def clustering_datagen(matrix_dim, matrix_type, datagen_dir, config_dir):
path_name = '.'.join(['clustering', matrix_type, str(matrix_dim)])
datagen_write = join(datagen_dir, path_name)
save_path = join(config_dir, path_name)
row, col = split_rowcol(matrix_dim)
X = join(datagen_write, 'X.data')
Y = join(datagen_write, 'Y.data')
YbyC = join(datagen_write, 'YbyC.data')
C = join(datagen_write, 'C.data')
nc = '50'
dc = '10.0'
dr = '1.0'
fbf = '100.0'
cbf = '100.0'
config = dict(nr=row,
nf=col,
nc=nc,
dc=dc,
dr=dr,
fbf=fbf,
cbf=cbf,
X=X,
C=C,
Y=Y,
YbyC=YbyC,
fmt=DATA_FORMAT)
config_writer(save_path + '.json', config)
return save_path
def regression1_datagen(matrix_dim, matrix_type, datagen_dir, config_dir):
path_name = '.'.join(['regression1', matrix_type, str(matrix_dim)])
datagen_write = join(datagen_dir, path_name)
save_path = join(config_dir, path_name)
row, col = split_rowcol(matrix_dim)
numSamples = row
numFeatures = col
maxFeatureValue = '5'
maxWeight = '5'
loc_weights = join(datagen_write, 'weight.data')
loc_data = join(datagen_write, 'X.data')
loc_labels = join(datagen_write, 'Y.data')
noise = '1'
intercept = '0'
sparsity = MATRIX_TYPE_DICT[matrix_type]
tranform_labels = '1'
fmt = DATA_FORMAT
config = [
numSamples, numFeatures, maxFeatureValue, maxWeight, loc_weights,
loc_data, loc_labels, noise, intercept, sparsity, fmt, tranform_labels
]
config_writer(save_path + '.json', config)
return save_path
def stats1_datagen(matrix_dim, matrix_type, datagen_dir, config_dir):
path_name = '.'.join(['stats1', matrix_type, str(matrix_dim)])
datagen_write = join(datagen_dir, path_name)
save_path = join(config_dir, path_name)
row, col = split_rowcol(matrix_dim)
DATA = join(datagen_write, 'X.data')
TYPES = join(datagen_write, 'types')
TYPES1 = join(datagen_write, 'set1.types')
TYPES2 = join(datagen_write, 'set2.types')
INDEX1 = join(datagen_write, 'set1.indices')
INDEX2 = join(datagen_write, 'set2.indices')
MAXDOMAIN = '1100'
SETSIZE = '20'
LABELSETSIZE = '10'
# NC should be less than C and more than num0
# NC = 10 (old value)
# num0 = NC/2
# num0 < NC < C
# NC = C/2
NC = int(int(col)/2)
config = dict(R=row, C=col, NC=NC, MAXDOMAIN=MAXDOMAIN, DATA=DATA, TYPES=TYPES, SETSIZE=SETSIZE,
LABELSETSIZE=LABELSETSIZE, TYPES1=TYPES1, TYPES2=TYPES2, INDEX1=INDEX1,
INDEX2=INDEX2, fmt=DATA_FORMAT)
config_writer(save_path + '.json', config)
return save_path
def regression1_datagen(matrix_dim, matrix_type, datagen_dir, config_dir):
path_name = '.'.join(['regression1', matrix_type, str(matrix_dim)])
datagen_write = join(datagen_dir, path_name)
save_path = join(config_dir, path_name)
row, col = split_rowcol(matrix_dim)
numSamples = row
numFeatures = col
maxFeatureValue = '5'
maxWeight = '5'
loc_weights = join(datagen_write, 'weight.data')
loc_data = join(datagen_write, 'X.data')
loc_labels = join(datagen_write, 'Y.data')
noise = '1'
intercept = '0'
sparsity = MATRIX_TYPE_DICT[matrix_type]
tranform_labels = '1'
fmt = DATA_FORMAT
config = [numSamples, numFeatures, maxFeatureValue, maxWeight, loc_weights, loc_data,
loc_labels, noise, intercept, sparsity, fmt, tranform_labels]
config_writer(save_path + '.json', config)
return save_path
def stats1_datagen(matrix_dim, matrix_type, datagen_dir, config_dir):
path_name = '.'.join(['stats1', matrix_type, str(matrix_dim)])
datagen_write = join(datagen_dir, path_name)
save_path = join(config_dir, path_name)
row, col = split_rowcol(matrix_dim)
DATA = join(datagen_write, 'X.data')
TYPES = join(datagen_write, 'types')
TYPES1 = join(datagen_write, 'set1.types')
TYPES2 = join(datagen_write, 'set2.types')
INDEX1 = join(datagen_write, 'set1.indices')
INDEX2 = join(datagen_write, 'set2.indices')
MAXDOMAIN = '1100'
SETSIZE = '20'
LABELSETSIZE = '10'
# NC should be less than C and more than num0
# NC = 10 (old value)
# num0 = NC/2
# num0 < NC < C
# NC = C/2
NC = int(int(col)/2)
config = dict(R=row, C=col, NC=NC, MAXDOMAIN=MAXDOMAIN, DATA=DATA, TYPES=TYPES, SETSIZE=SETSIZE,
LABELSETSIZE=LABELSETSIZE, TYPES1=TYPES1, TYPES2=TYPES2, INDEX1=INDEX1,
INDEX2=INDEX2, fmt=DATA_FORMAT)
config_writer(save_path + '.json', config)
return save_path
def dimreduction_datagen(matrix_dim, matrix_type, datagen_dir, config_dir):
path_name = '.'.join(['dimreduction', matrix_type, str(matrix_dim)])
datagen_write = join(datagen_dir, path_name)
save_path = join(config_dir, path_name)
row, col = split_rowcol(matrix_dim)
R = row
C = col
OUT = join(datagen_write, 'X.data')
config = dict(R=R, C=C, OUT=OUT, FMT=DATA_FORMAT)
config_writer(save_path + '.json', config)
return save_path
def stats2_datagen(matrix_dim, matrix_type, datagen_dir, config_dir):
path_name = '.'.join(['stats2', matrix_type, str(matrix_dim)])
datagen_write = join(datagen_dir, path_name)
save_path = join(config_dir, path_name)
row, col = split_rowcol(matrix_dim)
D = join(datagen_write, 'X.data')
Xcid = join(datagen_write, 'Xcid.data')
Ycid = join(datagen_write, 'Ycid.data')
A = join(datagen_write, 'A.data')
config = dict(nr=row, nf=col, D=D, Xcid=Xcid, Ycid=Ycid,
A=A, fmt=DATA_FORMAT)
config_writer(save_path + '.json', config)
return save_path
def stats2_datagen(matrix_dim, matrix_type, datagen_dir, config_dir):
path_name = '.'.join(['stats2', matrix_type, str(matrix_dim)])
datagen_write = join(datagen_dir, path_name)
save_path = join(config_dir, path_name)
row, col = split_rowcol(matrix_dim)
D = join(datagen_write, 'X.data')
Xcid = join(datagen_write, 'Xcid.data')
Ycid = join(datagen_write, 'Ycid.data')
A = join(datagen_write, 'A.data')
config = dict(nr=row, nf=col, D=D, Xcid=Xcid, Ycid=Ycid,
A=A, fmt=DATA_FORMAT)
config_writer(save_path + '.json', config)
return save_path
def multinomial_datagen(matrix_dim, matrix_type, datagen_dir, config_dir):
path_name = '.'.join(['multinomial', matrix_type, str(matrix_dim)])
datagen_write = join(datagen_dir, path_name)
save_path = join(config_dir, path_name)
row, col = split_rowcol(matrix_dim)
numSamples = row
numFeatures = col
sparsity = MATRIX_TYPE_DICT[matrix_type]
num_categories = '150'
intercept = '0'
X = join(datagen_write, 'X.data')
Y = join(datagen_write, 'Y.data')
fmt = DATA_FORMAT
config = [numSamples, numFeatures, sparsity, num_categories, intercept,
X, Y, fmt, '1']
config_writer(save_path + '.json', config)
return save_path
def clustering_datagen(matrix_dim, matrix_type, datagen_dir, config_dir):
path_name = '.'.join(['clustering', matrix_type, str(matrix_dim)])
datagen_write = join(datagen_dir, path_name)
save_path = join(config_dir, path_name)
row, col = split_rowcol(matrix_dim)
X = join(datagen_write, 'X.data')
Y = join(datagen_write, 'Y.data')
YbyC = join(datagen_write, 'YbyC.data')
C = join(datagen_write, 'C.data')
nc = '50'
dc = '10.0'
dr = '1.0'
fbf = '100.0'
cbf = '100.0'
config = dict(nr=row, nf=col, nc=nc, dc=dc, dr=dr, fbf=fbf, cbf=cbf, X=X, C=C, Y=Y,
YbyC=YbyC, fmt=DATA_FORMAT)
config_writer(save_path + '.json', config)
return save_path
def multinomial_datagen(matrix_dim, matrix_type, datagen_dir, config_dir):
path_name = '.'.join(['multinomial', matrix_type, str(matrix_dim)])
datagen_write = join(datagen_dir, path_name)
save_path = join(config_dir, path_name)
row, col = split_rowcol(matrix_dim)
numSamples = row
numFeatures = col
sparsity = MATRIX_TYPE_DICT[matrix_type]
num_categories = '150'
intercept = '0'
X = join(datagen_write, 'X.data')
Y = join(datagen_write, 'Y.data')
fmt = DATA_FORMAT
config = [numSamples, numFeatures, sparsity, num_categories, intercept,
X, Y, fmt, '1']
config_writer(save_path + '.json', config)
return save_path