt')
if args.get == "parents":
ans = input("Whose Parents would you like to find? ")
while t.findPerson(ans) is None:
ans = input("That person isn't in the tree, sorry. Try again: ")
if t.getParents(ans) is None:
print(ans, "has no parents in the tree.")
else:
print("The parents of ", ans, "are: ")
print(", ".join(t.getParents(ans)))
if args.get == "siblings":
ans = input("Whose siblings would you like to find? ")
while t.findPerson(ans) is None:
ans = input("That person isn't in the tree, sorry. Try agian: ")
def play_game(self):
shaker = sh.Shaker()
shake_switch = False
shake_ended = False
vis = visualizer()
cap = cv2.VideoCapture(0)
frame_cnt = 0
if self.save_video:
fourcc = cv2.VideoWriter_fourcc(*'XVID')
out = cv2.VideoWriter(
self.out_dir + "webcam_out.avi",\
fourcc, round(cap.get(5)), \
frame_size)
out_mask = cv2.VideoWriter(
self.out_dir + "webcam_out_mask.avi",\
fourcc, round(cap.get(5)), \
frame_size)
decision_cnt = 0
finger_cnt = 0
rps = 'r'
while cap.isOpened():
ret, frame = cap.read()
frame_cnt += 1
if ret is False:
break
frame = cv2.resize(frame, frame_size)
#frame = cv2.flip(frame, 0)
#frame = cv2.flip(frame, 1)
mask = sd.detect_skin(frame)
if self.save_video:
out.write(cv2.cvtColor(mask,\
cv2.COLOR_GRAY2BGR))
if shake_ended is True:
if shake_switch is False:
print('shake ended')
shake_switch = True
img1, img2 = shaker.get_minmax_image()
cv2.imwrite(self.out_dir + 'webcam_max.jpg', img1)
cv2.imwrite(self.out_dir + 'webcam_min.jpg', img2)
scc = SkinColorClassifier(img1, img2)
mask = scc.mask_image(frame)
mask = sd.morphological_transform(mask)
cv2.imshow('scc mask',mask)
frame, finger_cnt = count_finger(frame, mask)
print(finger_cnt)
else:
mask = sd.detect_skin(frame)
decision_cnt += 1
if shake_switch is False:
shake_ended = shaker.shake_detect(mask, frame)
#out.write(frame)
out_mask.write(cv2.cvtColor(mask, cv2.COLOR_GRAY2BGR))
frame = vis.visualize(frame, finger_cnt, decision_cnt, True)
cv2.imshow('frame', frame)
k = cv2.waitKey(5) & 0xFF
if k == 27:
break
if self.save_video:
out.release()
out_mask.release()
plt.plot(shaker.yhistory)
plt.ylabel('avg y')
plt.plot(shaker.smoothed)
plt.ylabel('smoothed')
plt.savefig(self.out_dir + "webcam_plot.png")
plt.clf()
cap.release()
cv2.destroyAllWindows()
if shake_switch:
return 1
else:
return 0
def play_game(self):
shaker = sh.Shaker()
shake_switch = False
shake_ended = False
vis = visualizer()
cap = cv2.VideoCapture(self.in_dir + self.video_name)
frame_cnt = 0
f = open(self.out_dir + self.report_name, 'a')
f.write(self.video_name + ": ")
pure_video_name = self.video_name.replace('.MOV', '')
if self.save_video:
fourcc = cv2.VideoWriter_fourcc(*'XVID')
out = cv2.VideoWriter(
self.out_dir + pure_video_name + "out.avi",\
fourcc, round(cap.get(5)), \
frame_size)
avg = 0
decision_cnt = 0
finger_cnt = 0
rps = 'r'
while cap.isOpened():
ret, frame = cap.read()
frame_cnt += 1
if ret is False:
break
frame = cv2.resize(frame, frame_size)
frame = cv2.flip(frame, 0)
frame = cv2.flip(frame, 1)
mask = sd.detect_skin(frame)
#cv2.imshow('mask', mask)
if self.save_video:
out.write(cv2.cvtColor(mask,\
cv2.COLOR_GRAY2BGR))
if shake_ended is True:
if shake_switch is False:
print('shake ended')
#time.sleep(2)
shake_switch = True
img1, img2 = shaker.get_minmax_image()
#cv2.imwrite(self.out_dir + pure_video_name + '_max.jpg', img1)
#cv2.imwrite(self.out_dir + pure_video_name + '_min.jpg', img2)
#f.write(str(frame_cnt))
#mask = scc.mask_image(frame)
mask = sd.morphological_transform(mask)
frame, finger_cnt = count_finger(frame, mask)
print(finger_cnt)
else:
mask = sd.detect_skin(frame)
decision_cnt += 1
if shake_switch is False:
shake_ended = shaker.shake_detect(mask, frame)
frame = vis.visualize(frame, finger_cnt, decision_cnt)
cv2.imshow('frame', frame)
k = cv2.waitKey(5) & 0xFF
if k == 27:
break
time.sleep(2)
f.write('\n')
f.close()
if self.save_video:
out.release()
plt.plot(shaker.yhistory)
plt.ylabel('avg y')
plt.plot(shaker.smoothed)
plt.ylabel('smoothed')
plt.savefig(self.out_dir + pure_video_name + "_plot.png")
plt.clf()
cap.release()
cv2.destroyAllWindows()
if shake_switch:
return 1
else:
return 0
import visualize
emotion_array = visualize.visualizer()
emotion_array = np.array(emotion_array)
emotion_array = (emotion_array / sum(emotion_array)) * 100
plt.rcParams['figure.figsize'] = (13.5, 5.5)
for i in range(len(emotion_array)):
axes = plt.subplot(2, 4, i)
emojis_img = io.imread('images/emojis/%s.png' % str(class_names[i]))
plt.imshow(emojis_img)
plt.xlabel(str(emotion_array(i)), fontsize=16)
axes.set_xticks([])
axes.set_yticks([])
plt.tight_layout()
plt.savefig(os.path.join('images/results/{}.png'.format(i + 1)))
plt.close()
self.tiles.append(x)
self.board_map[self.numbers[0]].append(x)
self.numbers = self.numbers[1:]
x = tile("Wood", self.numbers[0], '#006600')
self.tiles.append(x)
self.board_map[self.numbers[0]].append(x)
self.numbers = self.numbers[1:]
x = tile("Sheep", self.numbers[0], '#99ff33')
self.tiles.append(x)
self.board_map[self.numbers[0]].append(x)
self.numbers = self.numbers[1:]
x = tile("Wheat", self.numbers[0], '#cccc00')
self.tiles.append(x)
self.board_map[self.numbers[0]].append(x)
self.numbers = self.numbers[1:]
self.tiles.append(tile("Desert", 0, '#999966'))
shuffle(self.tiles)
board = board()
view = visualizer()
board = view.visualize_board(board, x, y)
# view.draw_settlement(board.vertices[0].coord, '#ff0000')
# view.draw_road(board.vertices[0].coord, board.vertices[1].coord, '#ff0000')
GREEN = (0, 255, 0)
THICKNESS = 3
if __name__ == '__main__':
import cv2
import data
from visualize import visualizer, cv2Window
from detect import detectMultiscale
def predictionCallback(img):
start = timer()
detections = detectMultiscale(img)
if PROFILE:
print('Prediction took %fs' % (timer() - start,))
for (xMin, yMin, xMax, yMax) in detections:
cv2.rectangle(img, (xMin, yMin), (xMax, yMax), GREEN, THICKNESS)
if TEST:
visualizer(data.getTestImagePaths(), predictionCallback, WINDOW_TITLE)
elif TRAIN:
from train import train
train(STAGE_IDX, TRAIN_CALIB)
elif LIVE:
from RealSense import Streamer, LiveDisplay
with cv2Window(LIVE_WINDOW_TITLE) as win, Streamer() as stream:
liveStream = LiveDisplay(stream, win)
liveStream.run(predictionCallback)
def play_game(self):
shaker = sh.DiffShaker()
scc = None
shake_switch = False
shake_ended = False
cnt_list = []
vis = visualizer()
cap = cv2.VideoCapture(self.in_dir + self.video_name)
print(self.in_dir + self.video_name)
frame_cnt = 0
f = open(self.out_dir + self.report_name, 'a')
f.write(self.video_name + ": ")
pure_video_name = self.video_name.replace('.MOV', '')
decision_cnt = 0
finger_cnt = 0
if self.save_video:
fourcc = cv2.VideoWriter_fourcc(*'XVID')
out = cv2.VideoWriter(
self.out_dir + pure_video_name + "out.avi",\
fourcc, round(cap.get(5)), \
frame_size)
ret, prev_frame = cap.read()
prev_frame = render_frame(prev_frame)
while cap.isOpened():
ret, curr_frame = cap.read()
frame_cnt += 1
if ret is False:
break
curr_frame = render_frame(curr_frame)
if shake_ended is True:
if shake_switch is False:
# only started once
print('shake ended')
#time.sleep(2)
shake_switch = True
img1, img2 = shaker.get_minmax_image()
cv2.imwrite(self.out_dir + pure_video_name + '_max.jpg',
img1)
cv2.imwrite(self.out_dir + pure_video_name + '_min.jpg',
img2)
f.write(str(frame_cnt))
scc = SkinColorClassifier(img1, img2)
start_time = time.time()
mask = scc.mask_image(curr_frame)
curr_frame, finger_cnt = count_finger(curr_frame, mask)
print(time.time() - start_time)
else:
mask = sd.detect_skin(curr_frame)
decision_cnt += 1
if shake_switch is False:
mask, shake_ended = \
shaker.shake_detect(prev_frame, curr_frame)
cv2.imshow('mask', mask)
if self.save_video:
out.write(cv2.cvtColor(mask,\
cv2.COLOR_GRAY2BGR))
prev_frame = curr_frame
curr_frame = vis.visualize(curr_frame, finger_cnt, decision_cnt)
cv2.imshow('frame', curr_frame)
k = cv2.waitKey(5) & 0xFF
if k == 27:
break
f.write('\n')
f.close()
if self.save_video:
out.release()
plt.plot(shaker.yhistory)
plt.ylabel('avg y')
plt.plot(shaker.smoothed)
plt.ylabel('smoothed')
plt.savefig(self.out_dir + pure_video_name + "_plot.png")
plt.clf()
plt.plot(cnt_list)
plt.savefig(self.out_dir + pure_video_name + \
"_finger_plot.png")
plt.clf()
cap.release()
cv2.destroyAllWindows()
return cnt_list