def load_residential_building(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
# target: V9
db = read_xls_data(
'data/regression/residential_building/Residential-Building-Data-Set.xlsx'
)
db = db.drop(0, axis='index')
db.reset_index(drop=True, inplace=True)
del db[db.columns[-1]]
columns = list(db.columns)
columns[-1] = 'target'
db.columns = columns
for c in db.columns:
db[c] = db[c].astype(float)
return construct_return_set(db,
"residential_building",
return_X_y,
encode,
citation='uci',
name="residential_building",
verbose=verbose,
problem_type='regression',
onehot_threshold=onehot_threshold)
def load_stock_portfolio_performance(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
# target: normalized annual return
db = read_xls_data(
'data/regression/stock_portfolio_performance/stock portfolio performance data set.xlsx',
sheet_name='all period')
db.columns = db.iloc[0].values
db = db.drop(db.index[0], axis='index')
db.reset_index(drop=True, inplace=True)
del db[db.columns[0]]
columns = list(db.columns[0:5]) + [db.columns[11]]
db = db[columns]
columns = list(db.columns)
columns[-1] = 'target'
db.columns = columns
for c in db.columns:
db[c] = db[c].astype(float)
return construct_return_set(db,
"stock_portfolio_performance",
return_X_y,
encode,
citation='uci',
name="stock_portfolio_performance",
verbose=verbose,
problem_type='regression',
onehot_threshold=onehot_threshold)
def load_puma32h(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
data, meta = read_arff_data('data/regression/puma32h/puma32h.dat')
db = pd.DataFrame(data)
db.columns = list(db.columns[:-1]) + ['target']
return construct_return_set(db,
"puma32h",
return_X_y,
encode,
citation='keel',
name="puma32h",
verbose=verbose,
problem_type='regression')
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_zoo(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
data, meta = read_arff_data('data/classification/zoo/zoo.dat')
db = pd.DataFrame(data)
db.columns = list(db.columns[:-1]) + ['target']
return construct_return_set(db,
"zoo",
return_X_y,
encode,
citation='keel',
name="zoo",
verbose=verbose,
problem_type='classification',
onehot_threshold=onehot_threshold)
def load_communities(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
db = read_csv_data('data/regression/communities/communities.data', sep=',')
columns = list(db.columns)
columns[-1] = 'target'
db.columns = columns
return construct_return_set(db,
"communities",
return_X_y,
encode,
citation='uci',
name="communities",
verbose=verbose,
problem_type='regression',
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_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_ccpp(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
db = read_xls_data('data/regression/ccpp/Folds5x2_pp.xlsx',
sheet_name='Sheet1')
columns = list(db.columns)
columns[-1] = 'target'
db.columns = columns
return construct_return_set(db,
"ccpp",
return_X_y,
encode,
citation='uci',
name="ccpp",
verbose=verbose,
problem_type='regression',
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_cpu_performance(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
db = read_csv_data('data/regression/cpu_performance/machine.data.txt',
sep=',')
del db[db.columns[-1]]
del db[db.columns[1]]
columns = list(db.columns)
columns[-1] = 'target'
db.columns = columns
return construct_return_set(db,
"cpu_performance",
return_X_y,
encode,
citation='uci',
name="cpu_performance",
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)
def load_real_estate_valuation(return_X_y=False,
encode=True,
verbose=False,
onehot_threshold=10):
db = read_xls_data(
'data/regression/real_estate_valuation/Real estate valuation data set.xlsx'
)
del db[db.columns[0]]
columns = list(db.columns)
columns[-1] = 'target'
db.columns = columns
for c in db.columns:
db[c] = db[c].astype(float)
return construct_return_set(db,
"real_estate_valuation",
return_X_y,
encode,
citation='uci',
name="real_estate_valuation",
verbose=verbose,
problem_type='regression',
onehot_threshold=onehot_threshold)
