def run(cls, proba, preprocessing, **kwargs):
"""Function for executing specified test."""
if cls == 'subset':
p = kwargs['n_partitions']
else:
p = 1
ests = ESTS[(proba, preprocessing)]
prep = PREPROCESSING if preprocessing else None
data = Data(cls, proba, preprocessing, **kwargs)
X, y = data.get_data((LEN, WIDTH), MOD)
(F, wf), _ = data.ground_truth(X, y, p)
ens = EnsembleTransformer()
ens.add(cls, ests, prep, proba=proba, **kwargs)
ens.fit(X, y)
pred = ens.transform(X)
np.testing.assert_array_equal(F, pred)
lc_transform)
PROBA = True
PROCESSING = True
LEN = 12
WIDTH = 2
FOLDS = 3
PARTITIONS = 2
MOD, r = divmod(LEN, FOLDS)
assert r == 0
lg = LayerGenerator()
data = Data('subset', PROBA, PROCESSING, PARTITIONS, FOLDS)
X, y = data.get_data((LEN, WIDTH), MOD)
(F, wf), (P, wp) = data.ground_truth(X, y, subsets=PARTITIONS)
layer = lg.get_layer('subset', PROBA, PROCESSING, PARTITIONS, FOLDS)
lc = lg.get_layer_container('subset', PROBA, PROCESSING, PARTITIONS, FOLDS)
layer.indexer.fit(X)
cache = Cache(X, y, data)
def test_layer_fit():
"""[Parallel | Subset | Prep | Proba] test layer fit."""
layer_fit(layer, cache, F, wf)
def test_layer_predict():
lc_fit, lc_from_file, lc_from_csv, lc_predict,
lc_transform, lc_feature_prop)
PROBA = True
PROCESSING = False
LEN = 6
WIDTH = 2
FOLDS = 3
MOD, r = divmod(LEN, FOLDS)
assert r == 0
lg = LayerGenerator()
data = Data('blend', PROBA, PROCESSING)
X, y = data.get_data((LEN, WIDTH), MOD)
(F, wf), (P, wp) = data.ground_truth(X, y)
layer = lg.get_layer('blend', PROBA, PROCESSING)
lc = lg.get_layer_container('blend', PROBA, PROCESSING)
lc_p = lg.get_layer_container('blend',
PROBA,
PROCESSING,
propagate_features=[1])
layer.indexer.fit(X)
cache = Cache(X, y, data)
def test_layer_fit():
"""[Parallel | Blend | No Prep | Proba] test layer fit."""
"""
import numpy as np
from mlens.metrics import rmse
from mlens.base import BlendIndex
from mlens.utils.dummy import Data, ESTIMATORS, PREPROCESSING, OLS
from mlens.ensemble import BlendEnsemble
LEN = 6
WIDTH = 2
MOD = 2
data = Data('blend', False, True)
X, y = data.get_data((LEN, WIDTH), MOD)
(F, wf), (P, wp) = data.ground_truth(X, y, 1, False)
def test_run():
"""[Blend] 'fit' and 'predict' runs correctly."""
meta = OLS()
meta.fit(F, y[3:])
g = meta.predict(P)
ens = BlendEnsemble(test_size=3)
ens.add(ESTIMATORS, PREPROCESSING, dtype=np.float64)
ens.add(OLS(), meta=True, dtype=np.float64)
ens.fit(X, y)
pred = ens.predict(X)
raise ValueError
def null_func(y, p):
"""Test for failed aggregation"""
return 'not_value'
FOLDS = 3
LEN = 6
WIDTH = 2
MOD = 2
data1 = Data('stack', False, True, FOLDS)
X1, y1 = data1.get_data((LEN, WIDTH), MOD)
(F1, wf1), (P1, wp1) = data1.ground_truth(X1, y1, 1, False)
G1 = OLS().fit(F1, y1).predict(P1)
data2 = Data('stack', False, False, FOLDS)
X2, y2 = data1.get_data((LEN, WIDTH), MOD)
(F2, wf2), (P2, wp2) = data2.ground_truth(X2, y2, 1, False)
G2 = OLS().fit(F2, y2).predict(P2)
ens1 = SuperLearner(folds=FOLDS, scorer=rmse, verbose=100)
ens1.add(ESTIMATORS, PREPROCESSING, dtype=np.float64)
ens1.add_meta(OLS(), dtype=np.float64)
ens1_b = SuperLearner(folds=FOLDS, scorer=in_script_func)
ens1_b.add(ESTIMATORS, PREPROCESSING, dtype=np.float64)
ens1_b.add_meta(OLS(), dtype=np.float64)
