def test_robust_scaler_zero_variance_features():
"""Check RobustScaler on toy data with zero variance features"""
X = [[0., 1., +0.5],
[0., 1., -0.1],
[0., 1., +1.1]]
scaler = RobustScaler()
X_trans = scaler.fit_transform(X)
# NOTE: for such a small sample size, what we expect in the third column
# depends HEAVILY on the method used to calculate quantiles. The values
# here were calculated to fit the quantiles produces by np.percentile
# using numpy 1.9 Calculating quantiles with
# scipy.stats.mstats.scoreatquantile or scipy.stats.mstats.mquantiles
# would yield very different results!
X_expected = [[0., 0., +0.0],
[0., 0., -1.0],
[0., 0., +1.0]]
assert_array_almost_equal(X_trans, X_expected)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv)
# make sure new data gets transformed correctly
X_new = [[+0., 2., 0.5],
[-1., 1., 0.0],
[+0., 1., 1.5]]
X_trans_new = scaler.transform(X_new)
X_expected_new = [[+0., 1., +0.],
[-1., 0., -0.83333],
[+0., 0., +1.66667]]
assert_array_almost_equal(X_trans_new, X_expected_new, decimal=3)
def fit(self, data, args):
self.model = RobustScaler()
with Timer() as t:
self.model.fit(data.X_train, data.y_train)
return t.interval
def test_robust_scaler_iris():
X = iris.data
scaler = RobustScaler()
X_trans = scaler.fit_transform(X)
assert_array_almost_equal(np.median(X_trans, axis=0), 0)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv)
q = np.percentile(X_trans, q=(25, 75), axis=0)
iqr = q[1] - q[0]
assert_array_almost_equal(iqr, 1)
def test_robust_scaler_iris():
X = iris.data
scaler = RobustScaler()
X_trans = scaler.fit_transform(X)
assert_array_almost_equal(np.median(X_trans, axis=0), 0)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv)
q = np.percentile(X_trans, q=(25, 75), axis=0)
iqr = q[1] - q[0]
assert_array_almost_equal(iqr, 1)
def test_robust_scaler_2d_arrays():
"""Test robust scaling of 2d array along first axis"""
rng = np.random.RandomState(0)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
scaler = RobustScaler()
X_scaled = scaler.fit(X).transform(X)
assert_array_almost_equal(np.median(X_scaled, axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0)[0], 0)
def test_robust_scaler_2d_arrays():
"""Test robust scaling of 2d array along first axis"""
rng = np.random.RandomState(0)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
scaler = RobustScaler()
X_scaled = scaler.fit(X).transform(X)
assert_array_almost_equal(np.median(X_scaled, axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0)[0], 0)
def __init__(self, with_centering=True, with_scaling=True, quantile_range=(25.0, 75.0), copy=True):
self._hyperparams = {
'with_centering': with_centering,
'with_scaling': with_scaling,
'quantile_range': quantile_range,
'copy': copy}
self._wrapped_model = Op(**self._hyperparams)
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
class RobustScalerImpl():
def __init__(self, with_centering=True, with_scaling=True, quantile_range=(25.0, 75.0), copy=True):
self._hyperparams = {
'with_centering': with_centering,
'with_scaling': with_scaling,
'quantile_range': quantile_range,
'copy': copy}
self._wrapped_model = Op(**self._hyperparams)
def fit(self, X, y=None):
if (y is not None):
self._wrapped_model.fit(X, y)
else:
self._wrapped_model.fit(X)
return self
def transform(self, X):
return self._wrapped_model.transform(X)
class CreateRobustScaler(CreateModel):
def fit(self, data, args):
self.model = RobustScaler()
with Timer() as t:
self.model.fit(data.X_train, data.y_train)
return t.interval
def test(self, data):
assert self.model is not None
return self.model.transform(data.X_test)
def predict(self, data):
with Timer() as t:
self.predictions = self.test(data)
data.learning_task = LearningTask.REGRESSION
return t.interval
def test_robust_scaler_zero_variance_features():
"""Check RobustScaler on toy data with zero variance features"""
X = [[0., 1., +0.5], [0., 1., -0.1], [0., 1., +1.1]]
scaler = RobustScaler()
X_trans = scaler.fit_transform(X)
# NOTE: for such a small sample size, what we expect in the third column
# depends HEAVILY on the method used to calculate quantiles. The values
# here were calculated to fit the quantiles produces by np.percentile
# using numpy 1.9 Calculating quantiles with
# scipy.stats.mstats.scoreatquantile or scipy.stats.mstats.mquantiles
# would yield very different results!
X_expected = [[0., 0., +0.0], [0., 0., -1.0], [0., 0., +1.0]]
assert_array_almost_equal(X_trans, X_expected)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv)
# make sure new data gets transformed correctly
X_new = [[+0., 2., 0.5], [-1., 1., 0.0], [+0., 1., 1.5]]
X_trans_new = scaler.transform(X_new)
X_expected_new = [[+0., 1., +0.], [-1., 0., -0.83333], [+0., 0., +1.66667]]
assert_array_almost_equal(X_trans_new, X_expected_new, decimal=3)
'ProjectedGradientNMF':ProjectedGradientNMF(), 'QuadraticDiscriminantAnalysis':QuadraticDiscriminantAnalysis(), 'RANSACRegressor':RANSACRegressor(), 'RBFSampler':RBFSampler(), 'RadiusNeighborsClassifier':RadiusNeighborsClassifier(), 'RadiusNeighborsRegressor':RadiusNeighborsRegressor(), 'RandomForestClassifier':RandomForestClassifier(), 'RandomForestRegressor':RandomForestRegressor(), 'RandomizedLasso':RandomizedLasso(), 'RandomizedLogisticRegression':RandomizedLogisticRegression(), 'RandomizedPCA':RandomizedPCA(), 'Ridge':Ridge(), 'RidgeCV':RidgeCV(), 'RidgeClassifier':RidgeClassifier(), 'RidgeClassifierCV':RidgeClassifierCV(), 'RobustScaler':RobustScaler(), 'SGDClassifier':SGDClassifier(), 'SGDRegressor':SGDRegressor(), 'SVC':SVC(), 'SVR':SVR(), 'SelectFdr':SelectFdr(), 'SelectFpr':SelectFpr(), 'SelectFwe':SelectFwe(), 'SelectKBest':SelectKBest(), 'SelectPercentile':SelectPercentile(), 'ShrunkCovariance':ShrunkCovariance(), 'SkewedChi2Sampler':SkewedChi2Sampler(), 'SparsePCA':SparsePCA(), 'SparseRandomProjection':SparseRandomProjection(), 'SpectralBiclustering':SpectralBiclustering(), 'SpectralClustering':SpectralClustering(),