def load_data(dtype=np.float32, order='F'):
"""Load the data, then cache and memmap the train/test split"""
######################################################################
# Load dataset
safe_print("Loading dataset...")
data = fetch_mldata('MNIST original')
X = check_array(data['data'], dtype=dtype, order=order)
y = data["target"]
# Normalize features
X = X / 255
# Create train-test split (as [Joachims, 2006])
safe_print("Creating train-test split...")
n_train = 60000
X_train = X[:n_train]
y_train = y[:n_train]
X_test = X[n_train:]
y_test = y[n_train:]
return X_train, X_test, y_train, y_test
'No Preprocessing': [
RandomForestRegressor(random_state=SEED),
GradientBoostingRegressor()
]
}
ens.add(est, prep)
ens.add(GradientBoostingRegressor(), meta=True)
return ens
if __name__ == '__main__':
safe_print("\nML-ENSEMBLE\n")
safe_print("Benchmark of ML-ENSEMBLE against Scikit-learn estimators "
"on the friedman1 dataset.\n")
safe_print("Scoring metric: Root Mean Squared Error.\n")
safe_print("Available CPUs: %i\n" % os.cpu_count())
SEED = 2017
np.random.seed(SEED)
step = 4000
mi = step
mx = 40000 + step
ens_multi = build_ensemble(folds=2, shuffle=False, n_jobs=-1)
parser.add_argument('--classifiers',
nargs="+",
choices=ESTIMATORS,
type=str,
default=['Subsemble', 'BlendEnsemble'],
help="list of classifiers to benchmark.")
parser.add_argument('--order',
nargs="?",
default="C",
type=str,
choices=["F", "C"],
help="Allow to choose between fortran and C ordered "
"data")
args = vars(parser.parse_args())
safe_print(__doc__)
X_train, X_test, y_train, y_test = load_data(order=args["order"])
safe_print("")
safe_print("Dataset statistics:")
safe_print("===================")
safe_print("%s %d" % ("number of features:".ljust(25), X_train.shape[1]))
safe_print("%s %d" %
("number of classes:".ljust(25), np.unique(y_train).size))
safe_print("%s %s" % ("data type:".ljust(25), X_train.dtype))
safe_print("%s %d (size=%dMB)" %
("number of train samples:".ljust(25), X_train.shape[0],
int(X_train.nbytes / 1e6)))
safe_print("%s %d (size=%dMB)" %
("number of test samples:".ljust(25), X_test.shape[0],