cv = KFold(n_splits=K, shuffle=True)
clf = GaussianNB()
scores = []
for i in range(100):
features, labels = shuffle(features, labels)
for train, test in cv.split(features):
features_trn = features[train]
features_test = features[test]
labels_trn = [labels[item] for item in train]
labels_test = [labels[item] for item in test]
clf.fit(features_trn, labels_trn)
result = clf.predict(features_test)
score = accuracy_score(result, labels_test)
scores.append(score)
print()
print(scores)
print('Average Score = ', round(sum(scores) / (len(scores)), 5))
print('Standard Deviation = ', numpy.std(scores))
ft1, lb1 = preprocess_ft_lbls_num()
print(ft1.shape)
from sklearn.decomposition import PCA
from sklearn.feature_selection import SelectKBest
from sklearn.utils import shuffle
from sklearn.naive_bayes import GaussianNB
from sklearn.manifold import LocallyLinearEmbedding
from data.preprocess import features_preprocess, features_test_preprocess, labels_preprocess, labels_preprocess_num
from data.preprocess_2nd import preprocess_ft_lbls_num
from data.preprocess import ft_lbls_num
scores = []
embedding = LocallyLinearEmbedding(n_components=10)
(features1, labels1) = ft_lbls_num()
(features2, labels2) = preprocess_ft_lbls_num()
features1 = embedding.fit_transform(features1, labels1)
features2 = embedding.fit_transform(features2, labels2)
K = 5
cv = KFold(n_splits=K, shuffle=True)
features = numpy.concatenate((features1, features2))
labels = numpy.concatenate((labels1, labels2))
clf = svm.SVC(kernel='rbf')
for i in range(100):
features1, labels1 = shuffle(features1, labels1)
#features_trn = selection.fit_transform(features_trn, labels_trn)
#features_test =selection.transform(features_test)
features_trn = pca.fit_transform(features_trn, labels_trn)
features_test = pca.transform(features_test)
clf.fit(features_trn, labels_trn)
result = clf.predict(features_test)
score = accuracy_score(result, labels_test)
scores.append(score)
vrnc = pca.explained_variance_ratio_
variance_ratio1.extend(vrnc)
average_score = sum(scores) / K
(features, labels) = preprocess_ft_lbls_num()
scores = []
for train, test in cv.split(features):
features_trn = features[train]
features_test = features[test]
labels_trn = labels[train]
labels_test = labels[test]
#features_trn = selection.fit_transform(features_trn, labels_trn)
#features_test = selection.transform(features_test)
features_trn = pca.fit_transform(features_trn, labels_trn)
features_test = pca.transform(features_test)