read_path_val = "./data/test"
file_path_list = traversalDir_FirstDir(read_path_val)
test_data = merge(file_path_list)[diying_attribute]
read_path_val = "./data/test_set"
file_path_list = traversalDir_FirstDir(read_path_val)
sources = np.zeros((142276, 24))
for i in range(len(file_path_list)):
data = pd.read_csv(file_path_list[i], engine="python")["Class"]
sources[:, i] = data.values
sources = np.sum(sources, axis=1)
source_label = [1 if source > 0 else 0 for source in sources]
test_data["Class"] = source_label
# 构建训练集和测试集
train = pd.concat([train_data, val_data], axis=0)
train.iloc[:, 0:-1] = z_norm(train.iloc[:, 0:-1].copy())
train = train.values
np.random.shuffle(train)
train_x = train[:, 0:-1]
train_y = train[:, -1]
test = test_data
test.iloc[:, 0:-1] = z_norm(test.iloc[:, 0:-1].copy())
test = test.values
np.random.shuffle(test)
test_x = test[:, 0:-1]
test_y = test[:, -1]
# 打印输出训练集和测试集的信息
print("--------------------")
print("训练集样本大小为：", train_x.shape[0])
print("训练集正常样本大小为：", train_x.shape[0] - np.sum(train_y))
config = tf.ConfigProto()
config.gpu_options.allow_growth = True # 不全部占满显存, 按需分配
sess = tf.Session(config=config)
KTF.set_session(sess)
# 训练模型
read_path = "./data/train"
read_file_list = traversalDir_FirstDir(read_path)
data = merge(read_file_list)
diying_attribute = list(
pd.read_csv("./parameter/diying.csv", header=None)[0])
for i in range(len(diying_attribute)):
diying_attribute[i] = "BX0101_" + diying_attribute[i]
data = data[diying_attribute]
# 数据标准化
data = z_norm(data)
for i in range(0, 6):
# 创建模型
model = build_model(sequence_length)
# 得到训练数据
tmp = data.iloc[:, i]
train_x, train_y = GetData(tmp.values, sequence_length)
print(str(i) + data.columns[i] + " start!" + "Training...")
print(train_x.shape)
print(train_y.shape)
history = LossHistory()
model.fit(train_x,
train_y,
batch_size=batch_size,