def data_load(signal_size, filename, label, InputType, task):
'''
This function is mainly used to generate test data and training data.
filename:Data location
'''
if label == 0:
fl = (loadmat(filename)["bearing"][0][0][1]) # Take out the data
else:
fl = (loadmat(filename)["bearing"][0][0][2]) # Take out the data
fl = (fl - fl.min()) / (fl.max() - fl.min())
fl = fl.reshape(-1, )
data = []
start, end = 0, signal_size
while end <= fl[:signal_size * 1000].shape[0]:
if InputType == "TD":
x = fl[start:end]
elif InputType == "FD":
x = fl[start:end]
x = FFT(x)
else:
print("The InputType is wrong!!")
data.append(x)
start += signal_size
end += signal_size
graphset = RadiusGraph(10, data, label, task)
return graphset
def data_load(signal_size, filename, label, InputType, task):
'''
This function is mainly used to generate test data and training data.
filename:Data location
axisname:Select which channel's data,---->"_DE_time","_FE_time","_BA_time"
'''
fl = pd.read_csv(filename, skiprows=range(14), header=None)
fl = (fl - fl.min()) / (fl.max() - fl.min())
fl = fl.values
fl = fl.reshape(-1, )
data = []
start, end = 0, signal_size
while end <= fl[:signal_size * 1000].shape[0]:
if InputType == "TD":
x = fl[start:end]
elif InputType == "FD":
x = fl[start:end]
x = FFT(x)
else:
print("The InputType is wrong!!")
data.append(x)
start += signal_size
end += signal_size
graphset = KNNGraph(10, data, label, task)
return graphset
def data_load(signal_size, root, label, InputType, task):
'''
This function is mainly used to generate test data and training data.
root:Data location
'''
fl = pd.read_csv(
root,
sep='\t',
usecols=[1],
header=None,
)
fl = fl.values
fl = (fl - fl.min()) / (fl.max() - fl.min())
fl = fl.reshape(-1, )
data = []
start, end = 0, signal_size
while end <= fl[:signal_size * 1000].shape[0]:
if InputType == "TD":
x = fl[start:end]
elif InputType == "FD":
x = fl[start:end]
x = FFT(x)
else:
print("The InputType is wrong!!")
data.append(x)
start += signal_size
end += signal_size
graphset = PathGraph(10, data, label, task)
return graphset
def data_load(signal_size, filename, axisname, label, InputType, task):
'''
This function is mainly used to generate test data and training data.
filename:Data location
axisname:Select which channel's data,---->"_DE_time","_FE_time","_BA_time"
'''
datanumber = axisname.split(".")
if eval(datanumber[0]) < 100:
realaxis = "X0" + datanumber[0] + axis[0]
else:
realaxis = "X" + datanumber[0] + axis[0]
fl = loadmat(filename)[realaxis]
fl = (fl - fl.min()) / (fl.max() - fl.min())
fl = fl.reshape(-1, )
data = []
start, end = 0, signal_size
while end <= fl[:signal_size * 1000].shape[0]:
if InputType == "TD":
x = fl[start:end]
elif InputType == "FD":
x = fl[start:end]
x = FFT(x)
else:
print("The InputType is wrong!!")
data.append(x)
start += signal_size
end += signal_size
graphset = PathGraph(10, data, label, task)
return graphset
def data_load(signal_size, filename, dataname, label, InputType, task):
'''
This function is mainly used to generate test data and training data.
filename:Data location
'''
f = open(filename, "r", encoding='gb18030', errors='ignore')
fl = []
if dataname == "ball_20_0.csv":
for line in islice(f, 16, None): #Skip the first 16 lines
line = line.rstrip()
word = line.split(",", 8) #Separated by commas
fl.append(eval(word[1])
) # Take a vibration signal in the x direction as input
else:
for line in islice(f, 16, None): #Skip the first 16 lines
line = line.rstrip()
word = line.split("\t", 8) #Separated by \t
fl.append(eval(word[1])
) # Take a vibration signal in the x direction as input
fl = np.array(fl)
fl = (fl - fl.min()) / (fl.max() - fl.min())
fl = fl.reshape(-1, )
data = []
start, end = 0, signal_size
while end <= fl[:signal_size * 1000].shape[0]:
if InputType == "TD":
x = fl[start:end]
elif InputType == "FD":
x = fl[start:end]
x = FFT(x)
else:
print("The InputType is wrong!!")
data.append(x)
start += signal_size
end += signal_size
graphset = RadiusGraph(10, data, label, task)
return graphset