def load_satimage(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
db0 = read_csv_data('data/classification/satimage/sat.trn.txt', sep=' ')
db1 = read_csv_data('data/classification/satimage/sat.tst.txt', sep=' ')
db = pd.concat([db0, db1])
db.columns = list(db.columns[:-1]) + ['target']
return construct_return_set(db,
"SATIMAGE",
return_X_y,
encode,
citation='krnn',
name="SATIMAGE",
verbose=verbose,
problem_type='classification',
onehot_threshold=onehot_threshold)
def load_abalone(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
db = read_csv_data('data/classification/abalone/abalone.data.txt')
db.columns = list(db.columns[:-1]) + ['target']
del db[db.columns[0]]
return construct_return_set(db,
"abalone",
return_X_y,
encode,
citation='krnn',
name="abalone",
verbose=verbose,
problem_type='classification',
onehot_threshold=onehot_threshold)
def load_ecoli(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
db = read_csv_data('data/classification/ecoli/ecoli.data.txt',
delim_whitespace=True)
db.columns = list(db.columns[:-1]) + ['target']
del db[db.columns[0]]
print(db.columns)
return construct_return_set(db,
"ecoli",
return_X_y,
encode,
citation='krnn',
name="ecoli",
verbose=verbose,
problem_type='classification',
onehot_threshold=onehot_threshold)
def load_airfoil(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
db = read_csv_data('data/regression/airfoil/airfoil_self_noise.dat.txt',
sep='\t')
columns = list(db.columns)
columns[-1] = 'target'
db.columns = columns
return construct_return_set(db,
"airfoil",
return_X_y,
encode,
citation='uci',
name="airfoil",
verbose=verbose,
problem_type='regression',
onehot_threshold=onehot_threshold)
def load_winequality_red(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
db = read_csv_data('data/regression/winequality_red/winequality-red.csv',
sep=';',
header=0)
columns = list(db.columns)
columns[-1] = 'target'
db.columns = columns
return construct_return_set(db,
"winequality_red",
return_X_y,
encode,
citation='uci',
name="winequality_red",
verbose=verbose,
problem_type='regression',
onehot_threshold=onehot_threshold)
def load_slump_test(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
db = read_csv_data('data/regression/slump_test/slump_test.data.txt',
sep=',',
header=0)
del db[db.columns[0]]
columns = list(db.columns)
columns[-1] = 'target'
db.columns = columns
return construct_return_set(db,
"slump_test",
return_X_y,
encode,
citation='uci',
name="slump_test",
verbose=verbose,
problem_type='regression',
onehot_threshold=onehot_threshold)
def load_yacht_hydrodynamics(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
db = read_csv_data(
'data/regression/yacht_hydrodynamics/yacht_hydrodynamics.data.txt',
sep=None,
header=0,
delim_whitespace=True)
columns = list(db.columns)
columns[-1] = 'target'
db.columns = columns
return construct_return_set(db,
"yacht_hydrodynamics",
return_X_y,
encode,
citation='uci',
name="yacht_hydrodynamics",
verbose=verbose,
problem_type='regression',
onehot_threshold=onehot_threshold)