def load_data_cache(use_test=False):
# Random state
random_state = np.random.RandomState(seed=42)
if use_test:
print("!!! USING TEST DATA !!!")
(X_train, y_train), (X_valid,
y_valid), (X_test, y_test) = airlines.load_data(
random_state=random_state,
test_size=0.33,
valid_size=0.33 * (1 - 0.33))
X_train = np.concatenate([X_train, X_valid])
y_train = np.concatenate([y_train, y_valid])
X_valid, y_valid = X_test, y_test
else:
(X_train, y_train), (X_valid, y_valid), _ = airlines.load_data(
random_state=random_state,
test_size=0.33,
valid_size=0.33 * (1 - 0.33))
prepro_output = preprocessing.OneHotEncoder()
y_train = y_train.reshape(-1, 1)
y_valid = y_valid.reshape(-1, 1)
y_train = prepro_output.fit_transform(y_train).toarray()
y_valid = prepro_output.transform(y_valid).toarray()
prepro_input = minmaxstdscaler()
X_train = prepro_input.fit_transform(X_train)
X_valid = prepro_input.transform(X_valid)
print(f"X_train shape: {np.shape(X_train)}")
print(f"y_train shape: {np.shape(y_train)}")
print(f"X_valid shape: {np.shape(X_valid)}")
print(f"y_valid shape: {np.shape(y_valid)}")
return (X_train, y_train), (X_valid, y_valid)
def test_config(config):
import numpy as np
from sklearn.utils import check_random_state
from sklearn.ensemble import RandomForestClassifier
from deephyper.benchmark.datasets import airlines as dataset
rs_data = np.random.RandomState(seed=42)
ratio_test = 0.33
ratio_valid = (1 - ratio_test) * 0.33
train, valid, test = dataset.load_data(random_state=rs_data,
test_size=ratio_test,
valid_size=ratio_valid)
rs_classifier = check_random_state(42)
classifier = RandomForestClassifier(n_jobs=8,
random_state=rs_classifier,
**config)
classifier.fit(*train)
acc_train = classifier.score(*train)
acc_valid = classifier.score(*valid)
acc_test = classifier.score(*test)
print(f"Accuracy on Training: {acc_train:.3f}")
print(f"Accuracy on Validation: {acc_valid:.3f}")
print(f"Accuracy on Testing: {acc_test:.3f}")
def load_data():
# In this case passing a random state is critical to make sure
# that the same data are loaded all the time and that the test set
# is not mixed with either the training or validation set.
# It is important to not avoid setting a global seed for safety reasons.
random_state = np.random.RandomState(seed=42)
# Proportion of the test set on the full dataset
ratio_test = 0.33
# Proportion of the valid set on "dataset \ test set"
# here we want the test and validation set to have same number of elements
ratio_valid = (1 - ratio_test) * 0.33
# The 3rd result is ignored with "_" because it corresponds to the test set
# which is not interesting for us now.
(X_train,
y_train), (X_valid,
y_valid), _ = dataset.load_data(random_state=random_state,
test_size=ratio_test,
valid_size=ratio_valid)
# Uncomment the next line if you want to sub-sample the training data to speed-up
# the search, "n_samples" controls the size of the new training data
# X_train, y_train = resample(X_train, y_train, n_samples=int(1e4))
print(f"X_train shape: {np.shape(X_train)}")
print(f"y_train shape: {np.shape(y_train)}")
print(f"X_valid shape: {np.shape(X_valid)}")
print(f"y_valid shape: {np.shape(y_valid)}")
return (X_train, y_train), (X_valid, y_valid)
def test_load_data_airlines():
from deephyper.benchmark.datasets import airlines
import numpy as np
names = ["train", "valid", "test "]
data = airlines.load_data(random_state=42, summary=True)
for (X, y), subset_name in zip(data, names):
print(
f"X_{subset_name} shape: ",
np.shape(X),
f", y_{subset_name} shape: ",
np.shape(y),
)
from dhproj.advanced_hpo.mapping import CLASSIFIERS
from deephyper.benchmark.datasets import airlines as dataset
from sklearn.utils import check_random_state
rs_clf = check_random_state(42)
rs_data = check_random_state(42)
ratio_test = 0.33
ratio_valid = (1 - ratio_test) * 0.33
train, valid, test = dataset.load_data(
random_state=rs_data,
test_size=ratio_test,
valid_size=ratio_valid,
)
for clf_name, clf_class in CLASSIFIERS.items():
print(clf_name)
clf = clf_class(random_state=rs_clf)
clf.fit(*train)
acc_train = clf.score(*train)
acc_valid = clf.score(*valid)
acc_test = clf.score(*test)
print(f"Accuracy on Training: {acc_train:.3f}")
print(f"Accuracy on Validation: {acc_valid:.3f}")
print(f"Accuracy on Testing: {acc_test:.3f}\n")
def load_data():
train, valid, _ = airlines.load_data(random_state=42)
return train, valid
