def PCA_please(enable_PCA_cache, submit_test_prediction):
tr_identity, tr_labels, tr_images, valid_identity, valid_labels, valid_images = preprocessor.load_train_and_valid(
is_gabor=False)
unlabeled_images = preprocessor.load_unlabeled(is_gabor=False)
if (enable_PCA_cache):
pca_filename = 'pca.pkl'
if os.path.isfile(pca_filename):
pca = joblib.load(pca_filename)
else:
# save the PCA
pca = models.PCA()
pca.fit(unlabeled_images)
joblib.dump(pca, pca_filename)
else:
pca = models.PCA()
pca.fit(unlabeled_images)
pca_tr_images = pca.transform(tr_images)
pca_valid_images = pca.transform(valid_images)
model = models.SVM()
model.fit(pca_tr_images, tr_labels)
train_predictions = model.predict(pca_tr_images)
valid_predictions = model.predict(pca_valid_images)
printClassificationRate(model, valid_labels, valid_predictions, tr_labels,
train_predictions)
if (submit_test_prediction):
test_images = preprocessor.load_test(is_gabor=False)
pca_test_images = pca.transform(test_images)
test_predictions = model.predict(pca_test_images)
submission.output(test_predictions)
def main():
args = get_args()
X, y = load(args.data, 'train')
test_X, _ = load(args.data, args.test_split)
if args.dr_algorithm is not None:
num_train = X.shape[0]
concat_data = np.concatenate((X, test_X))
start = time.time()
if args.dr_algorithm == 'pca':
reduced_X = models.PCA(concat_data,
args.target_dim).fit(concat_data)
elif args.dr_algorithm == 'lle':
reduced_X = models.LLE(concat_data, args.target_dim,
args.lle_k).fit(concat_data)
else:
raise Exception('Invalid dimensionality reduction algorithm')
end = time.time()
print(f"dimensionality reduction took {end - start} seconds!")
X = reduced_X[:num_train]
test_X = reduced_X[num_train:]
model = models.KNN(args.knn_k)
model.fit(X, y)
y_hat = model.predict(test_X)
np.savetxt(args.predictions_file, y_hat, fmt='%d')
def PCA_Preprocess(pca_fit_data, train_features, valid_features,
test_features):
pca = models.PCA()
pca.fit(pca_fit_data)
transformed_pca_fit_dat = pca.transform(pca_fit_data)
transformed_train_features = pca.transform(train_features)
transformed_valid_features = pca.transform(valid_features)
transformed_test_features = pca.transform(test_features)
print "PCA n components: %d" % (pca.get_n_components())
return transformed_pca_fit_dat, transformed_train_features, transformed_valid_features, transformed_test_features