def test_fast_predict():
# test that the faster prediction change doesn't
# affect out-of-sample predictions:
# https://github.com/scikit-learn/scikit-learn/pull/6206
rng = np.random.RandomState(123)
n_samples = 10**3
# X values over the -10,10 range
X_train = 20.0 * rng.rand(n_samples) - 10
y_train = np.less(rng.rand(n_samples),
expit(X_train)).astype('int64').astype('float64')
weights = rng.rand(n_samples)
# we also want to test that everything still works when some weights are 0
weights[rng.rand(n_samples) < 0.1] = 0
slow_model = IsotonicRegression(y_min=0, y_max=1, out_of_bounds="clip")
fast_model = IsotonicRegression(y_min=0, y_max=1, out_of_bounds="clip")
# Build interpolation function with ALL input data, not just the
# non-redundant subset. The following 2 lines are taken from the
# .fit() method, without removing unnecessary points
X_train_fit, y_train_fit = slow_model._build_y(X_train,
y_train,
sample_weight=weights,
trim_duplicates=False)
slow_model._build_f(X_train_fit, y_train_fit)
# fit with just the necessary data
fast_model.fit(X_train, y_train, sample_weight=weights)
X_test = 20.0 * rng.rand(n_samples) - 10
y_pred_slow = slow_model.predict(X_test)
y_pred_fast = fast_model.predict(X_test)
assert_array_equal(y_pred_slow, y_pred_fast)
def test_isotonic_regression():
y = np.array([3, 7, 5, 9, 8, 7, 10])
y_ = np.array([3, 6, 6, 8, 8, 8, 10])
assert_array_equal(y_, isotonic_regression(y))
y = np.array([10, 0, 2])
y_ = np.array([4, 4, 4])
assert_array_equal(y_, isotonic_regression(y))
x = np.arange(len(y))
ir = IsotonicRegression(y_min=0., y_max=1.)
ir.fit(x, y)
assert_array_equal(ir.fit(x, y).transform(x), ir.fit_transform(x, y))
assert_array_equal(ir.transform(x), ir.predict(x))
# check that it is immune to permutation
perm = np.random.permutation(len(y))
ir = IsotonicRegression(y_min=0., y_max=1.)
assert_array_equal(ir.fit_transform(x[perm], y[perm]),
ir.fit_transform(x, y)[perm])
assert_array_equal(ir.transform(x[perm]), ir.transform(x)[perm])
# check we don't crash when all x are equal:
ir = IsotonicRegression()
assert_array_equal(ir.fit_transform(np.ones(len(x)), y), np.mean(y))
def test_isotonic_regression_ties_secondary_():
"""
Test isotonic regression fit, transform and fit_transform
against the "secondary" ties method and "pituitary" data from R
"isotone" package, as detailed in: J. d. Leeuw, K. Hornik, P. Mair,
Isotone Optimization in R: Pool-Adjacent-Violators Algorithm
(PAVA) and Active Set Methods
Set values based on pituitary example and
the following R command detailed in the paper above:
> library("isotone")
> data("pituitary")
> res1 <- gpava(pituitary$age, pituitary$size, ties="secondary")
> res1$x
`isotone` version: 1.0-2, 2014-09-07
R version: R version 3.1.1 (2014-07-10)
"""
x = [8, 8, 8, 10, 10, 10, 12, 12, 12, 14, 14]
y = [21, 23.5, 23, 24, 21, 25, 21.5, 22, 19, 23.5, 25]
y_true = [
22.22222, 22.22222, 22.22222, 22.22222, 22.22222, 22.22222, 22.22222,
22.22222, 22.22222, 24.25, 24.25
]
# Check fit, transform and fit_transform
ir = IsotonicRegression()
ir.fit(x, y)
assert_array_almost_equal(ir.transform(x), y_true, 4)
assert_array_almost_equal(ir.fit_transform(x, y), y_true, 4)
def test_isotonic_mismatched_dtype(y_dtype):
# regression test for #15004
# check that data are converted when X and y dtype differ
reg = IsotonicRegression()
y = np.array([2, 1, 4, 3, 5], dtype=y_dtype)
X = np.arange(len(y), dtype=np.float32)
reg.fit(X, y)
assert reg.predict(X).dtype == X.dtype
def test_isotonic_duplicate_min_entry():
x = [0, 0, 1]
y = [0, 0, 1]
ir = IsotonicRegression(increasing=True, out_of_bounds="clip")
ir.fit(x, y)
all_predictions_finite = np.all(np.isfinite(ir.predict(x)))
assert all_predictions_finite
def test_isotonic_regression_pickle():
y = np.array([3, 7, 5, 9, 8, 7, 10])
x = np.arange(len(y))
# Create model and fit
ir = IsotonicRegression(increasing='auto', out_of_bounds="clip")
ir.fit(x, y)
ir_ser = pickle.dumps(ir, pickle.HIGHEST_PROTOCOL)
ir2 = pickle.loads(ir_ser)
np.testing.assert_array_equal(ir.predict(x), ir2.predict(x))
def test_isotonic_regression_oob_raise():
# Set y and x
y = np.array([3, 7, 5, 9, 8, 7, 10])
x = np.arange(len(y))
# Create model and fit
ir = IsotonicRegression(increasing='auto', out_of_bounds="raise")
ir.fit(x, y)
# Check that an exception is thrown
assert_raises(ValueError, ir.predict, [min(x) - 10, max(x) + 10])
def test_isotonic_regression_ties_max():
# Setup examples with ties on maximum
x = [1, 2, 3, 4, 5, 5]
y = [1, 2, 3, 4, 5, 6]
y_true = [1, 2, 3, 4, 5.5, 5.5]
# Check that we get identical results for fit/transform and fit_transform
ir = IsotonicRegression()
ir.fit(x, y)
assert_array_equal(ir.fit(x, y).transform(x), ir.fit_transform(x, y))
assert_array_equal(y_true, ir.fit_transform(x, y))
def test_isotonic_regression_oob_bad_after():
# Set y and x
y = np.array([3, 7, 5, 9, 8, 7, 10])
x = np.arange(len(y))
# Create model and fit
ir = IsotonicRegression(increasing='auto', out_of_bounds="raise")
# Make sure that we throw an error for bad out_of_bounds value in transform
ir.fit(x, y)
ir.out_of_bounds = "xyz"
assert_raises(ValueError, ir.transform, x)
def test_isotonic_regression_oob_nan():
# Set y and x
y = np.array([3, 7, 5, 9, 8, 7, 10])
x = np.arange(len(y))
# Create model and fit
ir = IsotonicRegression(increasing='auto', out_of_bounds="nan")
ir.fit(x, y)
# Predict from training and test x and check that we have two NaNs.
y1 = ir.predict([min(x) - 10, max(x) + 10])
assert sum(np.isnan(y1)) == 2
def test_isotonic_regression_oob_clip():
# Set y and x
y = np.array([3, 7, 5, 9, 8, 7, 10])
x = np.arange(len(y))
# Create model and fit
ir = IsotonicRegression(increasing='auto', out_of_bounds="clip")
ir.fit(x, y)
# Predict from training and test x and check that min/max match.
y1 = ir.predict([min(x) - 10, max(x) + 10])
y2 = ir.predict(x)
assert max(y1) == max(y2)
assert min(y1) == min(y2)
def test_isotonic_dtype():
y = [2, 1, 4, 3, 5]
weights = np.array([.9, .9, .9, .9, .9], dtype=np.float64)
reg = IsotonicRegression()
for dtype in (np.int32, np.int64, np.float32, np.float64):
for sample_weight in (None, weights.astype(np.float32), weights):
y_np = np.array(y, dtype=dtype)
expected_dtype = \
check_array(y_np, dtype=[np.float64, np.float32],
ensure_2d=False).dtype
res = isotonic_regression(y_np, sample_weight=sample_weight)
assert res.dtype == expected_dtype
X = np.arange(len(y)).astype(dtype)
reg.fit(X, y_np, sample_weight=sample_weight)
res = reg.predict(X)
assert res.dtype == expected_dtype
def test_isotonic_zero_weight_loop():
# Test from @ogrisel's issue:
# https://github.com/scikit-learn/scikit-learn/issues/4297
# Get deterministic RNG with seed
rng = np.random.RandomState(42)
# Create regression and samples
regression = IsotonicRegression()
n_samples = 50
x = np.linspace(-3, 3, n_samples)
y = x + rng.uniform(size=n_samples)
# Get some random weights and zero out
w = rng.uniform(size=n_samples)
w[5:8] = 0
regression.fit(x, y, sample_weight=w)
# This will hang in failure case.
regression.fit(x, y, sample_weight=w)
def test_permutation_invariance():
# check that fit is permutation invariant.
# regression test of missing sorting of sample-weights
ir = IsotonicRegression()
x = [1, 2, 3, 4, 5, 6, 7]
y = [1, 41, 51, 1, 2, 5, 24]
sample_weight = [1, 2, 3, 4, 5, 6, 7]
x_s, y_s, sample_weight_s = shuffle(x, y, sample_weight, random_state=0)
y_transformed = ir.fit_transform(x, y, sample_weight=sample_weight)
y_transformed_s = \
ir.fit(x_s, y_s, sample_weight=sample_weight_s).transform(x)
assert_array_equal(y_transformed, y_transformed_s)
def test_isotonic_regression_with_ties_in_differently_sized_groups():
"""
Non-regression test to handle issue 9432:
https://github.com/scikit-learn/scikit-learn/issues/9432
Compare against output in R:
> library("isotone")
> x <- c(0, 1, 1, 2, 3, 4)
> y <- c(0, 0, 1, 0, 0, 1)
> res1 <- gpava(x, y, ties="secondary")
> res1$x
`isotone` version: 1.1-0, 2015-07-24
R version: R version 3.3.2 (2016-10-31)
"""
x = np.array([0, 1, 1, 2, 3, 4])
y = np.array([0, 0, 1, 0, 0, 1])
y_true = np.array([0., 0.25, 0.25, 0.25, 0.25, 1.])
ir = IsotonicRegression()
ir.fit(x, y)
assert_array_almost_equal(ir.transform(x), y_true)
assert_array_almost_equal(ir.fit_transform(x, y), y_true)