def backward_multitime(
train_x,
train_y,
test_x,
test_y,
n_selected_features,
data_key="test",
method="cnn",
cnn_setting_file="../../parameters/cnn_model_parameter.txt",
logger=None):
"""
This function implements the backward feature selection algorithm based on decision tree
Input
-----
train_x: {3d numpy array matrix}, shape (n_samples, n_features, time_length)
input data
train_y: {1d numpy array vector}, shape (n_samples,)
input class labels
test_x: {3d numpy array matrix}, shape (n_samples, n_features, time_length)
input data
test_y: {1d numpy array vector}, shape (n_samples,)
input class labels
Output
------
F: {numpy array}, shape (n_features, )
index of selected features
"""
if logger is None:
log_file = ""
logger = setup_logger(log_file)
train_samples, n_features, time_length = train_x.shape
f_score = []
eval_method = "f1"
if method == "cnn":
min_class = min(train_y)
max_class = max(train_y)
num_classes = max_class - min_class + 1
data_stru = data_structure(num_classes, min_class, n_features,
time_length)
cnn_setting = return_cnn_setting_from_file(cnn_setting_file)
logger.info('cnn setting:\n ' + cnn_setting.to_string())
saver_file_profix = "../../object/" + data_key + "/backward_multitime/" + method
saver_file_profix = init_folder(saver_file_profix)
saver_file_profix = saver_file_profix + return_cnn_keyword(cnn_setting)
eval_method = cnn_setting.eval_method
all_f_eval_value, all_f_train_time, all_f_test_time, predict_proba, saver_file, feature_list_obj_file, relu_base_array = model_evaluation_cnn(
train_x, train_y, test_x, test_y, data_stru, cnn_setting,
saver_file_profix, logger)
elif method == "rf":
model = RandomForestClassifier(n_estimators=50, random_state=0)
all_f_eval_value, all_f_train_time, all_f_test_time = model_evaluation_rf(
train_x, train_y, test_x, test_y, model, logger)
logger.info("With ALL Feature")
logger.info(method + " " + eval_method + " Value For ALL Feature: " +
str(all_f_eval_value))
logger.info(method + " Training time (sec): " + str(all_f_train_time))
logger.info(method + " Testing time (sec): " + str(all_f_test_time))
# selected feature set, initialized to contain all features
F = range(n_features)
count = n_features
iter_num = 0
while count > n_selected_features:
max_eval_value = -1
for i in range(n_features):
if i in F:
F.remove(i)
train_x_tmp = train_x[:, F, :]
test_x_tmp = test_x[:, F, :]
if method == "cnn":
eval_value, train_run_time, test_run_time, predict_proba, saver_file, feature_list_obj_file, relu_based_array = model_evaluation_cnn(
train_x_tmp, train_y, test_x_tmp, test_y, data_stru,
cnn_setting, saver_file_profix, logger)
f_eval_value = all_f_eval_value - eval_value
elif method == "rf":
eval_value, train_run_time, test_run_time = model_evaluation_rf(
train_x_tmp, train_y, test_x_tmp, test_y, model,
logger)
f_eval_value = all_f_eval_value - eval_value
logger.info("Without Feature " + str(i) + ": ")
logger.info(method + eval_method + " Value For Feature " +
str(i) + ": " + str(f_eval_value))
logger.info(method + " Training time (sec): " +
str(train_run_time))
logger.info(method + " Testing time (sec): " +
str(test_run_time))
f_score.append(f_eval_value)
F.append(i)
# record the feature which results in the largest accuracy
if eval_value > max_eval_value:
max_eval_value = eval_value
idx = i
logger.info("For iter " + str(iter_num))
logger.info("Eval score vector: " + str(f_score))
logger.info("The removed attribute is: " + str(idx))
# delete the feature which results in the largest accuracy
F.remove(idx)
count -= 1
iter_num = iter_num + 1
return np.array(F)
def cnn_load_main(parameter_file, file_keyword, function_keyword="cnn_classification"):
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)
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
cnn_setting = return_cnn_setting_from_file(cnn_setting_file)
cnn_setting.out_obj_folder = out_obj_folder
cnn_setting.out_model_folder = out_model_folder
cnn_setting.full_feature_num = 400
init_folder(out_obj_folder)
init_folder(out_model_folder)
print (out_model_folder)
model_file_list = list_files(out_model_folder)
result_obj_folder = obj_folder + method +"_result_folder"
result_obj_folder = init_folder(result_obj_folder)
logger = setup_logger('')
delimiter = ' '
loop_count = -1
saver_file_profix = ""
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', '')
saver_file_profix = file_key
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(data_folder + train_file, data_folder + test_file, '', class_column, delimiter, header)
data_group, attr_num = train_test_file_reading(data_folder + train_file, data_folder + test_file, '', class_column, delimiter, header)
train_x_matrix = data_group.train_x_matrix
train_y_vector = data_group.train_y_vector
test_x_matrix = data_group.test_x_matrix
test_y_vector = data_group.test_y_vector
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)
train_y_matrix = y_vector_to_matrix(train_y_vector, num_classes)
test_y_matrix = y_vector_to_matrix(test_y_vector, num_classes)
found_model_file = ""
for model_file in model_file_list:
if model_file.startswith(file_key):
model_file = model_file.split('.')[0]
found_model_file = out_model_folder + model_file + ".ckpt"
break
if found_model_file == "":
raise Exception("No model object file found!!!")
print(found_model_file)
cnn_session, logits_out, train_x_placeholder, keep_prob_placeholder, keeped_feature_list = load_model(found_model_file, data_stru, cnn_setting, logger)
last_conv_tensor = keeped_feature_list[0]
train_last_conv = cnn_session.run(last_conv_tensor, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0})
test_last_conv = cnn_session.run(last_conv_tensor, feed_dict={train_x_placeholder: test_x_matrix, keep_prob_placeholder: 1.0})
drop_num = 10
print(np.squeeze(test_last_conv[1, :, :, :]))
test_last_conv = top_attr_x_matrix(test_last_conv, drop_num)
print(np.squeeze(test_last_conv[1, :, :, :]))
train_last_conv = top_attr_x_matrix(train_last_conv, drop_num)
output_y_placeholder = tf.placeholder(tf.float32, [None, num_classes])
actual = tf.argmax(output_y_placeholder, axis=1)
prediction = tf.argmax(logits_out, axis=1)
correct_prediction = tf.equal(actual, prediction)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
ori_pred_y_vector = cnn_session.run(prediction, feed_dict={train_x_placeholder: test_x_matrix, keep_prob_placeholder: 1.0})
test_accuracy = cnn_session.run(accuracy, feed_dict={train_x_placeholder: test_x_matrix, keep_prob_placeholder: 1.0, output_y_placeholder: test_y_matrix})
cnn_session.close()
kernel_eval_matrix, ref_kernel_eval_matrix = last_conv_analysis(train_last_conv, train_y_vector)
print(kernel_eval_matrix.shape)
print(kernel_eval_matrix)
train_ins_len = len(train_y_vector)
test_ins_len = len(test_y_vector)
batch_size = 100
layer_list = np.array([400])
max_epoch = 10
stop_threshold = 0.99
activation_fun = 3
std_value = 0.02
eval_method = "acc"
saver_file = './test_1.save'
nn_setting = nn_parameters(layer_list, batch_size, max_epoch, stop_threshold, activation_fun, std_value, eval_method, saver_file)
all_pred_prob = []
for c in range(num_classes):
train_y_vector_class = np.zeros((train_ins_len))
index_class = np.where(train_y_vector==c)[0]
train_y_vector_class[index_class] = 1
train_y_m_class = y_vector_to_matrix(train_y_vector_class, 2)
test_y_vector_class = np.zeros((test_ins_len))
index_class = np.where(test_y_vector==c)[0]
test_y_vector_class[index_class] = 1
test_y_m_class = y_vector_to_matrix(test_y_vector_class, 2)
keep_num = 5
kernel_index = kernel_eval_matrix[c, 0:keep_num]
ref_kernel_index = ref_kernel_eval_matrix[c, 0:keep_num]
print("kernel index " + str(kernel_index))
print("ref kernel index " + str(ref_kernel_index))
kernel_index = np.concatenate((kernel_index, ref_kernel_index), axis=0)
print("union index " + str(kernel_index))
kernel_index = np.unique(kernel_index)
print("unique index " + str(kernel_index))
kernel_index = ref_kernel_eval_matrix[c, 0:keep_num]
train_x_class = train_last_conv[:, :, :, kernel_index]
test_x_class = test_last_conv[:, :, :, kernel_index]
print(train_x_class.shape)
reshape_col = 45 * len(kernel_index)
train_x_class = train_x_class.reshape((train_ins_len, reshape_col))
test_x_class = test_x_class.reshape((test_ins_len, reshape_col))
c_eval_value, c_train_time, c_test_time, c_predict_proba = run_nn(train_x_class, train_y_m_class, test_x_class, test_y_m_class, nn_setting)
all_pred_prob.append(c_predict_proba[:, 1]-c_predict_proba[:, 0])
all_pred_prob = np.array(all_pred_prob)
print(all_pred_prob.shape)
pred_vector = np.argmax(all_pred_prob, axis=0)
print(pred_vector)
print(all_pred_prob[:, 0])
print(all_pred_prob[:, 1])
print(all_pred_prob[:, 2])
final_accuracy = accuracy_score(pred_vector, test_y_vector)
avg_acc, ret_str = averaged_class_based_accuracy(ori_pred_y_vector, test_y_vector)
print("original avg acc" + str(avg_acc))
print("original accuracy: " + str(test_accuracy))
print(ret_str)
avg_acc, ret_str = averaged_class_based_accuracy(pred_vector, test_y_vector)
print("avg acc" + str(avg_acc))
print("new accuracy: " + str(final_accuracy))
print(ret_str)
load_result_analysis(all_pred_prob, test_y_vector)
sdfds
output_y_placeholder = tf.placeholder(tf.float32, [None, num_classes])
actual = tf.argmax(output_y_placeholder, axis=1)
prediction = tf.argmax(logits_out, axis=1)
correct_prediction = tf.equal(actual, prediction)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
test_eval_value = accuracy.eval(feed_dict={train_x_placeholder: test_x_matrix, output_y_placeholder: test_y_matrix, keep_prob_placeholder: 1.0})
print("fisrt")
print(test_eval_value)
conv_count = 1
drop_ratio = 0.1
#conv_variable_up_main(cnn_session, conv_count, drop_ratio)
weight_name = "conv_w_" + str(0) + ":0"
bias_name = "conv_b_" + str(0) + ":0"
ori_weight_variable = tf.get_default_graph().get_tensor_by_name(weight_name)
ori_bias_variable = tf.get_default_graph().get_tensor_by_name(bias_name)
weight_variable = tf.get_default_graph().get_tensor_by_name(weight_name)
bias_variable = tf.get_default_graph().get_tensor_by_name(bias_name)
ori_weight_variable = cnn_session.run(weight_variable)
ori_bias_variable = cnn_session.run(bias_variable)
train_drop_acc = []
test_drop_acc = []
for drop_i in range(50):
drop_weight_variable = np.copy(ori_weight_variable)
drop_bias_variable = np.copy(ori_bias_variable)
drop_index = []
drop_index.append(drop_i)
up_fir_weight, up_fir_bias = conv_variable_up(drop_weight_variable, drop_bias_variable, drop_index)
weight_assign = tf.assign(weight_variable, up_fir_weight)
bias_assign = tf.assign(bias_variable, up_fir_bias)
cnn_session.run(weight_assign)
cnn_session.run(bias_assign)
up_bias_variable = tf.get_default_graph().get_tensor_by_name(bias_name)
up_bias_variable_val = cnn_session.run(bias_variable)
train_eval_value = accuracy.eval(feed_dict={train_x_placeholder: train_x_matrix, output_y_placeholder: train_y_matrix, keep_prob_placeholder: 1.0})
train_drop_acc.append(train_eval_value)
test_eval_value = accuracy.eval(feed_dict={train_x_placeholder: test_x_matrix, output_y_placeholder: test_y_matrix, keep_prob_placeholder: 1.0})
test_drop_acc.append(test_eval_value)
print ("Drop " + str(drop_i))
print(train_eval_value)
print(test_eval_value)
print(train_drop_acc)
print(train_drop_acc.argsort())
print(test_drop_acc)
print(test_drop_acc.argsort())
sdfs
print("HERE")
fir_weight_variable_val = np.squeeze(fir_weight_variable_val)
kernel_dist_val = cnn_session.run(kernel_dist)
keep_index_val = cnn_session.run(keep_index)
print(fir_weight_variable_val.shape)
print(np.amax(fir_weight_variable_val, axis=1))
print(np.amin(fir_weight_variable_val, axis=1))
print(np.mean(fir_weight_variable_val, axis=1))
mean_row = np.mean(fir_weight_variable_val, axis=-1)
print(mean_row.shape)
dist_list = []
for r in range(40):
row = fir_weight_variable_val[:, r]
dist_list.append(np.linalg.norm(row-mean_row))
print (dist_list)
print(kernel_dist_val)
print(keep_index_val)
print(sorted(dist_list))
print("!!!")
#conv_variable_up(fir_weight_variable_val, fir_bias_variable_val)
sdfsd
train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading(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)
train_x_matrix = test_x_matrix[0:1, :, :, :]
#plot_2dmatrix(np.squeeze(train_x_matrix)[:, 0:5])
fir_out_tensor = tf.nn.conv2d(train_x_placeholder, fir_weight_variable, strides=[1, 1, 1, 1], padding='VALID') + fir_bias_variable
fir_out_tensor = tf.nn.relu(fir_out_tensor)
print(fir_out_tensor.get_shape())
fir_analysis_tensor = tf.reduce_max(fir_out_tensor, [1])
print(fir_analysis_tensor.get_shape())
fir_analysis_tensor = tf.reduce_max(fir_analysis_tensor, [1])
fir_analysis_tensor = tf.reduce_mean(fir_analysis_tensor, [0])
top_k_indices = tf.nn.top_k(fir_analysis_tensor, 10).indices
top_k_values = tf.nn.top_k(fir_analysis_tensor, 10).values
top_fir_out_tensor = tf.gather(fir_out_tensor, top_k_indices, axis=3)
sec_weight_variable = tf.get_default_graph().get_tensor_by_name("conv_w_1:0")
sec_bias_variable = tf.get_default_graph().get_tensor_by_name("conv_b_1:0")
sec_out_tensor = tf.nn.conv2d(fir_out_tensor, sec_weight_variable, strides=[1, 1, 1, 1], padding='VALID') + sec_bias_variable
sec_out_tensor = tf.nn.relu(sec_out_tensor)
sec_weight_var_val = cnn_session.run(sec_weight_variable)
#print(np.squeeze(sec_weight_var_val))
#sdfds
#plot_2dmatrix(fir_weight_var_val[:, 4])
#sdf
#print(fir_weight_var_val.T)
fir_out_tensor_val = cnn_session.run(fir_out_tensor, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0})
print(fir_out_tensor_val.shape)
top_fir_out_tensor = cnn_session.run(top_fir_out_tensor, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0})
print(top_fir_out_tensor.shape)
fir_analysis_tensor_val = cnn_session.run(fir_analysis_tensor, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0})
print(fir_analysis_tensor.shape)
top_k_indices_val = cnn_session.run(top_k_indices, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0})
top_k_values_val = cnn_session.run(top_k_values, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0})
fir_weight_variable_val = cnn_session.run(fir_weight_variable)
fir_weight_variable_val = np.squeeze(fir_weight_variable_val)
print(fir_weight_variable_val.shape)
print(fir_analysis_tensor_val)
fir_sort_in = np.argsort(fir_analysis_tensor_val)
print(fir_sort_in)
print(top_k_indices_val)
print(top_k_values_val)
plot_2dmatrix(fir_weight_variable_val[:, fir_sort_in[-10:]])
sdfd
for n in range(len(fir_out_tensor_val)):
for k in range(50):
ret_str = "k" + str(k) + ": "
kernel_max = -1
max_attr = -1
max_attr_list = []
for a in range(attr_num):
attr_max = max(fir_out_tensor_val[n, :, a, k])
max_attr_list.append(attr_max)
if attr_max > kernel_max:
kernel_max = attr_max
max_attr = a
if attr_max == 0:
ret_str = ret_str + str(a) + " "
print(ret_str)
print("max attr " + str(max_attr))
print(sorted(range(len(max_attr_list)), key=lambda k: max_attr_list[k]))
print("======")
print("label " + str(train_y_vector[0]))
fir_out_tensor_val = cnn_session.run(sec_out_tensor, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0})
print(fir_out_tensor_val.shape)
sdf
for n in range(len(fir_out_tensor_val)):
for k in range(40):
ret_str = "k" + str(k) + ": "
kernel_max = -1
max_attr = -1
max_attr_list = []
for a in range(attr_num):
attr_max = max(fir_out_tensor_val[n, :, a, k])
max_attr_list.append(attr_max)
if attr_max > kernel_max:
kernel_max = attr_max
max_attr = a
if attr_max == 0:
ret_str = ret_str + str(a) + " "
print(ret_str)
print("max attr " + str(max_attr))
print(sorted(range(len(max_attr_list)), key=lambda k: max_attr_list[k]))
print("======")
sdf
fir_out_mean_val = cnn_session.run(fir_out_mean, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0})
#fir_out_mean_val = np.squeeze(fir_out_mean_val)
print(fir_out_mean_val.shape)
plot_2dmatrix(np.squeeze(fir_out_mean_val[:, :, 0:5]))
sdfd
plot_2dmatrix(fir_weight_var_val)
min_class = min(train_y_vector)
max_class = max(train_y_vector)
num_classes = max_class - min_class + 1
if cnn_setting.eval_method == "accuracy":
cnn_eval_key = "acc"
elif num_classes > 2:
cnn_eval_key = "acc_batch"
else:
cnn_eval_key = "f1"
log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(min_class)+"_" + str(max_class) + "_act" + str(cnn_setting.activation_fun) + "_" + cnn_eval_key + '.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('============')
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(train_x_matrix[0, 0:3, 0:2, 0])
logger.info(test_x_matrix[0, 0:3, 0:2, 0])
train_y_matrix = y_vector_to_matrix(train_y_vector, num_classes)
test_y_matrix = y_vector_to_matrix(test_y_vector, num_classes)
cnn_eval_value, train_run_time, test_run_time, cnn_predict_proba, saver_file, feature_list_obj_file = run_cnn(train_x_matrix, train_y_matrix, test_x_matrix, test_y_matrix, data_stru, cnn_setting, saver_file_profix, logger)
logger.info("Fold eval value: " + str(cnn_eval_value))
logger.info(method + ' fold training time (sec):' + str(train_run_time))
logger.info(method + ' fold testing time (sec):' + str(test_run_time))
logger.info("save obj to " + saver_file)
def cnn_classification_main(parameter_file,
file_keyword,
function_keyword="cnn_classification"):
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)
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)
file_list = list_files(data_folder)
file_count = 0
class_column = 0
header = True
cnn_setting = return_cnn_setting_from_file(cnn_setting_file)
cnn_setting.out_obj_folder = out_obj_folder
cnn_setting.out_model_folder = out_model_folder
init_folder(out_obj_folder)
init_folder(out_model_folder)
result_obj_folder = obj_folder + method + "_result_folder"
result_obj_folder = init_folder(result_obj_folder)
delimiter = ' '
loop_count = -1
saver_file_profix = ""
attention_type = 0
attention_type = -1
cnn_setting.attention_type = attention_type
trans_bool = False # True: means ins * attr_len * 1 * attr_num
# False: means ins * attr_len * attr_num * 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', '')
saver_file_profix = file_key + "_atten" + str(attention_type)
valid_file = data_folder + train_file.replace('train', 'valid')
if os.path.isfile(valid_file) is False:
valid_file = ''
test_file = data_folder + train_file.replace('train', 'test')
if os.path.isfile(test_file) is False:
test_file = ''
data_group, attr_num = train_test_file_reading(
data_folder + train_file, test_file, valid_file, class_column,
delimiter, header)
data_group_processing(data_group, attr_num, trans_bool)
data_stru = data_group.gene_data_stru()
data_group.data_check(data_stru.num_classes, data_stru.min_class)
if cnn_setting.eval_method == "accuracy":
cnn_eval_key = "acc"
elif num_classes > 2:
cnn_eval_key = "acc_batch"
else:
cnn_eval_key = "f1"
log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(
data_stru.min_class
) + "_" + str(data_stru.num_classes) + "_act" + str(
cnn_setting.activation_fun
) + "_" + cnn_eval_key + "_attention" + str(attention_type) + '.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('============')
if file_count == 0:
logger.info('train matrix shape: ' +
str(data_group.train_x_matrix.shape))
logger.info('train label shape: ' +
str(data_group.train_y_vector.shape))
logger.info(data_group.train_x_matrix[0, 0:3, 0:2, 0])
pred_y_prob, train_run_time, test_run_time, cnn_model = run_cnn(
cnn_setting, data_group, saver_file_profix, logger)
pred_y_vector = np.argmax(pred_y_prob, axis=1)
avg_acc, ret_str = averaged_class_based_accuracy(
pred_y_vector, data_group.test_y_vector)
acc_value = accuracy_score(data_group.test_y_vector, pred_y_vector,
True)
logger.info("Averaged acc: " + str(acc_value))
logger.info(ret_str)
logger.info("Fold eval value: " + str(acc_value))
logger.info(method + ' fold training time (sec):' +
str(train_run_time))
logger.info(method + ' fold testing time (sec):' + str(test_run_time))
logger.info("save obj to " + cnn_model.saver_file)
def fixed_width_forward_multitime(train_x, train_y, test_x, test_y, n_selected_features, keep_k=5, data_key="test", fold_key="", method="cnn", cnn_setting_file = "../../parameters/cnn_model_parameter.txt", logger=None, function_key="best_forward_multitime"):
"""
This function implements the forward feature selection algorithm based on decision tree
Input
-----
train_x: {3d numpy array matrix}, shape (n_samples, n_features, time_length)
input data
train_y: {1d numpy array vector}, shape (n_samples,)
input class labels
test_x: {3d numpy array matrix}, shape (n_samples, n_features, time_length)
input data
test_y: {1d numpy array vector}, shape (n_samples,)
input class labels
Output
------
F: {numpy array}, shape (n_features, )
index of selected features
"""
if logger is None:
log_file = ""
logger = setup_logger(log_file)
train_samples, n_features, time_length = train_x.shape
eval_method = "f1"
if method == "cnn":
min_class = min(train_y)
max_class = max(train_y)
num_classes = max_class - min_class + 1
data_stru = data_structure(num_classes, min_class, n_features, time_length)
cnn_setting = return_cnn_setting_from_file(cnn_setting_file)
logger.info('cnn setting:\n ' + cnn_setting.to_string())
saver_file_profix = "../../object/" + data_key + "/" +function_key + "/cnn_model_folder/"
saver_file_profix = init_folder(saver_file_profix)
saver_file_profix = saver_file_profix + fold_key
eval_method = cnn_setting.eval_method
elif method == "rf":
model = RandomForestClassifier(n_estimators=20, random_state=0)
# selected feature set, initialized to contain all features
F = []
F_eval_score = []
F_available = []
count = len(F)
if count == 0:
F_available = range(n_features)
F_eval_score = np.zeros(n_features) - 1
while count < n_selected_features:
max_eval_value = -1
f_score = []
logger.info("For iter " + str(count))
logger.info("available list for this iter: " + str(F_available))
for i in F_available:
if i not in F:
F.append(i)
train_x_tmp = train_x[:, F, :]
test_x_tmp = test_x[:, F, :]
F_key = str(F)[1:-1]
if method == "cnn":
eval_value, train_run_time, test_run_time, predict_proba, saver_file, feature_list_obj_file, relu_based_array = model_evaluation_cnn(train_x_tmp, train_y, test_x_tmp, test_y, data_stru, cnn_setting, saver_file_profix + "_F" + F_key, logger)
f_eval_value = eval_value
elif method == "rf":
eval_value, train_run_time, test_run_time = model_evaluation_rf(train_x_tmp, train_y, test_x_tmp, test_y, model, logger)
f_eval_value = eval_value
if count == 0:
F_eval_score[i] = eval_value
logger.info("Features With: " + str(F))
logger.info("Adding Feature " + str(i) + ": ")
logger.info(method + " " + eval_method + " Value For Feature " + str(i) + ": " + str(f_eval_value))
logger.info(method +" Training time (sec): " + str(train_run_time))
logger.info(method + " Testing time (sec): " + str(test_run_time))
f_score.append(f_eval_value)
F.pop()
# record the feature which results in the largest accuracy
if eval_value > max_eval_value:
max_eval_value = eval_value
idx = i
F_eval_score[idx] = -1
if count == 0:
F_available = []
for sel in range(keep_k):
add_id = np.argmax(F_eval_score)
F_available.append(add_id)
F_eval_score[add_id] = -1
else:
F_available.remove(idx)
add_id = np.argmax(F_eval_score)
F_available.append(add_id)
F_eval_score[add_id] = -1
logger.info("Eval score vector: " + str(f_score))
logger.info("The added attribute is: " + str(idx))
logger.info("larggest eval value is: " + str(max_eval_value))
# delete the feature which results in the largest accuracy
F.append(idx)
count += 1
return np.array(F)
def pv_classification_cnn(parameter_file,
file_keyword,
function_keyword="pv_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)
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 = 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('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')
#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
if method == 'fcn':
fold_accuracy, fold_f1_value, fold_predict_y, fold_train_time, fold_test_time, fold_predict_matrix = run_feature_projected_ijcnn_fcn(
train_x_matrix, train_y_vector, test_x_matrix, test_y_vector,
data_stru, cnn_setting, feature_dict, top_k,
file_key + '_' + method + '_count' + str(file_count), class_id,
logger)
else:
fold_accuracy, fold_f1_value, 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 + '_' + method + '_count' + str(file_count), 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 pv_cnn_generation_main(parameter_file,
file_keyword,
function_keyword="pv_cnn_generation"):
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_pv_cnn_generation(
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)
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.out_obj_folder = out_obj_folder
cnn_setting.out_model_folder = out_model_folder
cnn_setting.feature_method = 'save'
cnn_setting.eval_method = 'f1'
init_folder(out_obj_folder)
init_folder(out_model_folder)
result_obj_folder = obj_folder + method + "_result_folder"
result_obj_folder = init_folder(result_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) + '_' + 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('============')
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)
# Call the projected feature function here, just need to set feature_dict = None
feature_dict = None
top_k = -1
model_save_file = file_key + '_count' + str(file_count) + '_' + method
if method == 'fcn':
fold_accuracy, fold_f1_value, fold_predict_y, fold_train_time, fold_test_time, fold_predict_matrix = run_feature_projected_ijcnn_fcn(
train_x_matrix, train_y_vector, test_x_matrix, test_y_vector,
data_stru, cnn_setting, feature_dict, top_k, model_save_file,
class_id, logger)
else:
fold_accuracy, fold_f1_value, 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, model_save_file,
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 " + result_obj_folder + file_key +
"_all_feature_" + method + "_result.ckpt")
save_obj([
fold_accuracy, fold_f1_value, fold_predict_y, fold_train_time,
fold_test_time, fold_predict_matrix
], result_obj_folder + file_key + "_all_feature_" + method +
"_result.ckpt")
def cnn_classification_main(parameter_file,
file_keyword,
function_keyword="cnn_classification"):
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)
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)
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.out_obj_folder = out_obj_folder
cnn_setting.out_model_folder = out_model_folder
cnn_setting.feature_method = 'none'
cnn_key = return_cnn_keyword(cnn_setting)
init_folder(out_obj_folder)
init_folder(out_model_folder)
group_all = False
result_obj_folder = obj_folder + method + "_result_folder"
result_obj_folder = init_folder(result_obj_folder)
delimiter = ' '
loop_count = -1
saver_file_profix = ""
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', '')
saver_file_profix = file_key
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)
min_class = min(train_y_vector)
max_class = max(train_y_vector)
num_classes = max_class - min_class + 1
if cnn_setting.eval_method == "accuracy":
cnn_eval_key = "acc"
elif num_classes > 2:
cnn_eval_key = "acc_batch"
else:
cnn_eval_key = "f1"
log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(
min_class) + "_" + str(max_class) + "_act" + str(
cnn_setting.activation_fun) + "_" + cnn_eval_key + '.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('============')
#train_y_vector[50:80] = 1
#test_y_vector[30:40] = 1
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(train_x_matrix[0, 0:3, 0:2, 0])
logger.info(test_x_matrix[0, 0:3, 0:2, 0])
train_y_matrix = y_vector_to_matrix(train_y_vector, num_classes)
test_y_matrix = y_vector_to_matrix(test_y_vector, num_classes)
feature_dict = None
top_k = -1
model_save_file = file_key + '_count' + str(file_count) + '_' + method
cnn_eval_value, train_run_time, test_run_time, cnn_predict_proba, saver_file, feature_list_obj_file, relu_base_array = run_cnn(
train_x_matrix, train_y_matrix, test_x_matrix, test_y_matrix,
data_stru, cnn_setting, group_all, saver_file_profix, logger)
logger.info("Fold eval value: " + str(cnn_eval_value))
logger.info(method + ' fold training time (sec):' +
str(train_run_time))
logger.info(method + ' fold testing time (sec):' + str(test_run_time))
logger.info("save obj to " + saver_file)
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))
print out_conv.get_shape()
out_conv = tf.reshape(out_conv, [-1, feature_num])
print std_value
print feature_num
predict_y_prob = conf_out_layer(out_conv, feature_num, num_classes,
std_value)
#print "predict_y_prob"
print predict_y_prob.get_shape()
return predict_y_prob, keep_prob_placeholder, keeped_feature_list, saver_file
# End of CNN method
if __name__ == '__main__':
cnn_setting_file = "../../parameters/cnn_model_parameter.txt"
cnn_setting = return_cnn_setting_from_file(cnn_setting_file)
train_row = 20
test_row = 10
num_classes = 3
attr_num = 45
attr_len = 125
data_stru = return_data_stru(num_classes, 0, attr_num, attr_len, 0)
train_x_matrix = np.random.rand(train_row, attr_len, attr_num, 1)
test_x_matrix = np.random.rand(test_row, attr_len, attr_num, 1)
train_y_vector = np.array(
[0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1, 0, 0, 0, 2])
test_y_vector = np.array([0, 0, 0, 1, 1, 1, 0, 0, 2, 2])
train_y_matrix = y_vector_to_matrix(train_y_vector, num_classes)
test_y_matrix = y_vector_to_matrix(test_y_vector, num_classes)
print train_x_matrix.shape
