def cal_k_tran(data, input_k, input_bin):
x_start = 10
x_var_start = 10000
model_mean = 0
model_variance = 0.01
data.clear_change_points()
cheb = chebyshev_base(min_size=60, max_window=60, k=input_k)
for i, file_name in enumerate(data.get_files_test()):
change_points = []
measurements = data.get_dataset_test(i)
# xs = np.zeros((len(measurements), 2))
# ps = np.zeros((len(measurements), 2))
x = x_start
x_var = x_var_start
for index, measurement in enumerate(measurements):
x, x_var = kalman.update(x, x_var, measurement, model_variance)
# xs[i] = x, x_var
x, x_var = kalman.predict(x, x_var, model_mean, model_variance)
# ps[i] = x, x_var
is_change = cheb.add_element(x)
if is_change:
change_points.append(index)
data.set_change_points(change_points)
return data
def get_changepoint_BinCheb(self, instances, is_normal=False):
cheb = ""
if self.is_k:
cheb = chebyshev_base(min_size=self.min_winsize,
max_window=self.max_winsize,
k=self.K)
else:
cheb = chebyshev_base_e(min_size=self.min_winsize,
max_window=self.max_winsize,
e=self.E)
bin = binning(bin_period=self.Bin_size)
change_points = []
temp_bin = []
mean_list = []
# instances = data.get_dataset_test(i)
for index, instance in enumerate(instances):
is_change = False
can_add_bin = bin.can_add_bin()
if not can_add_bin:
temp_bin.append(bin.get_bin())
mean_bin = mean(bin.get_bin())
mean_list.append(mean_bin)
is_change = cheb.add_element(mean_bin)
bin = binning(bin_period=self.Bin_size)
bin.add_instance(instance)
if is_change:
if is_normal:
for j in range(index - self.Bin_size, index):
change_points.append(j)
else:
change_points.append(index)
self.cheb = cheb
self.ex = cheb.get_exception()
return change_points, mean_list
def cal_k_tran(data,input_k,input_bin):
data.clear_change_points()
cheb = chebyshev_base(min_size=60, max_window=60, k=input_k)
bin = binning(bin_period=input_bin)
for i, file_name in enumerate(data.get_files_test()):
change_points = []
instances = data.get_dataset_test(i)
for index, instance in enumerate(instances):
is_change = False
can_add_bin = bin.can_add_bin()
if can_add_bin:
bin.add_instance(instance)
else:
mean_bin = mean(bin.get_bin())
is_change = cheb.add_element(mean_bin)
bin.reset_bin()
# if is_change:
# change_points.append(index)
if is_change:
for j in range(index - bin_period + 1, index + 1):
change_points.append(j)
data.set_change_points(change_points)
return data
def get_changepoint_baseCheb(self, instances):
cheb = chebyshev_base(min_size=self.min_winsize,
max_window=self.max_winsize,
k=self.K)
change_points = []
for index, instance in enumerate(instances):
is_change = False
is_change = cheb.add_element(instance)
if is_change:
change_points.append(index)
std_low_list = cheb.get_std_low_list()
std_high_list = cheb.get_std_high_list()
mean_list = cheb.get_mean_list()
return change_points, std_low_list, std_high_list, mean_list
def get_changepoint_kalmanBinCheb(self,
instances,
inpput_x=10,
input_var=10000,
model_mean=0,
model_variance=0.01):
x_start = inpput_x
x_var_start = input_var
model_mean = model_mean
model_variance = model_variance
cheb = chebyshev_base(min_size=self.min_winsize,
max_window=self.max_winsize,
k=self.K)
bin = binning(bin_period=self.Bin_size)
change_points = []
measurements = instances
# xs = np.zeros((len(measurements), 2))
# ps = np.zeros((len(measurements), 2))
x = x_start
x_var = x_var_start
for index, measurement in enumerate(measurements):
x, x_var = kalman.update(x, x_var, measurement, model_variance)
# xs[i] = x, x_var
x, x_var = kalman.predict(x, x_var, model_mean, model_variance)
# ps[i] = x, x_var
is_change = False
can_add_bin = bin.can_add_bin()
if not can_add_bin:
mean_bin = mean(bin.get_bin())
is_change = cheb.add_element(mean_bin)
bin.reset_bin()
bin.add_instance(x)
if is_change:
for j in range(index - self.bin_period + 1, index + 1):
change_points.append(j)
return change_points
def get_changepoint_kalmanCheb(self,
measurements,
inpput_x=10,
input_var=10000,
model_mean=0,
model_variance=0.01):
x_start = inpput_x
x_var_start = input_var
model_mean = model_mean
model_variance = model_variance
cheb = chebyshev_base(min_size=self.min_winsize,
max_window=self.max_winsize,
k=self.K)
change_points = []
# measurements = instances
# xs = np.zeros((len(measurements), 2))
# ps = np.zeros((len(measurements), 2))
x = x_start
x_var = x_var_start
for index, measurement in enumerate(measurements):
x, x_var = kalman.update(x, x_var, measurement, model_variance)
# xs[i] = x, x_var
x, x_var = kalman.predict(x, x_var, model_mean, model_variance)
# ps[i] = x, x_var
is_change = False
is_change = cheb.add_element(x)
if is_change:
change_points.append(index)
std_low_list = cheb.get_std_low_list()
std_high_list = cheb.get_std_high_list()
mean_list = cheb.get_mean_list()
return change_points, std_low_list, std_high_list, mean_list
def cal_k_tran(data, input_k, input_bin):
x_start = 10
x_var_start = 10000
model_mean = 0
model_variance = 0.01
data.clear_change_points()
cheb = chebyshev_base(min_size=60, max_window=60, k=input_k)
bin = binning(bin_period=input_bin)
for i, file_name in enumerate(data.get_files_test()):
change_points = []
measurements = data.get_dataset_test(i)
xs = np.zeros((len(measurements), 2))
ps = np.zeros((len(measurements), 2))
x = x_start
x_var = x_var_start
for index, measurement in enumerate(measurements):
x, x_var = kalman.update(x, x_var, measurement, model_variance)
xs[i] = x, x_var
x, x_var = kalman.predict(x, x_var, model_mean, model_variance)
ps[i] = x, x_var
is_change = False
can_add_bin = bin.can_add_bin()
if not can_add_bin:
mean_bin = mean(bin.get_bin())
is_change = cheb.add_element(mean_bin)
bin.reset_bin()
bin.add_instance(x)
if is_change:
for j in range(index - bin_period + 1, index + 1):
change_points.append(j)
data.set_change_points(change_points)
return data
for L in LS:
for I in IS:
# data = data_stream(path='C:\\Users\\karnk\\git\\data_stream\\dataset', type=type, pattern=pattern, len=L,
# interval=I)
data = data_stream(
path=
'D:\\git_project\\data stream\\lightcurve_benchmark\\{}'
.format(data_type),
type=type,
pattern=pattern,
len=L,
interval=I)
data.load_data_fromfile()
# cheb
cheb = chebyshev_base(min_size=60, max_window=60, k=k)
#Kalman
for i, file_name in enumerate(data.get_files_test()):
change_points = []
# file_name = data.get_file_name(i)
measurements = data.get_dataset_test(i)
xs = np.zeros((len(measurements), 2))
ps = np.zeros((len(measurements), 2))
x = x_start
x_var = x_var_start
for index, measurement in enumerate(measurements):
x, x_var = kalman.update(
x, x_var, measurement, model_variance)
xs[i] = x, x_var
for type in types:
for pattern in patterns:
for L in LS:
for I in IS:
# data = data_stream(path='C:\\Users\\karnk\\git\\data_stream\\dataset', type=type, pattern=pattern, len=L,
# interval=I)
data = data_stream(
path='D:\\git_project\\data stream\\dataset',
type=type,
pattern=pattern,
len=L,
interval=I)
data.load_data_fromfile()
# cheb
cheb = chebyshev_base(max_window=500, k=3)
change_points = []
#Kalman
for i in range(data.get_file_lenght()):
file_name = data.get_file_name(i)
measurements = data.get_dataset_test(i)
xs = np.zeros((len(measurements), 2))
ps = np.zeros((len(measurements), 2))
x = x_start
x_var = x_var_start
for index, measurement in enumerate(measurements):
x, x_var = kalman.update(x, x_var, measurement,
model_variance)
xs[i] = x, x_var
types = ["hinet"]
patterns = ["si"]
LS = [1,5]
IS = [100,1000]
for type in types:
for pattern in patterns:
for L in LS:
for I in IS:
# data = data_stream(path='C:\\Users\\karnk\\git\\data_stream\\dataset', type=type, pattern=pattern, len=L,
# interval=I)
data = data_stream(path='D:\\git_project\\data stream\\dataset', type=type, pattern=pattern, len=L,
interval=I)
data.load_data_fromfile()
# binning process
cheb = chebyshev_base(min_size=500,k=3)
change_points = []
for i in range(data.get_file_lenght()):
file_name = data.get_file_name(i)
instances = data.get_dataset_test(i)
bin = binning(bin_period=bin_period)
for index, instance in enumerate(instances):
is_change = False
can_add_bin = bin.can_add_bin()
if can_add_bin:
bin.add_instance(instance)
else:
mean_bin = mean(bin.get_bin())
is_change = cheb.add_element(mean_bin)
bin.reset_bin()