def create_adversarial_sampleset_2remote_mac_disrupt(resource_file_dir_path,
file_path,
n=10000,
k_min=2,
k_max=5):
if os.path.exists(file_path): # 如果文件存在
os.remove(file_path)
mac_dict = globalConfig.get_mac_dict()
dirs = os.listdir(resource_file_dir_path)
j = 0 # 统计生成的对抗样本数量
for point_tag in dirs:
data_path = os.path.join(resource_file_dir_path, point_tag)
files = os.listdir(data_path)
for file in files:
data_file = os.path.join(data_path, file)
data = pd.read_csv(data_file, header=None)
tokens = []
token = [0] * (seq_len + 1)
begin_time = data.iloc[0][0]
first_time = begin_time
i = 0 # 序列号
for row in data.itertuples():
if j < n:
if row[TIME_IDX] - begin_time > timeInterval:
token[seq_len] = '0'
tokens.append(token)
j += 1
begin_time = row[TIME_IDX]
token = [0] * (seq_len + 1)
i = 0
if row[TIME_IDX] - first_time > time_each_file * 1000:
break
idx = mac_dict.get(row[MAC_IDX], -1)
if idx == 13 or idx == 25: # 更换相隔很远的两个ble，ble14和ble26
idx = 25 + 13 - idx
if idx > -1 and i < seq_len:
value = getNumber(idx, row[RSSI_IDX])
if value > -1:
token[i] = value
i += 1
if j >= n:
break
pd.DataFrame(tokens).to_csv(file_path,
index=False,
encoding='utf-8',
mode="a+",
header=None)
print(file + " finish")
else:
continue
if j >= n:
pd.DataFrame(tokens).to_csv(file_path,
index=False,
encoding='utf-8',
mode="a+",
header=None)
break
df = pd.read_csv(file_path, header=None)
df.to_csv(file_path, columns=[i for i in range(seq_len + 1)])
def create_adversarial_sampleset_alternating_noise(resource_file_dir_path,
result_token_file, noise):
if os.path.exists(result_token_file): # 如果文件存在
os.remove(result_token_file)
data_tag = '0'
noise_flag = 1
mac_dict = globalConfig.get_mac_dict()
dirs = os.listdir(resource_file_dir_path)
for point_tag in dirs:
data_path = os.path.join(resource_file_dir_path, point_tag)
files = os.listdir(data_path)
for file in files:
data_file = os.path.join(data_path, file)
data = pd.read_csv(data_file, header=None)
tokens = []
token = [0] * (seq_len + 1)
begin_time = data.iloc[0][0]
first_time = begin_time
i = 0 # 序列号
for row in data.itertuples():
if row[TIME_IDX] - begin_time > timeInterval:
token[seq_len] = data_tag
tokens.append(token)
begin_time = row[TIME_IDX]
token = [0] * (seq_len + 1)
i = 0
if row[TIME_IDX] - first_time > time_each_file * 1000:
break
idx = mac_dict.get(row[MAC_IDX], -1)
if idx > -1 and i < seq_len:
if noise_flag:
value = getNumber(idx, row[RSSI_IDX] + noise) # 加噪声
noise_flag = 0
else:
value = getNumber(idx, row[RSSI_IDX] - noise) # 加噪声
noise_flag = 1
if value > -1:
token[i] = value
i += 1
pd.DataFrame(tokens).to_csv(result_token_file,
index=False,
encoding='utf-8',
mode="a+",
header=None)
print(file + " finish")
df = pd.read_csv(result_token_file, header=None)
df.to_csv(result_token_file, columns=[i for i in range(seq_len + 1)])
import globalConfig
import os
from keras_bert.bert import get_model
from keras_bert.backend import keras
import tensorflow as tf
from sklearn.utils import shuffle
from NonMasking import NonMasking
from sklearn.model_selection import train_test_split
import pandas as pd
training = True
seq_len = globalConfig.seq_len
token_dict = globalConfig.get_mac_dict()
pretrain_model_path = "model/bert_1.h5"
save_model_path = "model/discriminator_2_random_macdisrupt.h5"
train_data_file = "data/train_dataset.csv"
test_data_file = "data/test_dataset.csv"
df_train = pd.read_csv(train_data_file, index_col=0)
df_test = pd.read_csv(test_data_file, index_col=0)
x_train, y_train = df_train.values[:, :seq_len], df_train.values[:, seq_len:]
x_test, y_test = df_test.values[:, :seq_len], df_test.values[:, seq_len:]
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as session:
input_layer, transformed = get_model(
token_num=globalConfig.token_num,
head_num=globalConfig.head_num,
transformer_num=globalConfig.transformer_num,