def fit(cnf, predict, per_patient, features_file, n_iter, blend_cnf, test_dir):
config = util.load_module(cnf).config
image_files = data.get_image_files(config.get('train_dir'))
names = data.get_names(image_files)
labels = data.get_labels(names).astype(np.float32)[:, np.newaxis]
if features_file is not None:
runs = {'run': [features_file]}
else:
runs = data.parse_blend_config(yaml.load(open(blend_cnf)))
scalers = {run: StandardScaler() for run in runs}
tr, te = data.split_indices(image_files, labels)
y_preds = []
for i in range(n_iter):
print("iteration {} / {}".format(i + 1, n_iter))
for run, files in runs.items():
print("fitting features for run {}".format(run))
X = data.load_features(files)
X = scalers[run].fit_transform(X)
X = data.per_patient_reshape(X) if per_patient else X
est = get_estimator(X.shape[1], image_files, labels,
eval_size=0.0 if predict else 0.1)
est.fit(X, labels)
if not predict:
y_pred = est.predict(X[te]).ravel()
y_preds.append(y_pred)
y_pred = np.mean(y_preds, axis=0)
y_pred = np.clip(np.round(y_pred).astype(int),
np.min(labels), np.max(labels))
print("kappa after run {}, iter {}: {}".format(
run, i, util.kappa(labels[te], y_pred)))
print("confusion matrix")
print(confusion_matrix(labels[te], y_pred))
else:
X = data.load_features(files, test=True)
X = scalers[run].transform(X)
X = data.per_patient_reshape(X) if per_patient else X
y_pred = est.predict(X).ravel()
y_preds.append(y_pred)
if predict:
y_pred = np.mean(y_preds, axis=0)
y_pred = np.clip(np.round(y_pred),
np.min(labels), np.max(labels)).astype(int)
submission_filename = util.get_submission_filename()
image_files = data.get_image_files(test_dir or config.get('test_dir'))
names = data.get_names(image_files)
image_column = pd.Series(names, name='image')
level_column = pd.Series(y_pred, name='level')
predictions = pd.concat([image_column, level_column], axis=1)
print("tail of predictions file")
print(predictions.tail())
predictions.to_csv(submission_filename, index=False)
print("saved predictions to {}".format(submission_filename))
def fit(cnf, predict, per_patient, features_file, n_iter, blend_cnf, test_dir):
config = util.load_module(cnf).config
image_files = data.get_image_files(config.get('train_dir'))
names = data.get_names(image_files)
labels = data.get_labels(names).astype(np.float32)[:, np.newaxis]
if features_file is not None:
runs = {'run': [features_file]}
else:
runs = data.parse_blend_config(yaml.load(open(blend_cnf)))
scalers = {run: StandardScaler() for run in runs}
tr, te = data.split_indices(image_files, labels)
y_preds = []
for i in range(n_iter):
print("iteration {} / {}".format(i + 1, n_iter))
for run, files in list(runs.items()):
print("fitting features for run {}".format(run))
X = data.load_features(files)
X = scalers[run].fit_transform(X)
X = data.per_patient_reshape(X) if per_patient else X
est = get_estimator(X.shape[1], image_files, labels,
eval_size=0.0 if predict else 0.1)
est.fit(X, labels)
if not predict:
y_pred = est.predict(X[te]).ravel()
y_preds.append(y_pred)
y_pred = np.mean(y_preds, axis=0)
y_pred = np.clip(np.round(y_pred).astype(int),
np.min(labels), np.max(labels))
print("kappa after run {}, iter {}: {}".format(
run, i, util.kappa(labels[te], y_pred)))
print("confusion matrix")
print(confusion_matrix(labels[te], y_pred))
else:
X = data.load_features(files, test=True)
X = scalers[run].transform(X)
X = data.per_patient_reshape(X) if per_patient else X
y_pred = est.predict(X).ravel()
y_preds.append(y_pred)
if predict:
y_pred = np.mean(y_preds, axis=0)
y_pred = np.clip(np.round(y_pred),
np.min(labels), np.max(labels)).astype(int)
submission_filename = util.get_submission_filename()
image_files = data.get_image_files(test_dir or config.get('test_dir'))
names = data.get_names(image_files)
image_column = pd.Series(names, name='image')
level_column = pd.Series(y_pred, name='level')
predictions = pd.concat([image_column, level_column], axis=1)
print("tail of predictions file")
print(predictions.tail())
predictions.to_csv(submission_filename, index=False)
print("saved predictions to {}".format(submission_filename))
def process_post(self, post):
"""
Process post received from the message queue.
"""
# is this a post matching one or more persons?
post_add = False
text = data.normalize(post['text']).lower()
self.first_person = None
# check post language
if data.get_text_language(text) == 'fr':
for person in self.persons:
names = data.get_names(person)
if data.check_names(names, text, person['words']) == 1:
# one more post for this person
if not post_add:
post_add = True
# get next post id
post_id = self.db.incr('nextPostId')
# add post to person's posts list
key = 'person:%d:posts:%d' % (person['id'],
self.stats_last_update)
self.db.rpush(key, post_id)
# update stats for this person
self.update_person_stats(person)
if post_add:
# add post to db
self.db.set_post(int(post_id),
json.dumps(post))
# add post id to current hour
key = 'posts:%d' % (self.stats_last_update)
self.db.rpush(key, post_id)
else:
logging.debug('found english word in %s', text)
def main(cnf, weights_from):
config = util.load_module(cnf).config
# print(config)
if weights_from is None:
weights_from = config.weights_file
else:
weights_from = str(weights_from)
print(config.get('train_dir'))
files = data.get_image_files(config.get('train_dir'))
names = data.get_names(files)
labels = data.get_labels(names).astype(np.float32)
print("Checkpoint 5")
net = create_net(config)
print("Checkpoint 6")
print(weights_from)
# print(net.load_params_from())
try:
print("Checkpoint 7")
net.load_params_from(weights_from)
print("Checkpoint 8")
print("loaded weights from {}".format(weights_from))
except IOError:
print("couldn't load weights starting from scratch")
print("fitting ...")
print(files)
print(labels)
net.fit(files, labels)
def main(cnf, weights_from):
config = util.load_module(cnf).config
if weights_from is None:
weights_from = config.weights_file
else:
weights_from = str(weights_from)
files = data.get_image_files(config.get('train_dir'))
names = data.get_names(files)
labels = data.get_labels(names).astype(np.float32)
net = create_net(config)
try:
net.load_params_from(weights_from)
print("loaded weights from {}".format(weights_from))
except IOError:
print("couldn't load weights starting from scratch")
print("Shape of files: " + str(files.shape))
print("Shape of labels: " + str(labels.shape))
start = time.time()
print("fitting ...")
net.fit(files, labels)
end = time.time()
print("Time elapsed for fitting: " + str(end - start))
def main(cnf, classes, weights_from, predict):
config = util.load_module(cnf).config
files = data.get_image_files(config.get('train_dir'))
names = data.get_names(files)
names = [int(x) for x in names ]
data.classes = int(classes)
labels = data.get_labels(names)
net = create_net(config)
print files.shape
print labels.shape
if predict :
if weights_from is None:
weights_from = config.weights_file
else:
weights_from = str(weights_from)
print weights_from
try:
net.load_params_from(weights_from)
print("loaded weights from {}".format(weights_from))
except IOError:
print("couldn't load weights starting from scratch")
if not predict:
print("fitting ...")
net.fit(files, labels)
else:
print("predicting ...")
test_files = data.get_image_files(config.get('test_dir'))
y_pred = net.predict(test_files)
y_pred = y_pred.transpose()
print y_pred
y_pred = np.clip(np.round(y_pred),
np.min(labels), np.max(labels)).astype(int)
#print y_pred
submission_filename = util.get_submission_filename()
image_files = data.get_image_files(config.get('test_dir'))
names = data.get_names(image_files)
image_column = pd.Series(names, name='photo_id')
level_column = pd.DataFrame(y_pred)#name='labels')
level_column = level_column.apply(lambda x : string_submit(x))
predictions = pd.concat([image_column, level_column], axis=1)
print("tail of predictions file")
print(predictions.tail())
predictions.columns = ['photo_id', 'labels']
predictions.to_csv(submission_filename, index=False)
print("saved predictions to {}".format(submission_filename))
def main(cnf, classes, weights_from, predict):
config = util.load_module(cnf).config
files = data.get_image_files(config.get('train_dir'))
names = data.get_names(files)
names = [int(x) for x in names]
data.classes = int(classes)
labels = data.get_labels(names)
net = create_net(config)
print files.shape
print labels.shape
if predict:
if weights_from is None:
weights_from = config.weights_file
else:
weights_from = str(weights_from)
print weights_from
try:
net.load_params_from(weights_from)
print("loaded weights from {}".format(weights_from))
except IOError:
print("couldn't load weights starting from scratch")
if not predict:
print("fitting ...")
net.fit(files, labels)
else:
print("predicting ...")
test_files = data.get_image_files(config.get('test_dir'))
y_pred = net.predict(test_files)
y_pred = y_pred.transpose()
print y_pred
y_pred = np.clip(np.round(y_pred), np.min(labels),
np.max(labels)).astype(int)
#print y_pred
submission_filename = util.get_submission_filename()
image_files = data.get_image_files(config.get('test_dir'))
names = data.get_names(image_files)
image_column = pd.Series(names, name='photo_id')
level_column = pd.DataFrame(y_pred) #name='labels')
level_column = level_column.apply(lambda x: string_submit(x))
predictions = pd.concat([image_column, level_column], axis=1)
print("tail of predictions file")
print(predictions.tail())
predictions.columns = ['photo_id', 'labels']
predictions.to_csv(submission_filename, index=False)
print("saved predictions to {}".format(submission_filename))
def main(directory, convert_directory, test, crop_size, extension):
try:
os.mkdir(convert_directory)
except OSError:
pass
filenames = [os.path.join(dp, f) for dp, dn, fn in os.walk(directory)
for f in fn if f.endswith('jpeg') or f.endswith('tiff')]
filenames = sorted(filenames)
if test:
names = data.get_names(filenames)
y = data.get_labels(names)
for f, level in zip(filenames, y):
if level == 1:
try:
img = convert(f, crop_size)
img.show()
Image.open(f).show()
real_raw_input = vars(__builtins__).get('raw_input',input)
real_raw_input('enter for next')
except KeyboardInterrupt:
exit(0)
print("Resizing images in {} to {}, this takes a while."
"".format(directory, convert_directory))
n = len(filenames)
# process in batches, sometimes weird things happen with Pool on my machine
batchsize = 500
batches = n // batchsize + 1
pool = Pool(N_PROC)
args = []
label= {}
csv = open('trainLabels.csv')
csv_lines = csv.readlines()[1:]
for line in csv_lines:
line = line.rstrip('\n')
cols = line.split(',')
label[cols[0]] = cols[1]
csv.close()
for f in filenames:
args.append((convert, (directory, convert_directory, f, crop_size,
extension), label))
for i in range(batches):
print("batch {:>2} / {}".format(i + 1, batches))
pool.map(process, args[i * batchsize: (i + 1) * batchsize])
pool.close()
print('done')
def main(directory, convert_directory, test, crop_size, extension):
try:
os.mkdir(convert_directory)
except OSError:
pass
filenames = [os.path.join(dp, f) for dp, dn, fn in os.walk(directory)
for f in fn if f.endswith('jpeg') or f.endswith('tiff')]
filenames = sorted(filenames)
if test:
names = data.get_names(filenames)
y = data.get_labels(names)
for f, level in zip(filenames, y):
if level == 1:
try:
img = convert(f, crop_size)
img.show()
Image.open(f).show()
real_raw_input = vars(__builtins__).get('raw_input',input)
real_raw_input('enter for next')
except KeyboardInterrupt:
exit(0)
print("Resizing images in {} to {}, this takes a while."
"".format(directory, convert_directory))
n = len(filenames)
# process in batches, sometimes weird things happen with Pool on my machine
batchsize = 500
batches = n // batchsize + 1
pool = Pool(N_PROC)
args = []
for f in filenames:
args.append((convert, (directory, convert_directory, f, crop_size,
extension)))
for i in range(batches):
print("batch {:>2} / {}".format(i + 1, batches))
pool.map(process, args[i * batchsize: (i + 1) * batchsize])
pool.close()
print('done')
def main(cnf, weights_from, fold, exp_run_folder, train_retina):
config = util.load_module(cnf).config
config.cnf[
'fold'] = fold # <-- used to change the directories for weights_best, weights_epoch and weights_final
config.cnf['exp_run_folder'] = exp_run_folder
protocol = data.settings['protocol']
if train_retina != 'train_retina':
folds = yaml.load(open('folds/' + protocol + '.yml'))
f0, f1 = fold.split('x')
train_list = folds['Fold_' + f0][int(f1) - 1]
files = data.get_image_files(config.get('train_dir'), train_list)
else:
files = data.get_image_files(config.get('train_dir'))
if weights_from is None:
weights_from = config.weights_file
else:
weights_from = str(weights_from)
names = data.get_names(files)
labels = data.get_labels(names, label_file='folds/' + protocol +
'.csv').astype(np.int32)
net = nn.create_net(config)
try:
net.load_params_from(weights_from)
print("loaded weights from {}".format(weights_from))
except IOError:
print("couldn't load weights, starting from scratch")
#Print layerinfo
print("## Layer information")
import nolearn
layer_info = nolearn.lasagne.PrintLayerInfo()
print(layer_info._get_greeting(net))
layer_info, legend = layer_info._get_layer_info_conv(net)
print(layer_info)
print(legend)
print("fitting ...")
net.fit(files, labels)
def main(cnf, weights_from):
config = util.load_module(cnf).config
if weights_from is None:
weights_from = config.weights_file
else:
weights_from = str(weights_from)
files = data.get_image_files(config.get('train_dir'))
names = data.get_names(files)
labels = data.get_labels(names).astype(np.float32)
net = create_net(config)
try:
net.load_params_from(weights_from)
print("loaded weights from {}".format(weights_from))
except IOError:
print("couldn't load weights starting from scratch")
print("fitting ...")
net.fit(files, labels)
def build(cnf, weights_from):
config = util.load_module(cnf).config
if weights_from is None:
weights_from = config.weights_file
else:
weights_from = str(weights_from)
files = data.get_image_files(config.get('train_dir'))
names = data.get_names(files)
labels = data.get_labels(names).astype(np.float32)
net = create_net(config)
try:
net.load_params_from(weights_from)
print("loaded weights from {}".format(weights_from))
except IOError:
print("couldn't load weights starting from scratch")
print("fitting ...")
# net.fit(files, labels)
return net, files, names, labels
import argparse
import numpy as np
import tensorflow as tf
from model import ANN
import data
parser = argparse.ArgumentParser(description='Visualize ANN')
parser.add_argument('-d',
'--dataset',
type=str,
default='mnist',
choices=data.get_names())
parser.add_argument('--num_iter', type=int, default=5000)
args = parser.parse_args()
dataset = data.init_dataset(name=args.dataset)
model = ANN(dataset.shape)
model.train(dataset.tr_data, dataset.tr_labels, num_iter=args.num_iter)
and the final loss for each minibatch is calculated from this average.
CrossEntropyLoss is used because this is a categorization task, since we're
predicting the next letter of the name given previous letters.
"""
import torch
import torch.nn as nn
import torch.optim as optim
import data
import helpers
from NamesRNN import NamesRNN
from hyperparameters import hps
import random
model = NamesRNN()
names = data.get_names(hps['filename'])
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=hps['learning_rate'])
batch_size = hps['batch_size']
for t in range(hps['epochs']):
batch = random.sample(names, batch_size)
# keep losses from each batch to be averaged later
batch_losses = []
for name in batch:
xs, ys = helpers.name_to_xy(name)
# keep losses from each sequence (name) to be averaged later
seq_losses = []
#@click.option('--test_dir', default=None, show_default=True,
# help="Override directory with test set images.")
cnf = 'configs/c_512_5x5_32.py'
predict = True
per_patient = True
features_file = None
n_iter =3
blend_cnf = 'blend.yml'
test_dir = None
#def fit(cnf, predict, per_patient, features_file, n_iter, blend_cnf, test_dir):
config = util.load_module(cnf).config
image_files = data.get_image_files(config.get('train_dir'))
names = data.get_names(image_files)
labels = data.get_labels(names).astype(np.float32)[:, np.newaxis]
if features_file is not None:
runs = {'run': [features_file]}
else:
runs = data.parse_blend_config(yaml.load(open(blend_cnf)))
scalers = {run: StandardScaler() for run in runs}
tr, te = data.split_indices(image_files, labels)
y_preds = []
for i in range(n_iter):
print("iteration {} / {}".format(i + 1, n_iter))
for run, files in runs.items():
def fit(cnf, exp_run_folder, classifier, features_file, n_iter, blend_cnf,
test_dir, fold):
config = util.load_module(cnf).config
config.cnf[
'fold'] = fold # <-- used to change the directories for weights_best, weights_epoch and weights_final
config.cnf['exp_run_folder'] = exp_run_folder
folds = yaml.load(open('folds/' + data.settings['protocol'] + '.yml'))
f0, f1 = fold.split('x')
train_list = folds['Fold_' + f0][int(f1) - 1]
test_list = folds['Fold_' + f0][0 if f1 == '2' else 1]
image_files = data.get_image_files(config.get('train_dir'), train_list)
names = data.get_names(image_files)
labels = data.get_labels(names,
label_file='folds/' + data.settings['protocol'] +
'.csv').astype(np.int32)[:, np.newaxis]
if features_file is not None:
runs = {'run': [features_file]}
else:
runs = {
run: [
os.path.join(exp_run_folder + '/data/features', f)
for f in files
]
for run, files in yaml.load(open(blend_cnf)).items()
}
scalers = {run: StandardScaler() for run in runs}
y_preds = []
y_preds_proba = []
for i in range(n_iter):
print("iteration {} / {}".format(i + 1, n_iter))
for run, files in runs.items():
files = [
f.replace('f0xf1.npy', '{}.npy'.format(fold)) for f in files
]
if classifier is None:
X_test = data.load_features(files, test=True)
if data.settings['protocol'] != 'protocol3':
y_pred_proba = X_test
y_proba = []
for i in range(0, len(X_test)):
y_proba.append(
y_pred_proba[i][1]) #using score from the positive
y_pred = np.clip(np.round(y_proba), 0, 1).astype(int)
else:
y_pred_proba = est.predict_proba(X)
else:
print("fitting features for run {}".format(run))
X_train = data.load_features(files)
l2Norm = np.linalg.norm(X_train, axis=1)
X_train = np.divide(X_train.T, l2Norm).T
est = estimator(data.settings['protocol'],
classifier,
X_train.shape[1],
image_files,
X_train,
labels,
run,
fold,
eval_size=0.1)
open(
exp_run_folder +
"/best_estimator_fold_{}.txt".format(fold),
"w").write(str(est))
X_test = data.load_features(files, test=True)
l2Norm = np.linalg.norm(X_test, axis=1)
X_test = np.divide(X_test.T, l2Norm).T
if data.settings['protocol'] != 'protocol3':
y_pred = est.predict(X_test).ravel()
y_pred_proba = est.predict_proba(X_test).ravel()
y_proba = []
for i in range(0, 2 * len(X_test), 2):
y_proba.append(
y_pred_proba[i +
1]) #using score from the positive
else:
y_pred_binary = est.predict(X_test)
y_pred = preprocessing.LabelBinarizer().fit([0, 1, 2])
y_pred = y_pred.inverse_transform(y_pred_binary)
y_proba = est.predict_proba(X_test)
image_files = data.get_image_files(test_dir or config.get('test_dir'),
test_list)
names = data.get_names(image_files)
labels = data.get_labels(
names, label_file='folds/' + data.settings['protocol'] +
'.csv').astype(np.int32)[:, np.newaxis] # , per_patient=per_patient
image_column = pd.Series(names, name='image')
labels_column = pd.Series(np.squeeze(labels), name='true')
level_column = pd.Series(y_pred, name='pred')
if data.settings['protocol'] != 'protocol3':
proba_column = pd.Series(y_proba, name='proba')
predictions = pd.concat(
[image_column, labels_column, level_column, proba_column], axis=1)
else:
proba_label_0 = pd.Series(y_proba[:, 0], name='proba_label_0')
proba_label_1 = pd.Series(y_proba[:, 1], name='proba_label_1')
proba_label_2 = pd.Series(y_proba[:, 2], name='proba_label_2')
predictions = pd.concat([
image_column, labels_column, level_column, proba_label_0,
proba_label_1, proba_label_2
],
axis=1)
predictions.to_csv(exp_run_folder +
"/ranked_list_fold_{}.csv".format(fold),
sep=';')
print("tail of predictions")
print(predictions.tail())
acc = len(filter(lambda
(l, y): l == y, zip(labels, y_pred))) / float(len(labels))
print("accuracy: {}".format(acc))
print("confusion matrix")
print(confusion_matrix(labels, y_pred))
if data.settings['protocol'] != 'protocol3':
auc = calc_auc(y_proba, labels, exp_run_folder, classifier, fold)
print("AUC: {}".format(auc))
average_precision = average_precision_score(labels, y_proba)
print("average precision: {}".format(average_precision))
c_matrix = confusion_matrix(labels, y_pred)
print("sensitivity: {}".format(c_matrix[1][1] /
(c_matrix[1][1] + c_matrix[0][1])))
print("specificity: {}".format(c_matrix[0][0] /
(c_matrix[0][0] + c_matrix[1][0])))
else:
y_test = label_binarize(labels, classes=[0, 1, 2])
auc = roc_auc_score(y_test, y_proba, average='macro')
print("AUC: {}".format(auc))
average_precision = average_precision_score(y_test,
y_proba,
average="macro")
print("mean average precision: {}".format(average_precision))
results = pd.concat([
pd.Series(exp_run_folder, name='folder'),
pd.Series(fold, name='fold'),
pd.Series(auc, name='auc'),
pd.Series(average_precision, name='ap'),
pd.Series(acc, name='acc')
],
axis=1)
with open('results.csv', 'a') as f:
results.to_csv(f, header=False)
