def load_light_select_dataset(input_path, file_name, is_mix=False):
string_name = file_name.split('_')
data_type = string_name[0]
pattern = string_name[1]
# path = 'C:\\git\\data_stream\\lightcurve_benchmark\\{}'.format(data_type)
path = '{}{}'.format(input_path, data_type)
if is_mix:
data = data_stream(path=path,
type=data_type,
pattern=pattern,
mix_path=file_name[4:])
data.load_mixdata_fromfile()
else:
L = int(string_name[2][1:])
I = int(string_name[3][1:])
data = data_stream(path=path,
type=data_type,
pattern=pattern,
len=L,
interval=I)
data.load_data_fromfile()
return data
def load_light_dataset(input_path, data_type):
data_list = {}
LS = [1, 5]
IS = [5, 10, 30, 60]
patterns = ["sq"]
for pattern in patterns:
for L in LS:
for I in IS:
title = "{}_{}_L{}_I{}".format(data_type, pattern, L, I)
path = '{}{}'.format(input_path, data_type)
# path = 'C:\\git\\data_stream\\lightcurve_benchmark\\{}'.format(data_type)
data = data_stream(path=path,
type=type,
pattern=pattern,
len=L,
interval=I)
data.load_data_fromfile()
data_list[title] = data
return data_list
LS = [5]
IS = [10, 30, 60]
# IS = [5]
process_var = 1
process_mean = 0
dic = {}
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\\lightcurve_benchmark\\pca',
type=type,
pattern=pattern,
len=L,
interval=I)
data.load_data_fromfile()
key_dict = "{}_L{}_I_{}".format(pattern, L, I)
dic[key_dict] = data
choice = ""
while choice != "exit":
# try:
pattern_in = input("Input pattern {} : ".format(patterns))
# L_in = input("Input Len {} : ".format(LS))
I_in = input("Input Interval {} : ".format(IS))
input_format = "{}_L{}_I_{}".format(pattern_in, LS[0], I_in)
element = dic.get(input_format)
IS = [10, 30, 60]
bin_periods = [4, 6]
# first loop
for bin_period in bin_periods:
for data_type in data_types:
for type in types:
for pattern in patterns:
for L in LS:
for I in IS:
transfounds = []
data = data_stream(
path=
'C:\\git\\data_stream\\lightcurve_benchmark\\{}'
.format(data_type),
type=type,
# path='D:\\git_project\\data stream\\lightcurve_benchmark\\{}'.format(data_type), type=type,
pattern=pattern,
len=L,
interval=I)
# path='C:\\lightcurve_benchmark\\lightcurve_benchmark\\{}'.format(data_type), type=type,
# pattern=pattern, len=L,
# interval=I)
data.load_data_fromfile()
for k in K_start:
data = cal_k_tran(data=data,
input_k=k,
input_bin=bin_period)
true_alerts, false_alerts, tran_found = data.count_TF_tranfound(
)
transfounds.append([k, tran_found])
types = ["Ligthcurve"]
# types = ["gaia"]
patterns = ["sq"]
L = 1
IS = [5,10,30,60]
bin_periods = [3,4,10,15,20,23,25,30]
# first loop
for type in types:
for data_type in data_types:
for pattern in patterns:
for I in IS:
# path = 'D:\\git_project\\data stream\\lightcurve_benchmark\\{}'.format(data_type)
path = 'C:\\git\\data_stream\\lightcurve_benchmark\\{}'.format(data_type)
# path = 'C:\\git\\data_stream\\gaia\\{}'.format(data_type)
data = data_stream(path=path, type=type,pattern=pattern, len=L,interval=I)
data.load_data_fromfile()
for bin_period in bin_periods:
file_format_name = '{}_{}_bin{}'.format(type, data_type, bin_period)
for k in ks:
data_sk, result_text = cal_sk_bin(data=data,
input_bin=bin_period,input_k=k,
file_format="{}_k{}".format(file_format_name,k), L=L, I=I)
print("{}_k{} cheb sk".format(file_format_name,k))
head, rows = data_sk.result_for_ROC(data_type, Algo='SK',K=k, Bin=bin_period, cheb_size=Cheb_win)
ut.list_to_csv(rows=rows, csv_name="ks_bin//roc_bin.csv", is_append=True)
head, rows = data_sk.result_for_ROC(data_type, Algo='SK', K=k,
Bin=bin_period,is_normalization=True,cheb_size=Cheb_win)
ut.list_to_csv(rows=rows, csv_name="ks_bin//roc_nor.csv", is_append=True)
#
# # ut.list_to_txt(rows=result_text, csv_name="ks_bin//{}".format(txt_file_name),