186 lines
7.7 KiB
Python
186 lines
7.7 KiB
Python
import loadData
|
||
import numpy as np
|
||
import tensorflow as tf
|
||
import pandas as pd
|
||
|
||
'''
|
||
class ConcatLabel：
|
||
这是一个给data加上label的类
|
||
使用示例：ConcatLabel(data, label,if_load)
|
||
作用是按是否采用加载将data文件分别添加上label
|
||
需要传入的参数有：
|
||
data:要添加label的data 是一个list类型或者np.array
|
||
label:添加的label为几 最好是int类型
|
||
if_load:是否采用按加载来分 true则采用，false则不采用 布尔类型
|
||
'''
|
||
|
||
|
||
class ConcatLabel(object):
|
||
|
||
def __init__(self, data, label, if_load):
|
||
self.data = data
|
||
self.if_load = if_load
|
||
self.label = label
|
||
|
||
def __call__(self, *args, **kwargs):
|
||
data = np.array(self.data)
|
||
if not self.if_load:
|
||
length, dim = data.shape
|
||
label_list = [[self.label] for i in range(length)]
|
||
label_list = np.array(label_list)
|
||
dataWithLabel = tf.concat([data, label_list], axis=1)
|
||
return dataWithLabel
|
||
height, length, dim = data.shape
|
||
data_new = tf.reshape(data, [height * length, dim])
|
||
label_list = [[self.label] for i in range(height * length)]
|
||
label_list = np.array(label_list)
|
||
dataWithLabel = tf.concat([data_new, label_list], axis=1)
|
||
dataWithLabel = tf.reshape(dataWithLabel, [height, length, dim + 1])
|
||
return dataWithLabel
|
||
|
||
|
||
'''
|
||
class PieceAndBag：
|
||
这是一个给data分成train_data和test_data的类
|
||
使用示例：ConcatLabel(data, if_load)
|
||
作用是按是否采用加载将data文件分成(train_data,train_label和(test_data,test_label)
|
||
需要传入的参数有：
|
||
data:要添加label的data 是一个list类型或者np.array
|
||
if_load:是否采用按加载来分 true则采用，false则不采用 布尔类型
|
||
'''
|
||
|
||
|
||
class PieceAndBag(object):
|
||
|
||
def __init__(self, data, if_load):
|
||
self.data = data
|
||
self.if_load = if_load
|
||
|
||
def __call__(self, *args, **kwargs):
|
||
data = self.data
|
||
data = np.array(data)
|
||
test_data = []
|
||
train_data = []
|
||
test_label = []
|
||
train_label = []
|
||
if not self.if_load:
|
||
heigth, dim = data.shape
|
||
for i in range(heigth):
|
||
if i % 6 == 0:
|
||
test_data.append(data[i, :-1])
|
||
test_label.append(data[i, -1])
|
||
else:
|
||
train_data.append(data[i, :-1])
|
||
train_label.append(data[i, -1])
|
||
train_data = np.array(train_data)
|
||
train_label = np.array(train_label)
|
||
test_data = np.array(test_data)
|
||
test_label = np.array(test_label)
|
||
return (train_data, train_label), (test_data, test_label)
|
||
height, length, dim = data.shape
|
||
data = tf.reshape(data, [height * length, dim])
|
||
for i in range(height * length):
|
||
if i % 6 == 0:
|
||
test_data.append(data[i, :-1])
|
||
test_label.append(data[i, -1])
|
||
else:
|
||
train_data.append(data[i, :-1])
|
||
train_label.append(data[i, -1])
|
||
|
||
train_data = np.array(train_data)
|
||
train_label = np.array(train_label)
|
||
test_data = np.array(test_data)
|
||
test_label = np.array(test_label)
|
||
print(train_data.shape)
|
||
print(train_label.shape)
|
||
print(test_data.shape)
|
||
print(test_label.shape)
|
||
train_data = tf.reshape(np.array(train_data), [height, length, dim - 1])
|
||
train_label = tf.reshape(np.array(train_label), [height, length, 1])
|
||
test_data = tf.reshape(np.array(test_data), [height, length, dim - 1])
|
||
test_label = tf.reshape(np.array(test_label), [height, length, 1])
|
||
|
||
train_data = tf.transpose(train_data, [1, 2, 0])
|
||
train_label = tf.transpose(train_label, [1, 2, 0])
|
||
test_data = tf.transpose(test_data, [1, 2, 0])
|
||
test_label = tf.transpose(test_label, [1, 2, 0])
|
||
return (train_data, train_label), (test_data, test_label)
|
||
|
||
|
||
if __name__ == '__main__':
|
||
data0 = loadData.DataDeal1(9, 'E:\data\DDS_data\平行齿轮箱齿轮表面磨损故障恒速\DATA')
|
||
data = np.array(data0(9, 'E:\data\DDS_data\平行齿轮箱齿轮表面磨损故障恒速\DATA'))
|
||
dataWithLabel1 = ConcatLabel(data, 1, True)
|
||
dataWithLabel1 = np.array(dataWithLabel1(data, 1, True))
|
||
|
||
# 导入第二类故障并打标签
|
||
data0 = loadData.DataDeal1(9, 'E:\data\DDS_data\平行齿轮箱齿轮齿根裂纹故障恒速\DATA')
|
||
data = np.array(data0(9, 'E:\data\DDS_data\平行齿轮箱齿轮齿根裂纹故障恒速\DATA'))
|
||
dataWithLabel2 = ConcatLabel(data, 2, True)
|
||
dataWithLabel2 = np.array(dataWithLabel2(data, 2, True))
|
||
|
||
# 导入第三类故障并打标签
|
||
data0 = loadData.DataDeal1(9, 'E:\data\DDS_data\平行齿轮箱齿轮断齿故障恒速\DATA')
|
||
data = np.array(data0(9, 'E:\data\DDS_data\平行齿轮箱齿轮断齿故障恒速\DATA'))
|
||
dataWithLabel3 = ConcatLabel(data, 3, True)
|
||
dataWithLabel3 = np.array(dataWithLabel3(data, 3, True))
|
||
|
||
# 导入第四类故障并打标签
|
||
data0 = loadData.DataDeal1(9, 'E:\data\DDS_data\平行齿轮箱齿轮偏心故障恒速\DATA')
|
||
data = np.array(data0(9, 'E:\data\DDS_data\平行齿轮箱齿轮偏心故障恒速\DATA'))
|
||
dataWithLabel4 = ConcatLabel(data, 4, True)
|
||
dataWithLabel4 = np.array(dataWithLabel4(data, 4, True))
|
||
|
||
# 导入第五类故障并打标签
|
||
data0 = loadData.DataDeal1(9, 'E:\data\DDS_data\平行齿轮箱齿轮缺齿故障恒速\DATA')
|
||
data = np.array(data0(9, 'E:\data\DDS_data\平行齿轮箱齿轮缺齿故障恒速\DATA'))
|
||
dataWithLabel5 = ConcatLabel(data, 5, True)
|
||
dataWithLabel5 = np.array(dataWithLabel5(data, 5, True))
|
||
|
||
# 导入第六类故障并打标签
|
||
data0 = loadData.DataDeal1(9, 'E:\data\DDS_data\平行齿轮箱轴承复合故障恒速\DATA')
|
||
data = np.array(data0(9, 'E:\data\DDS_data\平行齿轮箱轴承复合故障恒速\DATA'))
|
||
dataWithLabel6 = ConcatLabel(data, 6, True)
|
||
dataWithLabel6 = np.array(dataWithLabel6(data, 6, True))
|
||
|
||
# 导入第七类故障并打标签
|
||
data0 = loadData.DataDeal1(9, 'E:\data\DDS_data\平行齿轮箱轴承滚动体故障恒速\DATA')
|
||
data = np.array(data0(9, 'E:\data\DDS_data\平行齿轮箱轴承滚动体故障恒速\DATA'))
|
||
dataWithLabel7 = ConcatLabel(data, 7, True)
|
||
dataWithLabel7 = np.array(dataWithLabel7(data, 7, True))
|
||
|
||
# 导入第八类故障并打标签
|
||
data0 = loadData.DataDeal1(9, 'E:\data\DDS_data\平行齿轮箱轴承内圈故障恒速\DATA')
|
||
data = np.array(data0(9, 'E:\data\DDS_data\平行齿轮箱轴承内圈故障恒速\DATA'))
|
||
dataWithLabel8 = ConcatLabel(data, 8, True)
|
||
dataWithLabel8 = np.array(dataWithLabel8(data, 8, True))
|
||
|
||
# 导入第九类故障并打标签
|
||
data0 = loadData.DataDeal1(9, 'E:\data\DDS_data\平行齿轮箱轴承外圈故障恒速\DATA')
|
||
data = np.array(data0(9, 'E:\data\DDS_data\平行齿轮箱轴承外圈故障恒速\DATA'))
|
||
dataWithLabel9 = ConcatLabel(data, 9, True)
|
||
dataWithLabel9 = np.array(dataWithLabel9(data, 9, True))
|
||
|
||
data_all = tf.concat(
|
||
[dataWithLabel1, dataWithLabel2, dataWithLabel3, dataWithLabel4, dataWithLabel5, dataWithLabel6, dataWithLabel7,
|
||
dataWithLabel8, dataWithLabel9], axis=1)
|
||
|
||
data_all = np.array(data_all)
|
||
print(data_all.shape)
|
||
data_all =tf.transpose(data,[1,2,0])
|
||
print(data_all.shape)
|
||
data_train = tf.random.shuffle(data_all)
|
||
print(data_train)
|
||
data_all = tf.transpose(data, [2, 0, 1])
|
||
data_new = PieceAndBag(data_train, True)
|
||
(train_data, train_label), (test_data, test_label) = data_new(data_train, True)
|
||
train_data = np.array(train_data)
|
||
train_label = np.array(train_label)
|
||
test_data = np.array(test_data)
|
||
test_label = np.array(test_label)
|
||
|
||
print(train_data.shape)
|
||
print(train_label.shape)
|
||
print(test_data.shape)
|
||
print(test_label.shape)
|