def copy_files_to_label_dirs(inp_path, out_path, labels_file, process = None):
prep_out_path(out_path)
for i in range(0, 5):
os.makedirs(path.join(out_path, str(i)))
labels = pd.read_csv(labels_file)
existing_files = pd.DataFrame([path.splitext(f)[0] for f in os.listdir(inp_path)], columns =[labels.columns[0]])
existing_files = existing_files.merge(labels, on=existing_files.columns[0])
def processAndCopy(inp_file, out_file):
im = cv2.imread(inp_file)
im = process(im)
cv2.imwrite(out_file, im)
if process == None:
cp = copy
else:
cp = processAndCopy
for f, l in zip(existing_files['image'], existing_files['level']):
file_name = path.join(out_path, str(l), f + ".jpeg")
inp_file = path.join(inp_path, f + '.jpeg')
cp(inp_file, file_name)
print "copied {0} to {1}".format(inp_file, file_name)
def copy_files_to_label_dirs(inp_path, out_path, labels_file, process=None):
prep_out_path(out_path)
for i in range(0, 5):
os.makedirs(path.join(out_path, str(i)))
labels = pd.read_csv(labels_file)
existing_files = pd.DataFrame(
[path.splitext(f)[0] for f in os.listdir(inp_path)],
columns=[labels.columns[0]])
existing_files = existing_files.merge(labels, on=existing_files.columns[0])
def processAndCopy(inp_file, out_file):
im = cv2.imread(inp_file)
im = process(im)
cv2.imwrite(out_file, im)
if process == None:
cp = copy
else:
cp = processAndCopy
for f, l in zip(existing_files['image'], existing_files['level']):
file_name = path.join(out_path, str(l), f + ".jpeg")
inp_file = path.join(inp_path, f + '.jpeg')
cp(inp_file, file_name)
print "copied {0} to {1}".format(inp_file, file_name)
def copy_train_files(inp_path, train_path, labels_file):
prep_out_path(train_path)
labels = pd.read_csv(labels_file)
files_names = set(labels[labels.columns[0]].as_matrix())
all_files = set(os.listdir(inp_path))
train_files = all_files.intersection(files_names)
for f in train_files:
copy(path.join(inp_path, f), path.join(train_path, f))
def copy_test_files(inp_path, test_path, labels_file):
prep_out_path(test_path)
labels = pd.read_csv(labels_file)
file_names = set(labels[labels.columns[0]].as_matrix())
all_files = set(os.listdir(inp_path))
test_files = all_files.difference(file_names)
for f in test_files:
copy(path.join(inp_path, f), path.join(test_path, f))
def get_areal_features(root, features_path, masks_dir, n_bins = 100):
prep_out_path(features_path)
files = os.listdir(root)
df = pd.DataFrame(columns = range(n_bins * 2) + ['name', 'level'])
names = pd.read_csv(labels_file)
print "Starting extraction: ", time_now_str()
for j, f in enumerate(files):
label = names.loc[names['image'] == path.splitext(f)[0]]
start = time.time()
imr = ImageReader(root, f, masks_dir, gray_scale = True)
drusen = get_predicted_region(imr.image, Labels.Drusen)
blood = get_predicted_region(imr.image, Labels.Haemorage)
Bc = np.ones((5, 5))
labels_drusen, n_drusen = mh.label(drusen, Bc)
labels_blood, n_blood = mh.label(blood, Bc)
area = float(cv2.countNonZero(imr.mask))
outp = np.array([], dtype = np.int)
# sizes excluding background
sizes_drusen = mhl.labeled_size(labels_drusen)[1:] / area
sizes_blood = mhl.labeled_size(labels_blood)[1:] / area
hist_druzen, _ = np.histogram(sizes_drusen, n_bins, (0, 1e-3))
hist_blood, _ = np.histogram(sizes_blood, n_bins, (0, 1e-3))
outp = np.r_[outp, hist_druzen]
outp = np.r_[outp, hist_blood]
outp = np.r_[outp, label.values[0]]
df.loc[j] = outp
print "Extracted: {0}, took {1:02.2f} sec ".format(f, time.time() - start)
# write out the csv
df.to_csv(path.join(features_path, prefix + ".csv"), index = False, header=True)
print "Extracted: ", prefix, "@", time_now_str()
def copy_files_to_label_dirs(inp_path, out_path, labels_file):
prep_out_path(out_path)
labels = pd.read_csv(labels_file)
splitter = labels.columns[1]
dirs = np.unique(labels[splitter].as_matrix())
for dir in dirs:
p = path.join(out_path, dir)
os.makedirs(p)
bad = []
for f, l in zip(labels[labels.columns[0]], labels[labels.columns[1]]):
file_name = path.join(out_path, l, f)
inp_file = path.join(inp_path, f)
try:
shutil.copy(inp_file, file_name)
except IOError:
print "Cannot copy: {0}".format(f)
bad += [f]
continue
print "copied {0} to {1}".format(inp_file, file_name)
print bad
from kobra.tr_utils import prep_out_path, time_now_str
import os
from os import path
import mahotas as mh
import mahotas.labeled as mhl
import cv2
import time
preprocessed = '/kaggle/retina/train/labelled'
masks = '/kaggle/retina/train/masks'
orig = '/kaggle/retina/train/sample/split'
output = '/kaggle/retina/train/sample/features'
n_bins = 100
prep_out_path(output)
for i in range(0, 5):
prefix = str(i)
print "Starting extraction @ ", time_now_str()
files = os.listdir(path.join(preprocessed, prefix))
# intermediate output will be stored here
# we will save all the files first then join them into one csv file
df = pd.DataFrame(columns = range(n_bins * 2 + 1))
j = 0
for f in files:
start = time.time()
cv2.imwrite(out_im_name, toSave)
return out_im_name
def resize_only(image_name):
image = cv2.imread(image_name)
out_name = path.split(image_name)[1]
out_im_name = path.join(out_path, out_name)
toSave = cv2.resize(image, size)
cv2.imwrite(out_im_name, toSave)
def kmeans_only(image_name, K=10):
out_im_name = get_output_name(image_name)
image = cv2.imread(image_name)
toSave, _, _ = kmeans(image, K)
cv2.imwrite(out_im_name, toSave)
prep_out_path(out_path)
dv = Client().load_balanced_view()
fs = dv.map(kmeans_only, np.array(image_paths))
print "Started: ", time_now_str()
fs.wait()
print "Finished: ", time_now_str()
from kobra.tr_utils import prep_out_path, time_now_str
import os
from os import path
import mahotas as mh
import mahotas.labeled as mhl
import cv2
import time
preprocessed = '/kaggle/retina/train/labelled'
masks = '/kaggle/retina/train/masks'
orig = '/kaggle/retina/train/sample/split'
output = '/kaggle/retina/train/sample/features'
n_bins = 100
prep_out_path(output)
for i in range(0, 5):
prefix = str(i)
print "Starting extraction @ ", time_now_str()
files = os.listdir(path.join(preprocessed, prefix))
# intermediate output will be stored here
# we will save all the files first then join them into one csv file
df = pd.DataFrame(columns=range(n_bins * 2 + 1))
j = 0
for f in files:
start = time.time()
