def driver_embeddings(Data, alphabet_size=2, delta=0.1):
data_dim = len(Data[0])
data_size = len(Data)
possible_s = s_vals(Data[0], alphabet_size, data_dim)
R_vals = possible_r_vals(delta, possible_s)
partitions = shifts_gen.partition_string(Data[0])
random_s_block = all_random_numbers(possible_s, partitions, R_vals)
return return_embeddings(Data, random_s_block, R_vals, possible_s)
def driver_embeddings(Data, alphabet_size=2, delta=0.1):
data_dim = len(Data[0])
data_size = len(Data)
possible_s = s_vals(Data[0], alphabet_size, data_dim)
R_vals = possible_r_vals(delta, possible_s)
partitions = shifts_gen.partition_string(Data[0])
random_s_block = all_random_numbers(possible_s, partitions, R_vals)
return return_embeddings(Data, random_s_block, R_vals, possible_s)
def s_vals():
x_block = shifts_gen.partition_string(Data[0])[0]
s_val = []
s_def = math.log(data_dim * alphabet_size / 2, 2)
j = 0
while (True):
s = int(math.ceil(s_def**j))
j = j + 1
if s > len(x_block):
break
s_val.append(s)
return s_val
def s_vals():
x_block = shifts_gen.partition_string(Data[0])[0]
s_val = []
s_def = math.log(data_dim * alphabet_size/2, 2)
j = 0
while(True):
s = int(math.ceil(s_def ** j))
j = j + 1
if s > len(x_block):# or j > 2:
break
s_val.append(s)
return s_val
def s_vals(data_0, alphabet_size, data_dim):
x_block = shifts_gen.partition_string(data_0)[0]
s_val = []
s_def = math.log(data_dim * alphabet_size / 2, 2)
j = 0
while (True):
s = int(math.ceil(s_def**j))
j = j + 1
# Modification to original algorithm
if s > len(x_block) or j > 2:
break
s_val.append(s)
return s_val
def s_vals(data_0, alphabet_size, data_dim):
x_block = shifts_gen.partition_string(data_0)[0]
s_val = []
s_def = math.log(data_dim * alphabet_size / 2, 2)
j = 0
while(True):
s = int(math.ceil(s_def ** j))
j = j + 1
# Modification to original algorithm
if s > len(x_block) or j > 2:
break
s_val.append(s)
return s_val
def get_shifts_block(x):
partitions = shifts_gen.partition_string(x)
return [[shifts_gen.shifts(x_block, s) for s in possible_s]
for x_block in partitions]
# file_number = sys.argv[2]
delta = 0.1
file_number = 'proteinNew'
alphabet_size = 26
block_s_metric = defaultdict()
# Data = data_generation.data(data_size, data_dim)
Data = protein_read.read_file_protein('raw_data/multigene_zfill.txt')
data_size = len(Data)
data_dim = len(Data[0])
random_s_block = defaultdict()
final_metric = defaultdict()
# delta = data_generation.delta
partitions = shifts_gen.partition_string(Data[0])
num_partitions = len(partitions)
def s_vals():
x_block = shifts_gen.partition_string(Data[0])[0]
s_val = []
s_def = math.log(data_dim * alphabet_size / 2, 2)
j = 0
while (True):
s = int(math.ceil(s_def**j))
j = j + 1
if s > len(x_block):
break
s_val.append(s)
return s_val
def get_shifts_block(x):
partitions = shifts_gen.partition_string(x)
return [[shifts_gen.shifts(x_block, s) for s in possible_s] for x_block in partitions]
data_dim = int(sys.argv[2])
delta = float(sys.argv[3])
data_typos = int(sys.argv[4])
file_number = sys.argv[5]
alphabet_size = 2
Data = data_generation.random_data_generation(data_size, data_dim)
# Data = data_generation.data_typo(data_dim, k=data_typos)
data_dim = len(Data[0])
data_size = len(Data)
block_s_metric = defaultdict()
random_s_block = defaultdict()
final_metric = defaultdict()
partitions = shifts_gen.partition_string(Data[0])
num_partitions = len(partitions)
def s_vals():
x_block = shifts_gen.partition_string(Data[0])[0]
s_val = []
s_def = math.log(data_dim * alphabet_size/2, 2)
j = 0
while(True):
s = int(math.ceil(s_def ** j))
j = j + 1
if s > len(x_block):# or j > 2:
break
s_val.append(s)
return s_val