def plot_train_probs(subject, data_path, model_path):
with open(model_path + '/' + subject + '.pickle', 'rb') as f:
state_dict = pickle.load(f)
cnn = ConvNet(state_dict['params'])
cnn.set_weights(state_dict['weights'])
scalers = state_dict['scalers']
d = load_train_data(data_path, subject)
x, y = d['x'], d['y']
x, _ = scale_across_time(x, x_test=None, scalers=scalers) if state_dict['params']['scale_time'] \
else scale_across_features(x, x_test=None, scalers=scalers)
cnn.batch_size.set_value(x.shape[0])
probs = cnn.get_test_proba(x)
fpr, tpr, threshold = roc_curve(y, probs)
c = np.sqrt((1 - tpr)**2 + fpr**2)
opt_threshold = threshold[np.where(c == np.min(c))[0]]
print(opt_threshold)
x_coords = np.zeros(len(y), dtype='float64')
rng = np.random.RandomState(42)
x_coords += rng.normal(0.0, 0.08, size=len(x_coords))
plt.scatter(x_coords, probs, c=y, s=60)
plt.title(subject)
plt.show()
def predict(subject, data_path, model_path, submission_path):
patient_filenames = [filename for filename in os.listdir(model_path) if
subject in filename and filename.endswith('.pickle')]
for filename in patient_filenames:
print filename
d = load_test_data(data_path, subject)
x, id = d['x'], d['id']
with open(model_path + '/' + filename, 'rb') as f:
state_dict = cPickle.load(f)
scalers = state_dict['scalers']
x, _ = scale_across_time(x, x_test=None, scalers=scalers) if state_dict['params']['scale_time'] \
else scale_across_features(x, x_test=None, scalers=scalers)
cnn = ConvNet(state_dict['params'])
cnn.set_weights(state_dict['weights'])
test_proba = cnn.get_test_proba(x)
ans = zip(id, test_proba)
df = DataFrame(data=ans, columns=['clip', 'preictal'])
csv_name = '.'.join(filename.split('.')[:-1]) if '.' in filename else filename
df.to_csv(submission_path + '/' + csv_name + '.csv', index=False, header=True)
def predict(subject, data_path, model_path, submission_path):
patient_filenames = [
filename for filename in os.listdir(model_path)
if subject in filename and filename.endswith('.pickle')
]
for filename in patient_filenames:
print(filename)
d = load_test_data(data_path, subject)
x, id = d['x'], d['id']
with open(model_path + '/' + filename, 'rb') as f:
state_dict = pickle.load(f)
scalers = state_dict['scalers']
x, _ = scale_across_time(x, x_test=None, scalers=scalers) if state_dict['params']['scale_time'] \
else scale_across_features(x, x_test=None, scalers=scalers)
cnn = ConvNet(state_dict['params'])
cnn.set_weights(state_dict['weights'])
test_proba = cnn.get_test_proba(x)
ans = list(zip(id, test_proba))
df = DataFrame(data=ans, columns=['clip', 'preictal'])
csv_name = '.'.join(
filename.split('.')[:-1]) if '.' in filename else filename
df.to_csv(submission_path + '/' + csv_name + '.csv',
index=False,
header=True)
def plot_train_probs(subject, data_path, model_path):
with open(model_path + "/" + subject + ".pickle", "rb") as f:
state_dict = cPickle.load(f)
cnn = ConvNet(state_dict["params"])
cnn.set_weights(state_dict["weights"])
scalers = state_dict["scalers"]
d = load_train_data(data_path, subject)
x, y = d["x"], d["y"]
x, _ = (
scale_across_time(x, x_test=None, scalers=scalers)
if state_dict["params"]["scale_time"]
else scale_across_features(x, x_test=None, scalers=scalers)
)
cnn.batch_size.set_value(x.shape[0])
probs = cnn.get_test_proba(x)
fpr, tpr, threshold = roc_curve(y, probs)
c = np.sqrt((1 - tpr) ** 2 + fpr ** 2)
opt_threshold = threshold[np.where(c == np.min(c))[0]]
print opt_threshold
x_coords = np.zeros(len(y), dtype="float64")
rng = np.random.RandomState(42)
x_coords += rng.normal(0.0, 0.08, size=len(x_coords))
plt.scatter(x_coords, probs, c=y, s=60)
plt.title(subject)
plt.show()
