def fit(self, pipeline_config, instance):
assert pipeline_config['problem_type'] in [
'feature_classification', 'feature_multilabel',
'feature_regression'
]
dm = DataManager(verbose=pipeline_config["data_manager_verbose"])
dm.read_data(instance,
is_classification=(pipeline_config["problem_type"] in [
'feature_classification', 'feature_multilabel'
]),
test_split=pipeline_config["test_split"])
return {"data_manager": dm}
def fit(self, pipeline_config, instance):
# Get data manager for train, val, test data
if pipeline_config['problem_type'] in ['feature_classification', 'feature_multilabel', 'feature_regression']:
dm = DataManager(verbose=pipeline_config["data_manager_verbose"])
if pipeline_config['test_instances'] is not None:
dm_test = DataManager(verbose=pipeline_config["data_manager_verbose"])
else:
dm = ImageManager(verbose=pipeline_config["data_manager_verbose"])
if pipeline_config['test_instances'] is not None:
dm_test = ImageManager(verbose=pipeline_config["data_manager_verbose"])
# Read data
if pipeline_config['test_instances'] is not None:
# Use given test set
dm.read_data(instance,
is_classification=(pipeline_config["problem_type"] in ['feature_classification', 'feature_multilabel', 'image_classification']),
test_split=0.0)
dm_test.read_data(pipeline_config['test_instances'],
is_classification=(pipeline_config["problem_type"] in ['feature_classification', 'feature_multilabel', 'image_classification']),
test_split=0.0)
dm.X_test, dm.Y_test = dm_test.X_train, dm_test.Y_train.astype(np.int32)
else:
# Use test split
dm.read_data(instance,
is_classification=(pipeline_config["problem_type"] in ['feature_classification', 'feature_multilabel', 'image_classification']),
test_split=pipeline_config["test_split"])
return {"data_manager": dm}
from autoPyTorch import AutoNetClassification, AutoNetMultilabel
import autoPyTorch.pipeline.nodes as autonet_nodes
from autoPyTorch.components.metrics.additional_logs import test_result
import autoPyTorch.components.metrics as autonet_metrics
from autoPyTorch.data_management.data_manager import DataManager
dm = DataManager(verbose=1)
dataset_dir = os.path.abspath(os.path.join(os.path.dirname( __file__ ), '..', '..', 'datasets'))
# choose between the 5 defined testcases
TEST_CASE = 1
""" TEST CASE 1: Sparse data """
if TEST_CASE == 1:
dm.read_data(os.path.join(dataset_dir, "automl/newsgroups/newsgroups_public.info"), is_classification=True)
metric = "pac_metric"
additional_metrices = ["accuracy"]
""" TEST CASE 2: Sparse binary data """
if TEST_CASE == 2:
dm.read_data(os.path.join(dataset_dir, "automl/dorothea/dorothea_public.info"), is_classification=True)
metric = "auc_metric"
additional_metrices = ["accuracy"]
""" TEST CASE 3: Multilabel, sparse, binary, cv """
if TEST_CASE == 3:
dm.read_data(os.path.join(dataset_dir, "automl/tania/tania_public.info"), is_classification=True)
metric = "pac_metric"
additional_metrices = []
import os
import sys
import logging
from autoPyTorch import AutoNetClassification
from autoPyTorch.data_management.data_manager import DataManager
from autoPyTorch.utils.mem_test_thread import MemoryLogger
dm = DataManager(verbose=1)
dataset_dir = os.path.abspath(os.path.join(os.path.dirname( __file__ ), '..', 'datasets'))
dm.read_data(os.path.join(dataset_dir, "classification/dataset_28_optdigits.csv"), is_classification=True)
# 5620 samples, 10 classes, 65 features ---> 98% validation accuracy
mem_logger = MemoryLogger()
mem_logger.start()
try:
autonet = AutoNetClassification(early_stopping_patience=15, budget_type='epochs', min_budget=1, max_budget=9, num_iterations=1, log_level='error')
res = autonet.fit(X_train=dm.X,
import logging
from autoPyTorch import AutoNetClassification
from autoPyTorch.data_management.data_manager import DataManager
dm = DataManager(verbose=1)
dataset_dir = os.path.abspath(
os.path.join(os.path.dirname(__file__), '..', '..', 'datasets'))
# choose between the 10 classification testcases on real data.
TEST_CASE = 4
if TEST_CASE == 1:
dm.read_data(os.path.join(dataset_dir,
"classification/dataset_22_mfeat-zernike.csv"),
is_classification=True)
# 2000 samples, 10 classes, 48 features
if TEST_CASE == 2:
dm.read_data(os.path.join(dataset_dir, "classification/phpbL6t4U.csv"),
is_classification=True)
# 13910 samples, 6 classes, 128 features
if TEST_CASE == 3:
dm.read_data(os.path.join(dataset_dir, "classification/php0iVrYT.csv"),
is_classification=True)
# 748 samples, 2 classes, 4 features
if TEST_CASE == 4:
dm.read_data(os.path.join(dataset_dir,
sys.path.append(os.path.abspath(os.path.join(__file__, "..", "..", "..")))
import logging
from autoPyTorch import AutoNetClassification
from autoPyTorch.data_management.data_manager import DataManager
dm = DataManager(verbose=1)
dataset_dir = os.path.abspath(
os.path.join(os.path.dirname(__file__), '..', '..', 'datasets'))
# choose between the 10 classification testcases on real data.
TEST_CASE = 4
if TEST_CASE == 1:
dm.read_data("openml:22", is_classification=True)
# 2000 samples, 10 classes, 48 features
if TEST_CASE == 2:
dm.read_data("openml:1476", is_classification=True)
# 13910 samples, 6 classes, 128 features
if TEST_CASE == 3:
dm.read_data("openml:1464", is_classification=True)
# 748 samples, 2 classes, 4 features
if TEST_CASE == 4:
dm.read_data("openml:31", is_classification=True)
if TEST_CASE == 5:
dm.read_data("openml:28", is_classification=True)