def test_fit():
with dask.config.set(scheduler="single-threaded"):
sgd = SGDClassifier(max_iter=5, tol=1e-3)
sgd = fit(sgd, X, Y, classes=np.array([-1, 0, 1]))
sol = sgd.predict(z)
result = predict(sgd, Z)
assert result.chunks == ((2, 2), )
assert result.compute().tolist() == sol.tolist()
def test_dataframes():
df = pd.DataFrame({"x": range(10), "y": [0, 1] * 5})
ddf = dd.from_pandas(df, npartitions=2)
with dask.config.set(scheduler="single-threaded"):
sgd = SGDClassifier(max_iter=5, tol=1e-3)
sgd = fit(sgd, ddf[["x"]], ddf.y, classes=[0, 1])
sol = sgd.predict(df[["x"]])
result = predict(sgd, ddf[["x"]])
da.utils.assert_eq(sol, result)