def setUpClass(cls):
"""Set up model to test."""
cls = cls._prep_data(cls, reg=True)
cls.mod = Incremental(
StreamingEXTR(n_estimators_per_chunk=1,
max_n_estimators=39,
verbose=1))
# Set expected number of estimators
# This should be set manually depending on data.
cls.expected_n_estimators = 10
# Set helper values
super().setUpClass()
def setUpClass(cls):
"""Set up model to test."""
cls.n_samples = 1000
cls.x, cls.y = sklearn.datasets.make_regression(n_samples=int(2e4),
random_state=0,
n_features=400)
cls.mod = StreamingEXTR(n_estimators_per_chunk=1, max_n_estimators=39)
# Set expected number of estimators
cls.expected_n_estimators = 39
# Set helper values
super().setUpClass()
def setUpClass(cls):
"""Set up model to test."""
cls = cls._prep_data(cls, reg=True)
cls.mod = Incremental(
StreamingEXTR(n_estimators_per_chunk=4,
n_jobs=-1,
max_n_estimators=np.inf,
verbose=1))
# Set expected number of estimators
cls.expected_n_estimators = 40
# Set helper values
super().setUpClass()
def setUpClass(cls):
"""Set up model to test."""
cls.spf_n_fits = 10
cls.spf_sample_prop = 0.1
cls.dask_feeding = False
cls.n_estimators_per_sample = 10
cls.mod = StreamingEXTR(
verbose=1,
n_estimators_per_chunk=cls.n_estimators_per_sample,
max_n_estimators=np.inf,
dask_feeding=cls.dask_feeding,
spf_sample_prop=cls.spf_sample_prop,
spf_n_fits=cls.spf_n_fits)
super().setUpClass()
def bunch_of_examples():
from sklearn.datasets import make_blobs, make_regression
x, y = make_regression(n_samples=int(2e5),
random_state=0,
n_features=40)
srfr = StreamingRFR(n_estimators_per_chunk=5,
spf_n_fits=10,
dask_feeding=False,
verbose=0,
n_jobs=2)
srfr.fit(x, y)
# Fit 10 regressors
for _ in range(10):
x, y = make_regression(n_samples=int(2e5),
random_state=0,
n_features=40)
srfr = StreamingRFR(n_estimators_per_chunk=5,
max_n_estimators=100,
verbose=0,
n_jobs=5)
chunk_size = int(2e3)
for _ in range(20):
sample_idx = np.random.randint(0, x.shape[0], chunk_size)
srfr.partial_fit(x[sample_idx], y[sample_idx],
classes=np.unique(y))
print(f"SRFR: {srfr.score(x, y)}")
sext = StreamingEXTR(n_estimators_per_chunk=5,
max_n_estimators=100,
verbose=0,
n_jobs=5)
for _ in range(20):
sample_idx = np.random.randint(0, x.shape[0], chunk_size)
sext.partial_fit(x[sample_idx], y[sample_idx],
classes=np.unique(y))
print(f"SEXTR: {sext.score(x, y)}")
# Fit 10 classifiers
for _ in range(10):
x, y = make_blobs(n_samples=int(2e5),
random_state=0,
n_features=40,
centers=2,
cluster_std=100)
srfc = StreamingRFC(n_estimators_per_chunk=5,
max_n_estimators=100,
verbose=0,
n_jobs=5)
chunk_size = int(2e3)
for _ in range(20):
sample_idx = np.random.randint(0, x.shape[0], chunk_size)
srfc.partial_fit(x[sample_idx], y[sample_idx],
classes=np.unique(y))
print(f"SRFC: {srfc.score(x, y)}")
sext = StreamingEXTC(n_estimators_per_chunk=5,
max_n_estimators=100,
verbose=0,
n_jobs=5)
for _ in range(20):
sample_idx = np.random.randint(0, x.shape[0], chunk_size)
sext.partial_fit(x[sample_idx], y[sample_idx],
classes=np.unique(y))
print(f"SEXTC: {sext.score(x, y)}")