def set_kpca_obj(pars, data, sntype, type_number):
"""
Set kpca object based on cross-validation results.
input: pars, dict
output from read_hyperpar
data, array
output from read_matrix
sntype, list
output from read_matrix
type_number, dict
dictionary to translate types between raw data and final
classification
keywords -> final classificaton elements
values -> identifiers in raw data
output: obj_kpca, KernelPCA obj
tailored with cross-validation results
spec_matrix, array
low dimension spectroscopic matrix
labels, list
classes as defined in raw data files
"""
from sklearn.decomposition import KernelPCA
import numpy as np
# start kpca object
obj_kpca = KernelPCA()
obj_kpca.eigen_solver = pars['eigen_solver']
obj_kpca.kernel = pars['kernel']
obj_kpca.alpha = pars['alpha']
obj_kpca.gamma = pars['gamma']
obj_kpca.n_components = pars['n_components']
obj_kpca.coef0 = pars['coef0']
obj_kpca.degree = pars['degree']
obj_kpca.tol = pars['tol']
obj_kpca.fit_inverse_transform = pars['fit_inverse_transform']
obj_kpca.remove_zero_eig = pars['remove_zero_eig']
obj_kpca.kernel_params = pars['kernel_params']
obj_kpca.max_iter = pars['max_iter']
spec_matrix = obj_kpca.fit_transform(data)
# construct label vector
labels = []
for elem in sntype:
for classes in type_number.keys():
if elem in type_number[classes]:
labels.append(classes)
labels = np.array(labels)
return obj_kpca, spec_matrix, labels
print("SVM classifier's test accuracy on LDA:")
print(accuracy_score(y_test,y_test_pred))
###kPCA & LR
print('\n' * 3)
print("<3.1> refit logistic regression classifier on the kPCA transformed datasets.")
from sklearn.decomposition import KernelPCA
lr = LogisticRegression()
kpca = KernelPCA(n_components=2, kernel='rbf', gamma=15)
parameters=[0.005,0.010,0.015,0.020,0.025]
for i in range(5):
kpca.gamma=parameters[i]
X_train_kpca = kpca.fit_transform(X_train_std)
X_test_kpca = kpca.transform(X_test_std)
lr.fit(X_train_kpca, y_train)
y_train_pred = lr.predict(X_train_kpca)
y_test_pred = lr.predict(X_test_kpca)
print("LR classifier's train accuracy on kPCA:")
print(accuracy_score(y_train,y_train_pred))
print("LR classifier's test accuracy on kPCA:")
print(accuracy_score(y_test,y_test_pred))
###kPCA & SVM
print('\n' * 3)
print("<3.2> refit SVM regression classifier on the kPCA transformed datasets.")
from sklearn.svm import SVC
svm = SVC(kernel='linear', C=1.0, random_state=1)
#SVM
svm2 = SVC()
lda = LDA(n_components=2)
X_train_lda = lda.fit_transform(X_train_std, y_train)
X_test_lda = lda.transform(X_test_std)
svm2.fit(X_train_lda, y_train)
print('SVM_lda_train accuracy score: %.5f' %
(svm2.score(X_train_lda, y_train)))
print('SVM_lda_test accuracy score: %.5f' % (svm2.score(X_test_lda, y_test)))
#KPCA
#LogisticRegression
gamma_space = np.logspace(-2, 0, 4)
scikit_kpca = KernelPCA(n_components=13, kernel='rbf')
for gamma in gamma_space:
scikit_kpca.gamma = gamma
X_train_kpca = scikit_kpca.fit_transform(X_train_std)
X_test_kpca = scikit_kpca.transform(X_test_std)
log3 = LogisticRegression()
log3.fit(X_train_kpca, y_train)
print('(gamma:' + str(gamma) + ') LR_kpca_train accuracy score: %.5f' %
(log3.score(X_train_kpca, y_train)))
print('(gamma:' + str(gamma) + ') LR_kpca_test accuracy score: %.5f' %
(log3.score(X_test_kpca, y_test)))
#SVM
gamma_space = np.logspace(-2, 0, 4)
scikit_kpca = KernelPCA(n_components=13, kernel='rbf')
for gamma in gamma_space:
scikit_kpca.gamma = gamma
X_train_kpca = scikit_kpca.fit_transform(X_train_std)
