def test_regressor_quantile(output, client, listen_port, alpha):
X, y, w, dX, dy, dw = _create_data(objective='regression', output=output)
dask_regressor = dlgbm.DaskLGBMRegressor(local_listen_port=listen_port,
seed=42,
objective='quantile',
alpha=alpha,
n_estimators=10,
num_leaves=10,
tree_learner_type='data_parallel')
dask_regressor = dask_regressor.fit(dX,
dy,
client=client,
sample_weight=dw)
p1 = dask_regressor.predict(dX).compute()
q1 = np.count_nonzero(y < p1) / y.shape[0]
local_regressor = lightgbm.LGBMRegressor(seed=42,
objective='quantile',
alpha=alpha,
n_estimatores=10,
num_leaves=10)
local_regressor.fit(X, y, sample_weight=w)
p2 = local_regressor.predict(X)
q2 = np.count_nonzero(y < p2) / y.shape[0]
# Quantiles should be right
np.testing.assert_allclose(q1, alpha, atol=0.2)
np.testing.assert_allclose(q2, alpha, atol=0.2)
client.close()
def test_regressor_pred_contrib(output, client, listen_port):
X, y, w, dX, dy, dw = _create_data(objective='regression', output=output)
dask_regressor = dlgbm.DaskLGBMRegressor(time_out=5,
local_listen_port=listen_port,
tree_learner='data',
n_estimators=10,
num_leaves=10)
dask_regressor = dask_regressor.fit(dX,
dy,
sample_weight=dw,
client=client)
preds_with_contrib = dask_regressor.predict(dX,
pred_contrib=True).compute()
local_regressor = lightgbm.LGBMRegressor(n_estimators=10, num_leaves=10)
local_regressor.fit(X, y, sample_weight=w)
local_preds_with_contrib = local_regressor.predict(X, pred_contrib=True)
if output == "scipy_csr_matrix":
preds_with_contrib = np.array(preds_with_contrib.todense())
# contrib outputs for distributed training are different than from local training, so we can just test
# that the output has the right shape and base values are in the right position
num_features = dX.shape[1]
assert preds_with_contrib.shape[1] == num_features + 1
assert preds_with_contrib.shape == local_preds_with_contrib.shape
def test_regressor(output, client, listen_port):
X, y, w, dX, dy, dw = _create_data(objective='regression', output=output)
dask_regressor = dlgbm.DaskLGBMRegressor(time_out=5,
local_listen_port=listen_port,
seed=42,
num_leaves=10,
tree='data')
dask_regressor = dask_regressor.fit(dX,
dy,
client=client,
sample_weight=dw)
p1 = dask_regressor.predict(dX)
if output != 'dataframe':
s1 = r2_score(dy, p1)
p1 = p1.compute()
local_regressor = lightgbm.LGBMRegressor(seed=42, num_leaves=10)
local_regressor.fit(X, y, sample_weight=w)
s2 = local_regressor.score(X, y)
p2 = local_regressor.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=100.)
assert_eq(y, p2, rtol=1., atol=50.)
client.close()
def test_regressor_quantile(output, client, listen_port, alpha):
X, y, w, dX, dy, dw = _create_data(objective='regression', output=output)
params = {
"objective": "quantile",
"alpha": alpha,
"random_state": 42,
"n_estimators": 10,
"num_leaves": 10
}
dask_regressor = dlgbm.DaskLGBMRegressor(local_listen_port=listen_port,
tree_learner_type='data_parallel',
**params)
dask_regressor = dask_regressor.fit(dX,
dy,
client=client,
sample_weight=dw)
p1 = dask_regressor.predict(dX).compute()
q1 = np.count_nonzero(y < p1) / y.shape[0]
local_regressor = lightgbm.LGBMRegressor(**params)
local_regressor.fit(X, y, sample_weight=w)
p2 = local_regressor.predict(X)
q2 = np.count_nonzero(y < p2) / y.shape[0]
# Quantiles should be right
np.testing.assert_allclose(q1, alpha, atol=0.2)
np.testing.assert_allclose(q2, alpha, atol=0.2)
client.close()
def test_regressor_local_predict(client, listen_port):
X, y, w, dX, dy, dw = _create_data('regression', output='array')
dask_regressor = dlgbm.DaskLGBMRegressor(local_listen_port=listen_port,
seed=42)
dask_regressor = dask_regressor.fit(dX,
dy,
sample_weight=dw,
client=client)
p1 = dask_regressor.predict(dX)
p2 = dask_regressor.to_local().predict(X)
s1 = r2_score(dy, p1)
p1 = p1.compute()
s2 = dask_regressor.to_local().score(X, y)
# Predictions and scores should be the same
assert_eq(p1, p2)
assert_eq(s1, s2)
def test_regressor_local_predict(client, listen_port):
X, y, _, dX, dy, dw = _create_data('regression', output='array')
dask_regressor = dlgbm.DaskLGBMRegressor(local_listen_port=listen_port,
random_state=42,
n_estimators=10,
num_leaves=10,
tree_type='data')
dask_regressor = dask_regressor.fit(dX,
dy,
sample_weight=dw,
client=client)
p1 = dask_regressor.predict(dX)
p2 = dask_regressor.to_local().predict(X)
s1 = r2_score(dy, p1)
p1 = p1.compute()
s2 = dask_regressor.to_local().score(X, y)
# Predictions and scores should be the same
assert_eq(p1, p2)
assert_eq(s1, s2)
client.close()
