# Compose the training ( data & labels )
training_data = np.array(training_normal + training_dme)
training_label = np.array([0] * len(training_normal) +
[1] * len(training_dme),
dtype=int)
# Compose the testing
testing_data = np.array([
current_cbook.get_BoF_descriptor(
get_lbp_data(filename_normal[idx_test]))[0],
current_cbook.get_BoF_descriptor(
get_lbp_data(filename_dme[idx_test]))[0]
])
# Run the classification for this specific data
pred_label, roc = Classify(training_data, training_label, testing_data,
np.array([0, 1], dtype=int), **config_class)
results_by_codebook.append((pred_label, roc))
return results_by_codebook
################################################################################################
################################################################################################
### Define the global variable regarding the classification
config = [{
'classifier_str': 'random-forest',
'n_estimators': 100,
'gs_n_jobs': 8
training_data = dmr.fit_transform(training_data)
# Compose the testing
testing_data = np.array([
get_lbp_data(filename_normal[idx_test]),
get_lbp_data(filename_dme[idx_test])
])
# Project the testing_data
testing_data = dmr.transform(testing_data)
# Run the classification for this specific data
pred_label, roc = Classify(training_data,
training_label,
testing_data,
np.array([0, 1], dtype=int),
classifier_str='random-forest',
n_estimators=100,
n_jobs=60,
max_features=None)
results_cv.append((pred_label, roc))
# We have to store the final codebook
path_to_save = '/work/le2i/gu5306le/OCT/lbp_r_' + str(
radius) + '_hist_pca_results'
if not os.path.exists(path_to_save):
os.makedirs(path_to_save)
from sklearn.externals import joblib
joblib.dump(results_cv, join(path_to_save, 'hist.pkl'))
# OS library
import os
from os.path import join, isdir, isfile
# sys library
import sys
from protoclass.classification.classification import Classify
# Generate a vector
label = np.array([-1] * 1000 + [1] * 200)
data = np.random.random((label.shape[0], 5))
label2 = np.array([-1] * 100 + [1] * 20)
data2 = np.random.random((label2.shape[0], 5))
balancing_criterion = 'balance-cascade'
kind_smote = 'svm'
version_nearmiss = 3
classifier_str = 'naive-bayes'
pred_label, pred_prob, roc = Classify(
data,
label,
data2,
label2,
classifier_str=classifier_str,
class_prior=np.array([0.3,
0.7])) #, balancing_criterion=balancing_criterion)
print pred_label
print pred_prob
print roc
