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 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_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)