I have this code:
import numpy as np
#from bp.deep_bp import deep_train
def deep_train(train_x, train_y, test_x, test_y, layers_dims):
parameters = L_layer_model(train_x, train_y, layers_dims, num_iterations=2500, print_cost=True)
pred_train = predict(train_x, train_y, parameters)
pred_test = predict(test_x, test_x, parameters)
#from bp.shallow_bp import shallow_train
def shallow_train(train_set_x, train_set_y, test_set_x, test_set_y, sys_layers_dims):
dataset = load_resize_dataset()
train_set_x = dataset['train_set_x']
train_set_y = dataset['train_set_y']
test_set_x = dataset['test_set_x']
test_set_y = dataset['test_set_y']
d = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations=2000, learning_rate=0.0001,
print_cost=True)
#from factory.bp_data_factory import load_cat_dataset
def load_cat_dataset():
train_dataset = h5py.File('D:\research\SoftWareReliability-master\SoftWareReliability-master\resource\train_catvnoncat.h5', "r")
train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # train set features
train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # train set labels
test_dataset = h5py.File('D:\research\SoftWareReliability-master\SoftWareReliability-master\resource\test_catvnoncat.h5', "r")
test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # test set features
test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # test set labels
classes = np.array(test_dataset["list_classes"][:]) # the list of classes
train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))
test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))
return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes
#from factory.graph_data_factory import load_sys_dataset
def load_sys_dataset():
path = 'D:\research\SoftWareReliability-master\SoftWareReliability-master\resource\sourceData.txt'
data = np.loadtxt(path)
n = data.shape[0]
data2 = np.zeros(shape=n + 1)
data2[0] = 0
for i in range(n):
data2[i + 1] = data[i][1]
return data2
def shallow_bp(train_x, train_y, test_x, test_y, sys_layers_dims):
shallow_train(train_x, train_y, test_x, test_y, sys_layers_dims)
#def deep_dp(train_x, train_y, test_x, test_y, layers_dims):
# deep_train(train_x, train_y, test_x, test_y, layers_dims)
def read_decode_cat_data():
train_x_orig, train_y, test_x_orig, test_y, classes = load_cat_dataset()
m_train = train_x_orig.shape[0]
num_px = train_x_orig.shape[1]
m_test = test_x_orig.shape[0]
print("Number of training examples: " + str(m_train))
print("Number of testing examples: " + str(m_test))
print("Each image is of size: (" + str(num_px) + ", " + str(num_px) + ", 3)")
print("train_x_orig shape: " + str(train_x_orig.shape))
print("train_y shape: " + str(train_y.shape))
print("test_x_orig shape: " + str(test_x_orig.shape))
print("test_y shape: " + str(test_y.shape))
train_x_flatten = train_x_orig.reshape(train_x_orig.shape[0],
-1).T
test_x_flatten = test_x_orig.reshape(test_x_orig.shape[0], -1).T
train_x = train_x_flatten / 255.
test_x = test_x_flatten / 255.
print("train_x's shape: " + str(train_x.shape))
print("test_x's shape: " + str(test_x.shape))
n_x = 12288 # num_px * num_px * 3
n_h = 7
n_y = 1
layers_dims = (n_x, n_h, n_y)
return train_x, train_y, test_x, test_y
def Normalize(data):
m = np.mean(data)
mx = max(data)
mn = min(data)
print('mean: ' + str(m) + ' mx:' + str(mx) + ' mn:' + str(mn))
return [(float(i) - m) / (mx - mn) for i in data]
def read_decode_sys_data():
y = load_sys_dataset()
sum_count = len(y)
y = np.array(y)
np.delete(y, [y[0]])
x = np.arange(start=0, stop=sum_count, step=1)
x = Normalize(x)
y = Normalize(y)
x=np.array(x)
y=np.array(y)
last_train_index = int((sum_count - 1) * 0.8)
train_x = x[1:last_train_index]
train_y = y[1:last_train_index]
test_x = x[last_train_index:]
test_y = y[last_train_index:]
train_x_flatten = train_x.reshape(train_x.shape[0],
-1).T
test_x_flatten = test_x.reshape(test_y.shape[0], -1).T
train_y = train_y.reshape(1, -1)
test_y = test_y.reshape(1, -1)
return train_x_flatten, train_y, test_x_flatten, test_y
if __name__ == '__main__':
cat_layers_dims = [12288, 20, 7, 5, 1]
sys_layers_dims = [1, 1]
train_x, train_y, test_x, test_y = read_decode_sys_data()
shallow_bp(train_x, train_y, test_x, test_y, sys_layers_dims)
it shows me this error:
Python 3.9.12 (main, Apr 4 2022, 05:22:27) [MSC v.1916 64 bit (AMD64)]
Type "copyright", "credits" or "license" for more information.
IPython 8.2.0 -- An enhanced Interactive Python.
runfile('D:/research/SoftWareReliability-master/SoftWareReliability-master/presenter/bp_presenter.py', wdir='D:/research/SoftWareReliability-master/SoftWareReliability-master/presenter')
Traceback (most recent call last):
File D:\research\SoftWareReliability-master\SoftWareReliability-master\presenter\bp_presenter.py:133 in <module>
train_x, train_y, test_x, test_y = read_decode_sys_data()
File D:\research\SoftWareReliability-master\SoftWareReliability-master\presenter\bp_presenter.py:106 in read_decode_sys_data
y = load_sys_dataset()
File D:\research\SoftWareReliability-master\SoftWareReliability-master\presenter\bp_presenter.py:45 in load_sys_dataset
data = np.loadtxt(path)
File ~\anaconda3\lib\site-packages\numpy\lib\npyio.py:1067 in loadtxt
fh = np.lib._datasource.open(fname, 'rt', encoding=encoding)
File ~\anaconda3\lib\site-packages\numpy\lib\_datasource.py:193 in open
return ds.open(path, mode, encoding=encoding, newline=newline)
File ~\anaconda3\lib\site-packages\numpy\lib\_datasource.py:533 in open
raise IOError("%s not found." % path)
esource\sourceData.txt not found.r\SoftWareReliability-master
its looks in this part:
#from factory.graph_data_factory import load_sys_dataset
def load_sys_dataset():
path = 'D:\research\SoftWareReliability-master\SoftWareReliability-master\resource\sourceData.txt'
data = np.loadtxt(path)
n = data.shape[0]
data2 = np.zeros(shape=n + 1)
data2[0] = 0
for i in range(n):
data2[i + 1] = data[i][1]
return data2
but this path is 100% correct, whats the problem?
'D:\research\SoftWareReliability-master\SoftWareReliability-master\resource\sourceData.txt'