def test_load_data_covertype():
from deephyper.benchmark.datasets import covertype
import numpy as np
names = ["train", "valid", "test"]
data = covertype.load_data(random_state=42)
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),
)
def load_data_cache():
# Random state
random_state = np.random.RandomState(seed=42)
(X_train, y_train), (X_valid, y_valid), _ = covertype.load_data(
random_state=random_state
)
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 load_data():
train, valid, _ = covertype.load_data(random_state=42)
return train, valid