def firstProblem():
result = []
for m in range(100):
for size in ssize:
score = Score()
cv = LeaveNOut()
classifier = KNeighborsClassifier(n_neighbors=3, algorithm="kd_tree")
X = np.random.normal(mu, sigma, size)
X = np.expand_dims(X, axis=1)
Y = np.zeros([X.shape[0]])
Y = np.expand_dims(Y, axis=1)
one_indices = random.sample([i for i in range(X.shape[0])], size / 2)
Y[one_indices, 0] = 1
#leave one out
pred, true = cv.run(data=X, labels=Y, model=classifier, n_out=1)
c = score.c_score(pred, true)
auc_score = auc(pred, true, reorder=True)
result.append([c, auc_score, size, m])
data = pd.DataFrame(result)
data.to_csv('result1.csv', header=False, index=False)
def right_feature_selection(X, Y):
score = Score()
cv = LeaveNOut()
classifier = KNeighborsClassifier(n_neighbors=3, algorithm="kd_tree")
pred, true = cv.run(data=X, labels=Y, model=classifier, n_out=1, embedded_feature_selection=True)
c = score.c_score(pred, true)
auc_score = auc(pred, true, reorder=True)
return c, auc_score
def wrong_feature_selection(X, Y):
score = Score()
cv = LeaveNOut()
classifier = KNeighborsClassifier(n_neighbors=3, algorithm="kd_tree")
X, indices = cv.select(X, Y, select_count=10)
pred, true = cv.run(data=X, labels=Y, model=classifier, n_out=1)
c = score.c_score(pred, true)
auc_score = auc(pred, true, reorder=True)
return c, auc_score
