def test_min_max_scaler_iris(setup): X = iris scaler = MinMaxScaler() # default params X_trans = scaler.fit_transform(X) assert_array_almost_equal(X_trans.min(axis=0), 0) assert_array_almost_equal(X_trans.max(axis=0), 1) X_trans_inv = scaler.inverse_transform(X_trans) assert_array_almost_equal(X, X_trans_inv) # not default params: min=1, max=2 scaler = MinMaxScaler(feature_range=(1, 2)) X_trans = scaler.fit_transform(X) assert_array_almost_equal(X_trans.min(axis=0), 1) assert_array_almost_equal(X_trans.max(axis=0), 2) X_trans_inv = scaler.inverse_transform(X_trans) assert_array_almost_equal(X, X_trans_inv) # min=-.5, max=.6 scaler = MinMaxScaler(feature_range=(-.5, .6)) X_trans = scaler.fit_transform(X) assert_array_almost_equal(X_trans.min(axis=0), -.5) assert_array_almost_equal(X_trans.max(axis=0), .6) X_trans_inv = scaler.inverse_transform(X_trans) assert_array_almost_equal(X, X_trans_inv) # raises on invalid range scaler = MinMaxScaler(feature_range=(2, 1)) with pytest.raises(ValueError): scaler.fit(X)
def test_min_max_scaler_zero_variance_features(setup): # Check min max scaler on toy data with zero variance features X = [[0., 1., +0.5], [0., 1., -0.1], [0., 1., +1.1]] X_new = [[+0., 2., 0.5], [-1., 1., 0.0], [+0., 1., 1.5]] # default params scaler = MinMaxScaler() X_trans = scaler.fit_transform(X) X_expected_0_1 = [[0., 0., 0.5], [0., 0., 0.0], [0., 0., 1.0]] assert_array_almost_equal(X_trans, X_expected_0_1) X_trans_inv = scaler.inverse_transform(X_trans) assert_array_almost_equal(X, X_trans_inv) X_trans_new = scaler.transform(X_new) X_expected_0_1_new = [[+0., 1., 0.500], [-1., 0., 0.083], [+0., 0., 1.333]] assert_array_almost_equal(X_trans_new, X_expected_0_1_new, decimal=2) # not default params scaler = MinMaxScaler(feature_range=(1, 2)) X_trans = scaler.fit_transform(X) X_expected_1_2 = [[1., 1., 1.5], [1., 1., 1.0], [1., 1., 2.0]] assert_array_almost_equal(X_trans, X_expected_1_2) # function interface X_trans = minmax_scale(X) assert_array_almost_equal(X_trans, X_expected_0_1) X_trans = minmax_scale(X, feature_range=(1, 2)) assert_array_almost_equal(X_trans, X_expected_1_2)
def test_min_max_scaler1d(setup): X_list_1row = X_1row.to_numpy().tolist() X_list_1col = X_1col.to_numpy().tolist() # Test scaling of dataset along single axis for X in [X_1row, X_1col, X_list_1row, X_list_1col]: scaler = MinMaxScaler(copy=True) X_scaled = scaler.fit(X).transform(X) if isinstance(X, list): X = mt.array(X) # cast only after scaling done if _check_dim_1axis(X) == 1: assert_array_almost_equal(X_scaled.min(axis=0), mt.zeros(n_features)) assert_array_almost_equal(X_scaled.max(axis=0), mt.zeros(n_features)) else: assert_array_almost_equal(X_scaled.min(axis=0), .0) assert_array_almost_equal(X_scaled.max(axis=0), 1.) assert scaler.n_samples_seen_ == X.shape[0] # check inverse transform X_scaled_back = scaler.inverse_transform(X_scaled) assert_array_almost_equal(X_scaled_back, X) # Constant feature X = mt.ones((5, 1)) scaler = MinMaxScaler() X_scaled = scaler.fit(X).transform(X) assert X_scaled.min().to_numpy() >= 0. assert X_scaled.max().to_numpy() <= 1. assert scaler.n_samples_seen_ == X.shape[0] # Function interface X_1d = X_1row.ravel() min_ = X_1d.min() max_ = X_1d.max() assert_array_almost_equal((X_1d - min_) / (max_ - min_), minmax_scale(X_1d, copy=True))