def test_regressor(loop): # noqa
with cluster() as (s, [a, b]):
with Client(s['address'], loop=loop):
a = dlgbm.LGBMRegressor(local_listen_port=16400)
X2 = da.from_array(X, 5)
y2 = da.from_array(y, 5)
a.fit(X2, y2)
p1 = a.predict(X2)
b = lightgbm.LGBMRegressor()
b.fit(X, y)
assert_eq(p1, b.predict(X))
def test_regressor_local_predict(client, listen_port): # noqa
X, y, w, dX, dy, dw = _create_data('regression', output='array')
a = dlgbm.LGBMRegressor(local_listen_port=listen_port, seed=42)
a = a.fit(dX, dy, sample_weight=dw, client=client)
p1 = a.predict(dX)
p2 = a.to_local().predict(X)
s1 = r2_score(dy, p1)
p1 = p1.compute()
s2 = a.to_local().score(X, y)
print(s1)
# Predictions and scores should be the same
assert_eq(p1, p2)
np.isclose(s1, s2)
def test_regressor_local_predict(loop, listen_port):
with cluster() as (s, [a, b]):
with Client(s['address'], loop=loop):
X, y, w, dX, dy, dw = _create_data('regression', output="array")
a = dlgbm.LGBMRegressor(local_listen_port=listen_port, seed=42)
a = a.fit(dX, dy, sample_weight=dw)
p1 = a.predict(dX)
p2 = a.to_local().predict(X)
s1 = r2_score(dy, p1)
p1 = p1.compute()
s2 = a.to_local().score(X, y)
print(s1)
# Predictions and scores should be the same
assert_eq(p1, p2)
np.isclose(s1, s2)
def test_regressor_quantile(loop, output, listen_port, alpha):
with cluster() as (s, [a, b]):
with Client(s['address'], loop=loop) as client:
X, y, w, dX, dy, dw = _create_data('regression', output=output)
a = dlgbm.LGBMRegressor(local_listen_port=listen_port, seed=42, objective='quantile', alpha=alpha)
a = a.fit(dX, dy, client=client, sample_weight=dw)
p1 = a.predict(dX, client=client).compute()
q1 = np.count_nonzero(y < p1) / y.shape[0]
b = lightgbm.LGBMRegressor(seed=42, objective='quantile', alpha=alpha)
b.fit(X, y, sample_weight=w)
p2 = b.predict(X)
q2 = np.count_nonzero(y < p2) / y.shape[0]
# Quantiles should be right
np.isclose(q1, alpha, atol=.1)
np.isclose(q2, alpha, atol=.1)
def test_regress_newsread(client, listen_port):
data = dd.read_csv("./system_tests/data/*.gz",
compression="gzip",
blocksize=None)
dX = data.iloc[:, 1:]
dy = data.iloc[:, 0]
d_regress = dlgbm.LGBMRegressor(n_estimators=50,
local_listen_port=listen_port)
d_regress.fit(dX, dy)
dy_pred = d_regress.predict(dX, client=client)
# The dask_ml.metrics.r2_score method fails with dataframes so we compute the R2 score ourselves
numerator = ((dy - dy_pred)**2).sum()
denominator = ((dy - dy.mean())**2).sum()
r2_score = 1 - numerator / denominator
r2_score = r2_score.compute()
print(r2_score)
assert r2_score > 0.8
def test_regressor(output, client, listen_port): # noqa
X, y, w, dX, dy, dw = _create_data('regression', output=output)
a = dlgbm.LGBMRegressor(time_out=5, local_listen_port=listen_port, seed=42)
a = a.fit(dX, dy, client=client, sample_weight=dw)
p1 = a.predict(dX, client=client)
if output != 'dataframe':
s1 = r2_score(dy, p1)
p1 = p1.compute()
b = lightgbm.LGBMRegressor(seed=42)
b.fit(X, y, sample_weight=w)
s2 = b.score(X, y)
p2 = b.predict(X)
# Scores should be the same
if output != 'dataframe':
assert_eq(s1, s2, atol=.01)
# Predictions should be roughly the same
assert_eq(y, p1, rtol=1., atol=50.)
assert_eq(y, p2, rtol=1., atol=50.)
