def simple_diego(X, Y, metrics='acc'):
from sklearn.model_selection import train_test_split
# Split dataset for model testing
X_train, X_valid, y_train, y_valid = train_test_split(X,
Y,
test_size=0.2,
random_state=42)
ts_autobin = create_study(X_train, y_train)
ts_autobin.generate_trial(n_jobs=10,
mode='cus',
time_left_for_this_task=3600,
per_run_time_limit=360,
initial_configurations_via_metalearning=25,
ensemble_size=10,
ensemble_nbest=3,
ensemble_memory_limit=1024,
seed=1,
ml_memory_limit=10240,
include_estimators=[
"adaboost", "extra_trees",
"k_nearest_neighbors", "libsvm_svc",
"random_forest", "gaussian_nb",
"xgradient_boosting"
])
ts_autobin.optimize(X_valid, y_valid, n_jobs=-1, metrics=metrics)
ts_autobin.show_models()
return ts_autobin.pipeline
sys.path.append("%s/../.." % root)
sys.path.append("%s/.." % root)
sys.path.append("%s/../../.." % root)
sys.path.append("%s/../diego" % root)
# import warnings filter
from warnings import simplefilter
# ignore all future warnings
simplefilter(action='ignore', category=FutureWarning)
import numpy as np
from diego.study import create_study
from autosklearn.classification import AutoSklearnClassifier
import sklearn
import sklearn.datasets
import sklearn.metrics
if __name__ == "__main__":
X, y = sklearn.datasets.load_digits(return_X_y=True)
X_train, X_test, y_train, y_test = \
sklearn.model_selection.train_test_split(X, y, random_state=2047, train_size=0.8, test_size=0.2)
s = create_study(X_train,
y_train,
is_autobin=False,
metrics='acc',
sample_method=None,
precision=np.float32)
# s.generate_autosk_trial(mode='fast', n_jobs=1)
s.optimize(X_test, y_test)
s.show_models()
Author: Charles_Lai Email: [email protected] """ import os import sys root = os.path.dirname(os.path.abspath(__file__)) sys.path.append("%s/../.." % root) sys.path.append("%s/.." % root) sys.path.append("%s/../diego" % root) sys.path.append("%s/../../.." % root) sys.path.append(u"{0:s}".format(root)) import numpy as np from diego.study import create_study from autosklearn.classification import AutoSklearnClassifier if __name__ == "__main__": import sklearn.datasets digits = sklearn.datasets.load_breast_cancer() X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split( digits.data, digits.target, train_size=0.8, test_size=0.2) s = create_study(X_train, y_train, is_autobin=True, sample_method=None, precision=np.float32) # s.generate_autosk_trial(mode='fast', n_jobs=1) s.optimize(X_test, y_test, metrics='acc') s.show_models()