def run_feature_projected_classification(train_x_matrix,
train_y_vector,
test_x_matrix,
test_y_vector,
feature_array,
top_k,
method,
class_id=-1,
logger=None):
if logger is None:
logger = init_logging('')
train_row, attr_len, attr_num, input_map = train_x_matrix.shape
test_row, attr_len, attr_num, input_map = test_x_matrix.shape
real_num_classes, attr_num = feature_array.shape
all_predict_matrix = np.zeros(test_row * real_num_classes).reshape(
test_row, real_num_classes)
feature_col = attr_len * top_k * input_map
if class_id == -1:
min_class = min(train_y_vector)
max_class = max(train_y_vector) + 1
else:
min_class = class_id
max_class = class_id + 1
n_neighbors = 1
samples_leaf = 20
prob = True
all_f1_value = []
all_train_time = []
all_test_time = []
#min_class = 9
for i in range(min_class, max_class):
logger.info('class: ' + str(i))
temp_train_y_vector = np.where(train_y_vector == i, 1, 0)
temp_test_y_vector = np.where(test_y_vector == i, 1, 0)
fold_positive_len = len(np.where(temp_train_y_vector == 1)[0])
fold_negative_len = len(temp_train_y_vector) - fold_positive_len
logger.info("=====")
logger.info("positive class labels length: " + str(fold_positive_len))
logger.info("negative class labels length: " + str(fold_negative_len))
class_feature = feature_array[i]
class_feature = class_feature[0:top_k]
logger.info("feature list: " + str(class_feature))
temp_train_x_matrix = train_x_matrix[:, :, class_feature, :]
temp_test_x_matrix = test_x_matrix[:, :, class_feature, :]
temp_train_x_matrix = temp_train_x_matrix.reshape(
train_row, feature_col)
temp_test_x_matrix = temp_test_x_matrix.reshape(test_row, feature_col)
if method == 'knn':
class_accuracy, class_predict_y, class_predict_prob, class_train_time, class_test_time = run_knn(
temp_train_x_matrix, temp_train_y_vector, temp_test_x_matrix,
temp_test_y_vector, n_neighbors, prob)
elif method == 'rf':
class_accuracy, class_predict_y, class_predict_prob, class_train_time, class_test_time = run_rf(
temp_train_x_matrix, temp_train_y_vector, temp_test_x_matrix,
temp_test_y_vector, samples_leaf, prob)
elif method == 'libsvm':
class_accuracy, class_predict_y, class_predict_prob, class_train_time, class_test_time = run_libsvm(
temp_train_x_matrix, temp_train_y_vector, temp_test_x_matrix,
temp_test_y_vector, logger, prob, '', True)
class_accuracy, precision, recall, class_f1, tp, fp, tn, fn = f1_value_precision_recall_accuracy(
class_predict_y, temp_test_y_vector, 1)
logger.info(method + " f1 for class " + str(i) + ": " + str(class_f1))
logger.info(method + " accuracy for class " + str(i) + ": " +
str(class_accuracy))
all_f1_value.append(class_f1)
all_train_time.append(class_train_time)
all_test_time.append(class_test_time)
all_predict_matrix[:, i] = class_predict_prob[:, 1]
#if i > 2:
# break
all_accuracy, all_predict_y = predict_matrix_with_prob_to_predict_accuracy(
all_predict_matrix, test_y_vector)
return all_accuracy, all_f1_value, all_predict_y, all_train_time, all_test_time, all_predict_matrix
def run_feature_projected_cnn(train_x_matrix,
train_y_vector,
test_x_matrix,
test_y_vector,
data_stru,
cnn_setting,
feature_dict,
top_k,
saver_file_profix='',
class_id=-1,
logger=None):
if logger is None:
logger = init_logging('')
method = 'cnn'
real_num_classes = data_stru.num_classes
data_stru.num_classes = 2
cnn_setting.num_classes = 2
cnn_setting.feature_method = 'none'
num_classes = 2
train_row, attr_len, attr_num, input_map = train_x_matrix.shape
test_row, attr_len, attr_num, input_map = test_x_matrix.shape
all_predict_matrix = np.zeros(test_row * real_num_classes).reshape(
test_row, real_num_classes)
saver_file = ''
if class_id == -1:
min_class = min(train_y_vector)
max_class = max(train_y_vector) + 1
else:
min_class = class_id
max_class = class_id + 1
saver_file_profix = saver_file_profix + '_class'
keep_saver_file = ''
all_train_time = 0
all_test_time = 0
all_f1_value = []
all_train_time = []
all_test_time = []
for i in range(min_class, max_class):
logger.info('class: ' + str(i))
temp_train_y_vector = np.where(train_y_vector == i, 1, 0)
temp_test_y_vector = np.where(test_y_vector == i, 1, 0)
class_saver_profix = saver_file_profix + str(i)
fold_positive_len = len(np.where(temp_train_y_vector == 1)[0])
fold_negative_len = len(temp_train_y_vector) - fold_positive_len
logger.info("=====")
logger.info("positive class labels length: " + str(fold_positive_len))
logger.info("negative class labels length: " + str(fold_negative_len))
class_feature = feature_dict[i]
class_feature = class_feature[0:top_k]
print("class: " + str(i))
print("number of features: " + str(top_k))
print("Top features list: " + str(class_feature))
logger.info("Top feature list: " + str(class_feature))
temp_train_x_matrix = train_x_matrix[:, :, class_feature, :]
temp_test_x_matrix = test_x_matrix[:, :, class_feature, :]
temp_train_y_matrix = y_vector_to_matrix(temp_train_y_vector,
num_classes)
temp_test_y_matrix = y_vector_to_matrix(temp_test_y_vector,
num_classes)
if i == min_class:
train_x_placeholder, output_y_placeholder, predict_y_prob, keep_prob_placeholder, keeped_feature_list, saver_file = cnn_set_flow_graph(
data_stru, cnn_setting, input_map, False, logger)
keep_saver_file = saver_file
saver_file = cnn_setting.temp_obj_folder + class_saver_profix + keep_saver_file + "_top" + str(
top_k)
print saver_file
class_eval_value, class_train_time, class_test_time, class_predict_prob, fold_saver_file, fold_obj_file = cnn_train(
temp_train_x_matrix, temp_train_y_matrix, temp_test_x_matrix,
temp_test_y_matrix, num_classes, cnn_setting, train_x_placeholder,
output_y_placeholder, predict_y_prob, keep_prob_placeholder,
keeped_feature_list, saver_file, logger)
class_predict_y = np.argmax(class_predict_prob, axis=1)
class_accuracy, precision, recall, class_f1, tp, fp, tn, fn = f1_value_precision_recall_accuracy(
class_predict_y, temp_test_y_vector, 1)
if str(class_eval_value) == 'nan':
class_eval_value = 0
class_f1 = 0
logger.info(method + " f1 for class " + str(i) + ": " + str(class_f1))
logger.info(method + " accuracy for class " + str(i) + ": " +
str(class_accuracy))
logger.info(method + ' model saved: ' + fold_saver_file)
all_f1_value.append(class_f1)
all_train_time.append(class_train_time)
all_test_time.append(class_test_time)
all_predict_matrix[:, i] = class_predict_prob[:, 1]
#if i > 2:
# break
all_accuracy, all_predict_y = predict_matrix_with_prob_to_predict_accuracy(
all_predict_matrix, test_y_vector)
data_stru.num_classes = real_num_classes
return all_accuracy, all_f1_value, all_predict_y, all_train_time, all_test_time, all_predict_matrix