def cross_validate(subject, data_path, reg_C, random_cv=False):
if random_cv:
d = load_train_data(data_path, subject)
x, y = d['x'], d['y']
skf = StratifiedKFold(y, n_folds=10)
else:
filenames_grouped_by_hour = cPickle.load(open('filenames.pickle'))
data_grouped_by_hour = load_grouped_train_data(
data_path, subject, filenames_grouped_by_hour)
n_preictal, n_interictal = len(data_grouped_by_hour['preictal']), len(
data_grouped_by_hour['interictal'])
hours_data = data_grouped_by_hour['preictal'] + data_grouped_by_hour[
'interictal']
hours_labels = np.concatenate(
(np.ones(n_preictal), np.zeros(n_interictal)))
n_folds = n_preictal
skf = StratifiedKFold(hours_labels, n_folds=n_folds)
preictal_probs, labels = [], []
for train_indexes, valid_indexes in skf:
x_train, x_valid = [], []
y_train, y_valid = [], []
for i in train_indexes:
x_train.extend(hours_data[i])
y_train.extend(hours_labels[i] * np.ones(len(hours_data[i])))
for i in valid_indexes:
x_valid.extend(hours_data[i])
y_valid.extend(hours_labels[i] * np.ones(len(hours_data[i])))
x_train = [x[..., np.newaxis] for x in x_train]
x_train = np.concatenate(x_train, axis=3)
x_train = np.rollaxis(x_train, axis=3)
y_train = np.array(y_train)
x_valid = [x[..., np.newaxis] for x in x_valid]
x_valid = np.concatenate(x_valid, axis=3)
x_valid = np.rollaxis(x_valid, axis=3)
y_valid = np.array(y_valid)
n_valid_examples = x_valid.shape[0]
n_timesteps = x_valid.shape[-1]
x_train, y_train = reshape_data(x_train, y_train)
data_scaler = StandardScaler()
x_train = data_scaler.fit_transform(x_train)
logreg = LogisticRegression(C=reg_C)
logreg.fit(x_train, y_train)
x_valid = reshape_data(x_valid)
x_valid = data_scaler.transform(x_valid)
p_valid = predict(logreg, x_valid, n_valid_examples, n_timesteps)
preictal_probs.extend(p_valid)
labels.extend(y_valid)
return preictal_probs, labels
def curve_per_subject(subject, data_path, test_labels):
d = load_train_data(data_path, subject)
x, y_10m = d['x'], d['y']
n_train_examples = x.shape[0]
n_timesteps = x.shape[-1]
print 'n_preictal', np.sum(y_10m)
print 'n_inetrictal', np.sum(y_10m - 1)
x, y = reshape_data(x, y_10m)
data_scaler = StandardScaler()
x = data_scaler.fit_transform(x)
lda = LDA()
lda.fit(x, y)
pred_1m = lda.predict_proba(x)[:, 1]
pred_10m = np.reshape(pred_1m, (n_train_examples, n_timesteps))
pred_10m = np.mean(pred_10m, axis=1)
fpr, tpr, threshold = roc_curve(y_10m, pred_10m)
c = np.sqrt((1 - tpr) ** 2 + fpr ** 2)
opt_threshold = threshold[np.where(c == np.min(c))[0]][-1]
print opt_threshold
# ------- TEST ---------------
d = load_test_data(data_path, subject)
x_test, id = d['x'], d['id']
n_test_examples = x_test.shape[0]
n_timesteps = x_test.shape[3]
x_test = reshape_data(x_test)
x_test = data_scaler.transform(x_test)
pred_1m = lda.predict_proba(x_test)[:, 1]
pred_10m = np.reshape(pred_1m, (n_test_examples, n_timesteps))
pred_10m = np.mean(pred_10m, axis=1)
y_pred = np.zeros_like(test_labels)
y_pred[np.where(pred_10m >= opt_threshold)] = 1
cm = confusion_matrix(test_labels, y_pred)
print print_cm(cm, labels=['interictal', 'preictal'])
sn = 1.0 * cm[1, 1] / (cm[1, 1] + cm[1, 0])
sp = 1.0 * cm[0, 0] / (cm[0, 0] + cm[0, 1])
print sn, sp
sn, sp = [], []
t_list = np.arange(0.0, 1.0, 0.01)
for t in t_list:
y_pred = np.zeros_like(test_labels)
y_pred[np.where(pred_10m >= t)] = 1
cm = confusion_matrix(test_labels, y_pred)
sn_t = 1.0 * cm[1, 1] / (cm[1, 1] + cm[1, 0])
sp_t = 1.0 * cm[0, 0] / (cm[0, 0] + cm[0, 1])
sn.append(sn_t)
sp.append(sp_t)
return t_list, sn, sp
def curve_per_subject(subject, data_path, test_labels):
d = load_train_data(data_path, subject)
x, y_10m = d['x'], d['y']
n_train_examples = x.shape[0]
n_timesteps = x.shape[-1]
print 'n_preictal', np.sum(y_10m)
print 'n_inetrictal', np.sum(y_10m - 1)
x, y = reshape_data(x, y_10m)
data_scaler = StandardScaler()
x = data_scaler.fit_transform(x)
lda = LDA()
lda.fit(x, y)
pred_1m = lda.predict_proba(x)[:, 1]
pred_10m = np.reshape(pred_1m, (n_train_examples, n_timesteps))
pred_10m = np.mean(pred_10m, axis=1)
fpr, tpr, threshold = roc_curve(y_10m, pred_10m)
c = np.sqrt((1 - tpr)**2 + fpr**2)
opt_threshold = threshold[np.where(c == np.min(c))[0]][-1]
print opt_threshold
# ------- TEST ---------------
d = load_test_data(data_path, subject)
x_test, id = d['x'], d['id']
n_test_examples = x_test.shape[0]
n_timesteps = x_test.shape[3]
x_test = reshape_data(x_test)
x_test = data_scaler.transform(x_test)
pred_1m = lda.predict_proba(x_test)[:, 1]
pred_10m = np.reshape(pred_1m, (n_test_examples, n_timesteps))
pred_10m = np.mean(pred_10m, axis=1)
y_pred = np.zeros_like(test_labels)
y_pred[np.where(pred_10m >= opt_threshold)] = 1
cm = confusion_matrix(test_labels, y_pred)
print print_cm(cm, labels=['interictal', 'preictal'])
sn = 1.0 * cm[1, 1] / (cm[1, 1] + cm[1, 0])
sp = 1.0 * cm[0, 0] / (cm[0, 0] + cm[0, 1])
print sn, sp
sn, sp = [], []
t_list = np.arange(0.0, 1.0, 0.01)
for t in t_list:
y_pred = np.zeros_like(test_labels)
y_pred[np.where(pred_10m >= t)] = 1
cm = confusion_matrix(test_labels, y_pred)
sn_t = 1.0 * cm[1, 1] / (cm[1, 1] + cm[1, 0])
sp_t = 1.0 * cm[0, 0] / (cm[0, 0] + cm[0, 1])
sn.append(sn_t)
sp.append(sp_t)
return t_list, sn, sp
def cross_validate(subject, data_path, reg_C, random_cv=False):
if random_cv:
d = load_train_data(data_path,subject)
x, y = d['x'], d['y']
skf = StratifiedKFold(y, n_folds=10)
else:
filenames_grouped_by_hour = cPickle.load(open('filenames.pickle'))
data_grouped_by_hour = load_grouped_train_data(data_path, subject, filenames_grouped_by_hour)
n_preictal, n_interictal = len(data_grouped_by_hour['preictal']), len(data_grouped_by_hour['interictal'])
hours_data = data_grouped_by_hour['preictal'] + data_grouped_by_hour['interictal']
hours_labels = np.concatenate((np.ones(n_preictal), np.zeros(n_interictal)))
n_folds = n_preictal
skf = StratifiedKFold(hours_labels, n_folds=n_folds)
preictal_probs, labels = [], []
for train_indexes, valid_indexes in skf:
x_train, x_valid = [], []
y_train, y_valid = [], []
for i in train_indexes:
x_train.extend(hours_data[i])
y_train.extend(hours_labels[i] * np.ones(len(hours_data[i])))
for i in valid_indexes:
x_valid.extend(hours_data[i])
y_valid.extend(hours_labels[i] * np.ones(len(hours_data[i])))
x_train = [x[..., np.newaxis] for x in x_train]
x_train = np.concatenate(x_train, axis=3)
x_train = np.rollaxis(x_train, axis=3)
y_train = np.array(y_train)
x_valid = [x[..., np.newaxis] for x in x_valid]
x_valid = np.concatenate(x_valid, axis=3)
x_valid = np.rollaxis(x_valid, axis=3)
y_valid = np.array(y_valid)
n_valid_examples = x_valid.shape[0]
n_timesteps = x_valid.shape[-1]
x_train, y_train = reshape_data(x_train, y_train)
data_scaler = StandardScaler()
x_train = data_scaler.fit_transform(x_train)
logreg = LogisticRegression(C=reg_C)
logreg.fit(x_train, y_train)
x_valid = reshape_data(x_valid)
x_valid = data_scaler.transform(x_valid)
p_valid = predict(logreg, x_valid, n_valid_examples, n_timesteps)
preictal_probs.extend(p_valid)
labels.extend(y_valid)
return preictal_probs, labels
def train(subject, data_path, reg_C=None):
d = load_train_data(data_path, subject)
x, y = d['x'], d['y']
x, y = reshape_data(x, y)
data_scaler = StandardScaler()
x = data_scaler.fit_transform(x)
lda = LogisticRegression(C=reg_C)
lda.fit(x, y)
return lda, data_scaler
def predict(subject, model, data_scaler, data_path, submission_path, test_labels, opt_threshold_train):
d = load_test_data(data_path, subject)
x_test, id = d['x'], d['id']
n_test_examples = x_test.shape[0]
n_timesteps = x_test.shape[3]
x_test = reshape_data(x_test)
x_test = data_scaler.transform(x_test)
pred_1m = model.predict_proba(x_test)[:, 1]
pred_10m = np.reshape(pred_1m, (n_test_examples, n_timesteps))
pred_10m = np.mean(pred_10m, axis=1)
ans = zip(id, pred_10m)
df = DataFrame(data=ans, columns=['clip', 'preictal'])
df.to_csv(submission_path + '/' + subject + '.csv', index=False, header=True)
def train(subject, data_path, plot=False):
d = load_train_data(data_path, subject)
x, y = d['x'], d['y']
print 'n_preictal', np.sum(y)
print 'n_inetrictal', np.sum(y - 1)
n_channels = x.shape[1]
n_fbins = x.shape[2]
x, y = reshape_data(x, y)
data_scaler = StandardScaler()
x = data_scaler.fit_transform(x)
lda = LDA()
lda.fit(x, y)
coef = lda.scalings_ * lda.coef_[:1].T
channels = []
fbins = []
for c in range(n_channels):
fbins.extend(range(n_fbins)) # 0- delta, 1- theta ...
channels.extend([c] * n_fbins)
if plot:
fig = plt.figure()
for i in range(n_channels):
if n_channels == 24:
fig.add_subplot(4, 6, i)
else:
fig.add_subplot(4, 4, i)
ax = plt.gca()
ax.set_xlim([0, n_fbins])
ax.set_xticks(np.arange(0.5, n_fbins + 0.5, 1))
ax.set_xticklabels(np.arange(0, n_fbins))
max_y = max(abs(coef)) + 0.01
ax.set_ylim([0, max_y])
ax.set_yticks(
np.around(np.arange(0, max_y, max_y / 4.0), decimals=1))
for label in (ax.get_xticklabels() + ax.get_yticklabels()):
label.set_fontsize(15)
plt.bar(range(0, n_fbins),
abs(coef[i * n_fbins:i * n_fbins + n_fbins]))
fig.suptitle(subject, fontsize=20)
plt.show()
coefs = np.reshape(coef, (n_channels, n_fbins))
return lda, data_scaler, coefs
def predict(subject, model, data_scaler, data_path, submission_path):
d = load_test_data(data_path, subject)
x_test, id = d['x'], d['id']
n_test_examples = x_test.shape[0]
n_timesteps = x_test.shape[3]
x_test = reshape_data(x_test)
x_test = data_scaler.transform(x_test)
pred_1m = model.predict_proba(x_test)[:, 1]
pred_10m = np.reshape(pred_1m, (n_test_examples, n_timesteps))
pred_10m = np.mean(pred_10m, axis=1)
ans = zip(id, pred_10m)
df = DataFrame(data=ans, columns=['clip', 'preictal'])
df.to_csv(submission_path + '/' + subject + '.csv', index=False, header=True)
return pred_10m
def train(subject, data_path, plot=False):
d = load_train_data(data_path, subject)
x, y = d['x'], d['y']
print 'n_preictal', np.sum(y)
print 'n_inetrictal', np.sum(y - 1)
n_channels = x.shape[1]
n_fbins = x.shape[2]
x, y = reshape_data(x, y)
data_scaler = StandardScaler()
x = data_scaler.fit_transform(x)
lda = LDA()
lda.fit(x, y)
coef = lda.scalings_ * lda.coef_[:1].T
channels = []
fbins = []
for c in range(n_channels):
fbins.extend(range(n_fbins)) # 0- delta, 1- theta ...
channels.extend([c] * n_fbins)
if plot:
fig = plt.figure()
for i in range(n_channels):
if n_channels == 24:
fig.add_subplot(4, 6, i)
else:
fig.add_subplot(4, 4, i)
ax = plt.gca()
ax.set_xlim([0, n_fbins])
ax.set_xticks(np.arange(0.5, n_fbins + 0.5, 1))
ax.set_xticklabels(np.arange(0, n_fbins))
max_y = max(abs(coef)) + 0.01
ax.set_ylim([0, max_y])
ax.set_yticks(np.around(np.arange(0, max_y, max_y / 4.0), decimals=1))
for label in (ax.get_xticklabels() + ax.get_yticklabels()):
label.set_fontsize(15)
plt.bar(range(0, n_fbins), abs(coef[i * n_fbins:i * n_fbins + n_fbins]))
fig.suptitle(subject, fontsize=20)
plt.show()
coefs = np.reshape(coef, (n_channels, n_fbins))
return lda, data_scaler, coefs