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_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_sample_weight_parameter_default_value():
# check if default value of sample_weight parameter is one
ir = IsotonicRegression()
# random test data
rng = np.random.RandomState(42)
n = 100
x = np.arange(n)
y = rng.randint(-50, 50, size=(n, )) + 50. * np.log(1 + np.arange(n))
# check if value is correctly used
weights = np.ones(n)
y_set_value = ir.fit_transform(x, y, sample_weight=weights)
y_default_value = ir.fit_transform(x, y)
assert_array_equal(y_set_value, y_default_value)
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_sample_weight():
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]
expected_y = [1, 13.95, 13.95, 13.95, 13.95, 13.95, 24]
received_y = ir.fit_transform(x, y, sample_weight=sample_weight)
assert_array_equal(expected_y, received_y)
def test_isotonic_min_max_boundaries():
# check if min value is used correctly
ir = IsotonicRegression(y_min=2, y_max=4)
n = 6
x = np.arange(n)
y = np.arange(n)
y_test = [2, 2, 2, 3, 4, 4]
y_result = np.round(ir.fit_transform(x, y))
assert_array_equal(y_result, y_test)
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_auto_increasing():
# Set y and x for decreasing
y = np.array([5, 6.1, 6, 7, 10, 9, 10])
x = np.arange(len(y))
# Create model and fit_transform
ir = IsotonicRegression(increasing='auto')
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter("always")
y_ = ir.fit_transform(x, y)
# work-around for pearson divide warnings in scipy <= 0.17.0
assert all([
"invalid value encountered in " in str(warn.message) for warn in w
])
# Check that relationship increases
is_increasing = y_[0] < y_[-1]
assert is_increasing
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)
from mrex.linear_model import LinearRegression from mrex.isotonic import IsotonicRegression from mrex.utils import check_random_state n = 100 x = np.arange(n) rs = check_random_state(0) y = rs.randint(-50, 50, size=(n,)) + 50. * np.log1p(np.arange(n)) # ############################################################################# # Fit IsotonicRegression and LinearRegression models ir = IsotonicRegression() y_ = ir.fit_transform(x, y) lr = LinearRegression() lr.fit(x[:, np.newaxis], y) # x needs to be 2d for LinearRegression # ############################################################################# # Plot result segments = [[[i, y[i]], [i, y_[i]]] for i in range(n)] lc = LineCollection(segments, zorder=0) lc.set_array(np.ones(len(y))) lc.set_linewidths(np.full(n, 0.5)) fig = plt.figure() plt.plot(x, y, 'r.', markersize=12) plt.plot(x, y_, 'b.-', markersize=12)