log_loss(test_y, predict_y, labels=clf.classes_, eps=1e-15))
clf = KNeighborsClassifier(n_neighbors=alpha[best_alpha])
predict_and_plot_confusion_matrix(train_x_responseCoding, train_y,
cv_x_responseCoding, cv_y, clf)
clf = KNeighborsClassifier(n_neighbors=alpha[best_alpha])
clf.fit(train_x_responseCoding, train_y)
sig_clf = CalibratedClassifierCV(clf, method='sigmoid')
sig_clf.fit(train_x_responseCoding, train_y)
test_point_index = 1
predicted_cls = sig_clf.predict(test_x_responseCoding[0].reshape(1, -1))
print(" Actual class :", predicted_cls[0])
print("Predicted class :", test_y[test_point_index])
neighbors = clf.kneighbors(test_x_responseCoding[test_point_index].reshape(
1, -1))
print("the ", alpha[best_alpha],
"nearest neighbors of test points belong to class", neighbors)
#print("Frequency of nearesr point :",Counter(train_y(neighbors[1][0])))
clf = KNeighborsClassifier(n_neighbors=alpha[best_alpha])
clf.fit(train_x_responseCoding, train_y)
sig_clf = CalibratedClassifierCV(clf, method='sigmoid')
sig_clf.fit(train_x_responseCoding, train_y)
test_point_index = 100
predicted_cls = sig_clf.predict(test_x_responseCoding[0].reshape(1, -1))
print(" Actual class :", predicted_cls[0])
print("Predicted class :", test_y[test_point_index])
neighbors = clf.kneighbors(test_x_responseCoding[test_point_index].reshape(
1, -1))
clf = KNeighborsClassifier(n_neighbors=alpha[best_alpha])
predict_and_plot_confusion_matrix(train_x_responseCoding, train_y,
cv_x_responseCoding, cv_y, clf)
# Lets look at few test points
clf = KNeighborsClassifier(n_neighbors=alpha[best_alpha])
clf.fit(train_x_responseCoding, train_y)
sig_clf = CalibratedClassifierCV(clf, method="sigmoid")
sig_clf.fit(train_x_responseCoding, train_y)
test_point_index = 1
predicted_cls = sig_clf.predict(test_x_responseCoding[0].reshape(1, -1))
print("Predicted Class :", predicted_cls[0])
print("Actual Class :", test_y[test_point_index])
neighbors = clf.kneighbors(
test_x_responseCoding[test_point_index].reshape(1, -1), alpha[best_alpha])
print("The ", alpha[best_alpha],
" nearest neighbours of the test points belongs to classes",
train_y[neighbors[1][0]])
print("Fequency of nearest points :", Counter(train_y[neighbors[1][0]]))
#logistic Regression
alpha = [10**x for x in range(-6, 3)]
cv_log_error_array = []
for i in alpha:
print("for alpha =", i)
clf = SGDClassifier(class_weight='balanced',
alpha=i,
penalty='l2',
loss='log',
