def evaluate_fe_pipeline():
from mindware.utils.data_manager import DataManager
dm = DataManager()
# file_path = "data/proprocess_data.csv"
file_path = 'data/a9a/dataset_183_adult.csv'
dm.load_train_csv(file_path)
pipeline = FEPipeline(fe_enabled=True).fit(dm)
train_data = pipeline.transform(dm)
print(train_data)
print(train_data.data)
def load_data(dataset,
data_dir='./',
datanode_returned=False,
preprocess=True,
task_type=None):
dm = DataManager()
if task_type is None:
data_path = data_dir + 'data/datasets/%s.csv' % dataset
elif task_type in CLS_TASKS:
data_path = data_dir + 'data/cls_datasets/%s.csv' % dataset
elif task_type in RGS_TASKS:
data_path = data_dir + 'data/rgs_datasets/%s.csv' % dataset
else:
raise ValueError("Unknown task type %s" % str(task_type))
# Load train data.
if dataset in [
'higgs', 'amazon_employee', 'spectf', 'usps', 'vehicle_sensIT',
'codrna'
]:
label_column = 0
elif dataset in ['rmftsa_sleepdata(1)']:
label_column = 1
else:
label_column = -1
if dataset in ['spambase', 'messidor_features']:
header = None
else:
header = 'infer'
if dataset in ['winequality_white', 'winequality_red']:
sep = ';'
else:
sep = ','
train_data_node = dm.load_train_csv(
data_path,
label_col=label_column,
header=header,
sep=sep,
na_values=["n/a", "na", "--", "-", "?"])
if preprocess:
pipeline = FEPipeline(fe_enabled=False,
metric='acc',
task_type=task_type)
train_data = pipeline.fit_transform(train_data_node)
else:
train_data = train_data_node
if datanode_returned:
return train_data
else:
X, y = train_data.data
feature_types = train_data.feature_types
return X, y, feature_types
class TabularDataset(BaseDataset):
def __init__(self,
data_path: str,
is_regression=False,
label_column=-1,
header='infer',
sep=',',
nan_values=("n/a", "na", "--", "-", "?"),
train_val_split: bool = False,
val_split_size: float = 0.2):
super().__init__()
self.is_regression = is_regression
self.train_val_split = train_val_split
self.val_split_size = val_split_size
self.data_path = data_path
self.label_column = label_column
self.header = header
self.sep = sep
self.nan_values = nan_values
self.data_manager = None
self._process_pipeline = None
def load_tabular_data(self, data_path):
self.data_manager = DataManager()
train_data_node = self.data_manager.load_train_csv(
data_path,
label_col=self.label_column,
header=self.header,
sep=self.sep,
na_values=list(self.nan_values))
task_type = REGRESSION if self.is_regression else CLASSIFICATION
self._process_pipeline = FEPipeline(fe_enabled=False,
metric='acc',
task_type=task_type)
return self._process_pipeline.fit_transform(train_data_node)
def load_data(self):
self.train_dataset = self.load_tabular_data(self.data_path)
def load_test_data(self):
test_data_node = self.data_manager.load_test_csv(self.test_data_path,
has_label=False,
keep_default_na=True,
header=self.header,
sep=self.sep)
self.test_dataset = self._process_pipeline.transform(test_data_node)
choices=['none', 'bagging', 'blending', 'stacking', 'ensemble_selection'])
parser.add_argument('--n_jobs', type=int, default=1)
args = parser.parse_args()
time_limit = args.time_limit
eval_type = args.eval_type
n_jobs = args.n_jobs
ensemble_method = args.ens_method
if ensemble_method == 'none':
ensemble_method = None
print('==> Start to evaluate with Budget %d' % time_limit)
dm = DataManager()
train_node = dm.load_train_csv("train_dataset.csv", label_col=-1, header='infer', na_values=['nan', '?'])
test_node = dm.load_test_csv("test_dataset.csv", header='infer', has_label=True)
from mindware.components.utils.constants import REGRESSION
pipeline = FEPipeline(fe_enabled=False, task_type=REGRESSION)
train_data = pipeline.fit_transform(train_node)
test_data = pipeline.transform(test_node)
save_dir = './data/eval_exps/soln-ml'
if not os.path.exists(save_dir):
os.makedirs(save_dir)
rgs = Regressor(metric='mse',
ensemble_method=ensemble_method,
evaluation=eval_type,
time_limit=time_limit,