def multi_proj_feature_classification(
parameter_file,
file_keyword,
function_keyword="multi_proj_feature_classification"):
data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, cnn_obj_folder, cnn_temp_folder, cnn_setting_file = read_feature_classification(
parameter_file, function_keyword)
log_folder = init_folder(log_folder)
if method == 'cnn':
return projected_cnn_classification_main(parameter_file, file_keyword)
else:
# Need to check the rest
return False
print data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, cnn_obj_folder, cnn_temp_folder, cnn_setting_file
data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len,
class_column)
print obj_folder
file_list = list_files(data_folder)
obj_list = list_files(obj_folder)
class_column = 0
header = True
save_obj_folder = obj_folder[:-1] + "_" + method + "_out"
save_obj_folder = init_folder(save_obj_folder)
delimiter = ' '
loop_count = -1
for train_file in file_list:
if file_keyword not in train_file:
continue
loop_count = loop_count + 1
file_key = train_file.replace('.txt', '')
log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(
class_id) + '_top' + str(top_k) + '_' + method + '.log'
print "log file: " + log_file
logger = setup_logger(log_file, 'logger_' + str(loop_count))
logger.info('\nlog file: ' + log_file)
logger.info(train_file)
logger.info('method: ' + method)
logger.info('============')
found_obj_file = ''
for obj_file in obj_list:
if file_key in obj_file:
found_obj_file = obj_file
break
if found_obj_file == '':
raise Exception('No obj file found')
print found_obj_file
found_obj_file = obj_folder + found_obj_file
feature_array = load_obj(found_obj_file)[0]
feature_array = np.array(feature_array)
logger.info("feature array shape: " + str(feature_array.shape))
test_file = train_file.replace('train', 'test')
train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading_with_attrnum(
data_folder + train_file, data_folder + test_file, class_column,
delimiter, header)
if loop_count == 0:
logger.info('train matrix shape: ' + str(train_x_matrix.shape))
logger.info('train label shape: ' + str(train_y_vector.shape))
logger.info('test matrix shape: ' + str(test_x_matrix.shape))
logger.info('test label shape: ' + str(test_y_vector.shape))
train_x_matrix = train_test_transpose(train_x_matrix, attr_num,
attr_len, False)
test_x_matrix = train_test_transpose(test_x_matrix, attr_num, attr_len,
False)
data_stru.attr_num = top_k
fold_accuracy, fold_f1_value, fold_predict_y, fold_train_time, fold_test_time, fold_predict_matrix = run_feature_projected_classification(
train_x_matrix, train_y_vector, test_x_matrix, test_y_vector,
feature_array, top_k, method, class_id, logger)
logger.info("Fold F1: " + str(fold_f1_value))
logger.info(method + ' fold training time (sec):' +
str(fold_train_time))
logger.info(method + ' fold testing time (sec):' + str(fold_test_time))
logger.info(method + ' fold accuracy: ' + str(fold_accuracy))
logger.info("save obj to " + save_obj_folder + file_key + "_" +
method + "_project_" + method + "_result.ckpt")
save_obj([
fold_accuracy, fold_f1_value, fold_predict_y, fold_train_time,
fold_test_time, fold_predict_matrix
], save_obj_folder + file_key + "_" + method + "_project_" + method +
"_result.ckpt")
def backward_multitime_main(parameter_file="../../parameters/",
file_keyword="train_",
n_selected_features=15):
function_keyword = "backward_wrapper"
#data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_feature_classification(parameter_file, function_keyword)
data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_feature_classification(
parameter_file, function_keyword)
print data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file
log_folder = init_folder(log_folder)
out_obj_folder = init_folder(out_obj_folder)
out_model_folder = init_folder(out_model_folder)
data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len,
class_column)
file_list = list_files(data_folder)
file_count = 0
class_column = 0
header = True
delimiter = ' '
loop_count = -1
for train_file in file_list:
if file_keyword not in train_file:
continue
loop_count = loop_count + 1
file_key = train_file.replace('.txt', '')
log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(
class_id) + '_' + method + '.log'
print "log file: " + log_file
logger = setup_logger(log_file, 'logger_' + str(loop_count))
logger.info('\nlog file: ' + log_file)
logger.info(train_file)
logger.info('method: ' + method)
logger.info('============')
test_file = train_file.replace('train', 'test')
train_x_matrix, train_y_vector, test_x_matrix, test_y_vector = train_test_file_reading(
data_folder + train_file, data_folder + test_file, class_column,
delimiter, header)
n_samples, n_col = train_x_matrix.shape
train_x_matrix = train_x_matrix.reshape(n_samples, attr_num, attr_len)
n_samples, n_col = test_x_matrix.shape
test_x_matrix = test_x_matrix.reshape(n_samples, attr_num, attr_len)
if file_count == 0:
logger.info('train matrix shape: ' + str(train_x_matrix.shape))
logger.info('train label shape: ' + str(train_y_vector.shape))
logger.info('test matrix shape: ' + str(test_x_matrix.shape))
logger.info('test label shape: ' + str(test_y_vector.shape))
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
for c in range(min_class, max_class):
logger.info("Class: " + str(c))
temp_train_y_vector = np.where(train_y_vector == c, 1, 0)
temp_test_y_vector = np.where(test_y_vector == c, 1, 0)
top_features = backward_multitime(
train_x_matrix, temp_train_y_vector, test_x_matrix,
temp_test_y_vector, n_selected_features, data_keyword, method,
cnn_setting_file, logger)
logger.info("Top Features For Class " + str(c) + ": " +
str(top_features))
logger.info("End Of Class: " + str(c))
def forward_multitime_main(parameter_file="../../parameters/",
file_keyword="train_"):
function_keyword = "forward_wrapper"
#data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_feature_classification(parameter_file, function_keyword)
data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_feature_classification(
parameter_file, function_keyword)
print data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file
if data_keyword == "dsa" or data_keyword == "toy":
n_selected_features = 15
num_classes = 19
elif data_keyword == "rar":
n_selected_features = 30
num_classes = 33
elif data_keyword == "arc" or data_keyword == "fixed_arc":
n_selected_features = 30
num_classes = 18
elif data_keyword == "asl":
n_selected_features = 6
num_classes = 95
else:
raise Exception("Please fullfill the data basic information first!")
log_folder = init_folder(log_folder)
#out_obj_folder = init_folder(out_obj_folder)
#out_model_folder = init_folder(out_model_folder)
data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len,
class_column)
file_list = list_files(data_folder)
file_count = 0
class_column = 0
header = True
delimiter = ' '
loop_count = -1
##########
###already remove later
#already_obj_folder = "../../object/" + data_keyword + "/forward_wrapper/"
#already_obj_list = list_files(already_obj_folder)
###end of already remove later
for train_file in file_list:
if file_keyword not in train_file:
continue
loop_count = loop_count + 1
file_key = train_file.replace('.txt', '')
#already_obj_file = ""
already = False
#for already_obj_file in already_obj_list:
# if file_key in already_obj_file and method in already_obj_file:
# already = True
# break
##########
###already part
#if already is True:
# already_class_feature = load_obj(already_obj_folder + already_obj_file)[0]
#else:
# log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(class_id) + '_' + method + '.log'
# already_class_feature = None
###end of already part
log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(
class_id) + '_' + method + "_top" + str(
n_selected_features) + '_already' + str(already) + '.log'
print "log file: " + log_file
logger = setup_logger(log_file, 'logger_' + str(loop_count))
logger.info('\nlog file: ' + log_file)
logger.info(train_file)
logger.info('method: ' + method)
logger.info('============')
test_file = train_file.replace('train', 'test')
train_x_matrix, train_y_vector, test_x_matrix, test_y_vector = train_test_file_reading(
data_folder + train_file, data_folder + test_file, class_column,
delimiter, header)
n_samples, n_col = train_x_matrix.shape
train_x_matrix = train_x_matrix.reshape(n_samples, attr_num, attr_len)
n_samples, n_col = test_x_matrix.shape
test_x_matrix = test_x_matrix.reshape(n_samples, attr_num, attr_len)
if file_count == 0:
logger.info('train matrix shape: ' + str(train_x_matrix.shape))
logger.info('train label shape: ' + str(train_y_vector.shape))
logger.info('test matrix shape: ' + str(test_x_matrix.shape))
logger.info('test label shape: ' + str(test_y_vector.shape))
min_class = min(train_y_vector)
max_class = max(train_y_vector) + 1
for c in range(min_class, max_class):
logger.info("Class: " + str(c))
already_feature = []
#if already_class_feature is not None:
# class_already = already_class_feature[c, :]
# for already_f in class_already:
# already_feature.append(already_f)
# logger.info("already features: " +file_key + " with class " + str(c) + ": " + str(already_feature))
temp_train_y_vector = np.where(train_y_vector == c, 1, 0)
temp_test_y_vector = np.where(test_y_vector == c, 1, 0)
#print already_feature
top_features = forward_multitime(
train_x_matrix, temp_train_y_vector, test_x_matrix,
temp_test_y_vector, n_selected_features, data_keyword,
file_key, method, cnn_setting_file, logger, already_feature)
logger.info("Top Features For Class " + str(c) + ": " +
str(top_features))
logger.info("End Of Class: " + str(c))
def best_forward_multitime_main(parameter_file="../../parameters/", file_keyword="train_", function_keyword="best_forward_multitime"):
#data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_all_feature_classification(parameter_file, function_keyword)
data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_feature_classification(parameter_file, function_keyword)
print data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file
function_keyword = function_keyword + "_" + method
if data_keyword == "dsa" or data_keyword == "toy":
n_selected_features = 15
num_classes = 19
elif data_keyword == "rar":
n_selected_features = 30
num_classes = 33
elif data_keyword == "arc" or data_keyword == "fixed_arc":
n_selected_features = 30
num_classes = 18
elif data_keyword == "asl":
n_selected_features = 6
num_classes = 95
else:
raise Exception("Please fullfill the data basic information first!")
keep_k = 5
log_folder = init_folder(log_folder)
#out_obj_folder = init_folder(out_obj_folder)
#out_model_folder = init_folder(out_model_folder)
data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len, class_column)
file_list = list_files(data_folder)
file_count = 0
class_column = 0
header = True
delimiter = ' '
loop_count = -1
for train_file in file_list:
if file_keyword not in train_file:
continue
loop_count = loop_count + 1
file_key = train_file.replace('.txt', '')
log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(class_id) + '_' + method + "_top" + str(n_selected_features) +'.log'
print "log file: " + log_file
logger = setup_logger(log_file, 'logger_' + str(loop_count))
logger.info('\nlog file: ' + log_file)
logger.info(train_file)
logger.info('method: ' + method)
logger.info('============')
test_file = train_file.replace('train', 'test')
train_x_matrix, train_y_vector, test_x_matrix, test_y_vector = train_test_file_reading(
data_folder + train_file, data_folder + test_file, class_column, delimiter, header)
n_samples, n_col = train_x_matrix.shape
train_x_matrix = train_x_matrix.reshape(n_samples, attr_num, attr_len)
n_samples, n_col = test_x_matrix.shape
test_x_matrix = test_x_matrix.reshape(n_samples, attr_num, attr_len)
if file_count == 0:
logger.info('train matrix shape: ' + str(train_x_matrix.shape))
logger.info('train label shape: ' + str(train_y_vector.shape))
logger.info('test matrix shape: ' + str(test_x_matrix.shape))
logger.info('test label shape: ' + str(test_y_vector.shape))
min_class = min(train_y_vector)
max_class = max(train_y_vector) + 1
for c in range(min_class, max_class):
logger.info("Class: " + str(c))
temp_train_y_vector = np.where(train_y_vector == c, 1, 0)
temp_test_y_vector = np.where(test_y_vector == c, 1, 0)
top_features = fixed_width_forward_multitime(train_x_matrix, temp_train_y_vector, test_x_matrix, temp_test_y_vector, n_selected_features, keep_k, data_keyword, file_key, method, cnn_setting_file, logger)
logger.info("Top Features For Class " +str(c) + ": " + str(top_features))
logger.info("End Of Class: " + str(c))
def multi_projected_cnn_classification_main(parameter_file, file_keyword, function_keyword="multi_proj_classification"):
data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, cnn_obj_folder, cnn_temp_folder, cnn_setting_file = read_feature_classification(parameter_file, function_keyword)
obj_keyword = obj_folder.split('/')[-2]
model_saved_folder = "../../object/" + data_keyword + "/projected_classification/" + obj_keyword + "_top" + str(top_k) + "_cnn_model_folder/"
print obj_keyword
print cnn_obj_folder
print model_saved_folder
top_keyword = "_top" + str(top_k) + "."
group_all = False
log_folder = init_folder(log_folder)
#cnn_obj_folder = init_folder(cnn_obj_folder)
#cnn_temp_folder = init_folder(cnn_temp_folder)
data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len, class_column)
file_list = list_files(data_folder)
obj_list = list_files(obj_folder)
file_count = 0
class_column = 0
header = True
cnn_setting = return_cnn_setting_from_file(cnn_setting_file)
cnn_setting.save_obj_folder = cnn_obj_folder
cnn_setting.temp_obj_folder = cnn_temp_folder
cnn_setting.eval_method = 'f1'
#init_folder(cnn_obj_folder)
#init_folder(cnn_temp_folder)
save_obj_folder = "../../object/" + data_keyword + "/" + function_keyword + "/" + obj_keyword + "/"
save_obj_folder = init_folder(save_obj_folder)
delimiter = ' '
loop_count = -1
for train_file in file_list:
if file_keyword not in train_file:
continue
loop_count = loop_count + 1
file_key = train_file.replace('.txt', '')
log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(class_id) + '_top' + str(top_k) + '_' + method + '.log'
print "log file: " + log_file
logger = setup_logger(log_file, 'logger_' + str(loop_count))
logger.info('\nlog file: ' + log_file)
logger.info(train_file)
logger.info('cnn setting:\n ' + cnn_setting.to_string())
logger.info('method: ' + method)
logger.info('============')
found_obj_file = ''
for obj_file in obj_list:
if file_key in obj_file:
found_obj_file = obj_file
break
if found_obj_file == '':
raise Exception('No obj file found')
#
found_obj_file = obj_folder + found_obj_file
feature_dict = load_obj(found_obj_file)[0]
feature_dict = np.array(feature_dict)
logger.info("feature array shape: " + str(feature_dict.shape))
test_file = train_file.replace('train', 'test')
train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading_with_attrnum(
data_folder + train_file, data_folder + test_file, class_column, delimiter, header)
train_x_matrix = train_test_transpose(train_x_matrix, attr_num, attr_len, False)
test_x_matrix = train_test_transpose(test_x_matrix, attr_num, attr_len, False)
if file_count == 0:
logger.info('train matrix shape: ' + str(train_x_matrix.shape))
logger.info('train label shape: ' + str(train_y_vector.shape))
logger.info('test matrix shape: ' + str(test_x_matrix.shape))
logger.info('test label shape: ' + str(test_y_vector.shape))
logger.info("topk: " + str(top_k) )
data_stru.attr_num = top_k
fold_accuracy, fold_f1_list, fold_load_time, fold_test_time = run_load_predict_cnn(file_key, model_saved_folder, feature_dict, top_k, test_x_matrix, test_y_vector, data_stru, cnn_setting, group_all, save_obj_folder, logger)
logger.info("Fold ACC: " + str(fold_accuracy))
logger.info("Fold F1 list: " + str(fold_f1_list))
logger.info(method + ' fold training time (sec):' + str(fold_load_time))
logger.info(method + ' fold testing time (sec):' + str(fold_test_time))
def global_classification_main(parameter_file, file_keyword):
function_keyword = "global_classification"
data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, cnn_obj_folder, cnn_temp_folder, cnn_setting_file = read_feature_classification(
parameter_file, function_keyword)
data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len,
class_column)
file_list = list_files(data_folder)
obj_list = list_files(obj_folder)
file_count = 0
class_column = 0
header = True
cnn_setting = return_cnn_setting_from_file(cnn_setting_file)
cnn_setting.save_obj_folder = cnn_obj_folder
cnn_setting.temp_obj_folder = cnn_temp_folder
cnn_setting.eval_method = 'f1'
init_folder(cnn_obj_folder)
init_folder(cnn_temp_folder)
all_result_matrix = np.zeros((10, num_classes))
train_file_vector = []
prediction_matrix = []
f1_value_matrix = []
accuracy_vector = []
delimiter = ' '
all_accuracy = 0
all_train_time = 0
all_test_time = 0
loop_count = -1
for train_file in file_list:
if file_keyword not in train_file:
continue
loop_count = loop_count + 1
file_key = train_file.replace('.txt', '')
log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(
class_id) + '_top' + str(top_k) + '_' + method + '.log'
print "log file: " + log_file
logger = setup_logger(log_file, 'logger_' + str(loop_count))
logger.info('\nlog file: ' + log_file)
logger.info(train_file)
logger.info('cnn setting:\n ' + cnn_setting.to_string())
logger.info('method: ' + method)
logger.info('============')
continue
found_obj_file = ''
for obj_file in obj_list:
if file_key in obj_file:
found_obj_file = obj_file
break
if found_obj_file == '':
raise Exception('No obj file found')
print found_obj_file
print cnn_setting.save_obj_folder + file_key + "_" + method + "_projected_result.ckpt"
#
found_obj_file = obj_folder + found_obj_file
feature_dict = load_obj(found_obj_file)[0]
feature_dict = np.array(feature_dict)
logger.info("feature array shape: " + str(feature_dict.shape))
test_file = train_file.replace('train', 'test')
train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading_with_attrnum(
data_folder + train_file, data_folder + test_file, class_column,
delimiter, header)
if file_count == 0:
logger.info('train matrix shape: ' + str(train_x_matrix.shape))
logger.info('train label shape: ' + str(train_y_vector.shape))
logger.info('test matrix shape: ' + str(test_x_matrix.shape))
logger.info('test label shape: ' + str(test_y_vector.shape))
train_x_matrix = train_test_transpose(train_x_matrix, attr_num,
attr_len, False)
test_x_matrix = train_test_transpose(test_x_matrix, attr_num, attr_len,
False)
data_stru.attr_num = top_k
fold_accuracy, fold_avg_eval, fold_predict_y, fold_train_time, fold_test_time, fold_predict_matrix = run_feature_projected_cnn(
train_x_matrix, train_y_vector, test_x_matrix, test_y_vector,
data_stru, cnn_setting, feature_dict, top_k,
file_key + '_count' + str(file_count), class_id, logger)
prediction_matrix.append(fold_predict_y)
logger.info("Fold F1: " + str(fold_f1_value_list))
accuracy_vector.append(fold_accuracy)
all_accuracy = all_accuracy + fold_accuracy
all_train_time = all_train_time + fold_train_time
all_test_time = all_test_time + fold_test_time
logger.info(method + ' fold accuracy: ' + str(fold_accuracy))
logger.info(method + ' fold training time (sec):' +
str(fold_train_time))
logger.info(method + ' fold testing time (sec):' + str(fold_test_time))
save_obj([
fold_accuracy, fold_avg_eval, fold_predict_y, fold_train_time,
fold_test_time, fold_predict_matrix
], save_obj_folder + file_key + "_" + method +
"_global_cnn_result.ckpt")