def project_cnn_feature_combined_rf_lda_analysis_with_highest(
feature_matrix, y_vector, logger=None, rf_estimator=50):
if logger is None:
logger = setup_logger('')
feature_matrix = np.squeeze(feature_matrix)
num_instance, num_attribute, num_map = feature_matrix.shape
predict = True
skip_count = 0
rf_time = 0
lda_time = 0
keep_avg_acc = -1
map_attr_imp_matrix = []
success_count = 0
for i in range(0, num_map):
map_feature_matrix = feature_matrix[:, :, i]
if np.any(map_feature_matrix) is False:
skip_count = skip_count + 1
continue
rf_lda_avg_acc = 0
#feature_value_vector = []
start_time = 0
rf_feature_value_vector, rf_model, rf_f1_value, rf_run_time = rf_feature_extraction(
map_feature_matrix, y_vector, predict, logger, rf_estimator)
rf_time = rf_time + time.time() - start_time
if rf_model is not None:
rf_lda_avg_acc = rf_feature_value_vector
feature_value_vector = rf_feature_value_vector * rf_f1_value
start_time = 0
lda_feature_vector, lda_model, lad_averaged_acc, lad_run_time = lda_feature_extraction(
map_feature_matrix, y_vector, predict, logger)
lda_time = lda_time + time.time() - start_time
if lda_model is not None:
rf_lda_avg_acc = rf_lda_avg_acc + lda_feature_vector
success_count = success_count + 1
#rf_lda_avg_acc = rf_f1_value + lad_averaged_acc
if keep_avg_acc < rf_lda_avg_acc:
keep_avg_acc = rf_lda_avg_acc
feature_value_vector = feature_value_vector + lda_feature_vector * lad_averaged_acc
map_attr_imp_matrix = [feature_value_vector]
elif keep_avg_acc == rf_lda_avg_acc:
map_attr_imp_matrix.append(feature_value_vector)
map_attr_imp_matrix = np.array(map_attr_imp_matrix)
logger.info("success count: " + str(success_count))
logger.info("highest acc:" + str(keep_avg_acc))
return map_attr_imp_matrix, rf_time + lda_time
def project_cnn_feature_combined_rf_analysis(feature_matrix,
y_vector,
logger=None,
rf_estimator=50):
if logger is None:
logger = setup_logger('')
feature_matrix = np.squeeze(feature_matrix)
num_instance, num_attribute, num_map = feature_matrix.shape
predict = True
skip_count = 0
rf_time = 0
lda_time = 0
map_attr_imp_matrix = []
success_count = 0
feature_matrix_2d = feature_matrix.reshape(num_instance,
num_attribute * num_map)
start_time = time.time()
rf_feature_value_vector, rf_model, rf_f1_value, rf_run_time = rf_feature_extraction(
feature_matrix_2d, y_vector, predict, logger, rf_estimator)
rf_time = rf_time + time.time() - start_time
rf_feature_value_vector = rf_feature_value_vector.reshape(
num_attribute, num_map)
rf_feature_value_vector = np.sum(rf_feature_value_vector, axis=1)
sum_value = sum(rf_feature_value_vector)
rf_feature_value_vector = rf_feature_value_vector / float(sum_value)
rf_feature_value_vector = rf_feature_value_vector * rf_f1_value
rf_class_attr_list = map_attr_imp_analysis(rf_feature_value_vector, logger)
logger.info("rf feature value: " + str(rf_feature_value_vector.shape))
logger.info("rf f1 value: " + str(rf_f1_value))
logger.info("rf only attr:" + str(rf_class_attr_list))
feature_value_vector = rf_feature_value_vector
return feature_value_vector, rf_time + lda_time
def project_cnn_feature_combined_rf_lda_analysis(feature_matrix,
y_vector,
logger=None,
rf_estimator=50):
if logger is None:
logger = setup_logger('')
#feature_matrix = np.squeeze(feature_matrix)
num_instance, num_attribute, num_map = feature_matrix.shape
predict = True
skip_count = 0
rf_time = 0
lda_time = 0
map_attr_imp_matrix = []
success_count = 0
feature_matrix_2d = feature_matrix.reshape(num_instance,
num_attribute * num_map)
start_time = 0
rf_feature_value_vector, rf_model, rf_f1_value, rf_run_time = rf_feature_extraction(
feature_matrix_2d, y_vector, predict, logger, rf_estimator)
rf_time = rf_time + time.time() - start_time
start_time = 0
lda_feature_value_vector, lda_model, lda_f1_value, lda_run_time = lda_feature_extraction(
feature_matrix_2d, y_vector, predict, logger)
lda_time = time.time() - start_time
#print rf_feature_value_vector
#print np.sum(rf_feature_value_vector)
#print lda_feature_value_vector
#print np.sum(lda_feature_value_vector)
rf_feature_value_vector = rf_feature_value_vector.reshape(
num_attribute, num_map)
rf_feature_value_vector = np.sum(rf_feature_value_vector, axis=1)
sum_value = sum(rf_feature_value_vector)
rf_feature_value_vector = rf_feature_value_vector / float(sum_value)
rf_feature_value_vector = rf_feature_value_vector * rf_f1_value
rf_class_attr_list = map_attr_imp_analysis(rf_feature_value_vector, logger)
logger.info("rf feature value: " + str(rf_feature_value_vector))
logger.info("rf f1 value: " + str(rf_f1_value))
logger.info("rf only attr:" + str(rf_class_attr_list))
feature_value_vector = rf_feature_value_vector
if lda_feature_value_vector is not None:
lda_feature_value_vector = lda_feature_value_vector.reshape(
num_attribute, num_map)
lda_feature_value_vector = np.sum(lda_feature_value_vector, axis=1)
sum_value = sum(lda_feature_value_vector)
lda_feature_value_vector = lda_feature_value_vector / float(sum_value)
lda_feature_value_vector = lda_feature_value_vector * lda_f1_value
lda_class_attr_list = map_attr_imp_analysis(lda_feature_value_vector,
logger)
lda_max = max(lda_feature_value_vector)
logger.info("lda only attr:" + str(lda_class_attr_list))
logger.info("lda feature value: " + str(lda_feature_value_vector))
logger.info("lda f1 value: " + str(lda_f1_value))
logger.info("max lda value: " + str(lda_max))
if lda_max < 0.9:
feature_value_vector = feature_value_vector + lda_feature_value_vector
#if rf_f1_value > lda_f1_value:
# feature_value_vector = rf_feature_value_vector
#elif rf_f1_value < lda_f1_value:
# feature_value_vector = lda_feature_value_vector
#else:
# feature_value_vector = rf_feature_value_vector + lda_feature_value_vector
sum_value = sum(feature_value_vector)
feature_value_vector = feature_value_vector / float(sum_value)
class_attr_list = map_attr_imp_analysis(feature_value_vector, logger)
logger.info("overall rf and lda feature value: " +
str(feature_value_vector))
logger.info("rf and lda attr:" + str(class_attr_list))
return feature_value_vector, rf_time + lda_time
