fix compatibility with scikit-learn by dropping dependency from sklearn.testing (#158)

Author: StrikerRUS

lightning/impl/datasets/tests/test_samples_generator.py

@@ -1,17 +1,15 @@
 import numpy as np
 
-from sklearn.utils.testing import assert_equal
-
 from lightning.impl.datasets.samples_generator import make_nn_regression
 
 
 def test_make_nn_regression():
     X, y, w = make_nn_regression(n_samples=10, n_features=50, n_informative=5)
-    assert_equal(X.shape[0], 10)
-    assert_equal(X.shape[1], 50)
-    assert_equal(y.shape[0], 10)
-    assert_equal(w.shape[0], 50)
-    assert_equal(np.sum(X.data != 0), 10 * 5)
+    assert X.shape[0] == 10
+    assert X.shape[1] == 50
+    assert y.shape[0] == 10
+    assert w.shape[0] == 50
+    assert np.sum(X.data != 0) == 10 * 5
 
     X, y, w = make_nn_regression(n_samples=10, n_features=50, n_informative=50)
-    assert_equal(np.sum(X.data != 0), 10 * 50)
+    assert np.sum(X.data != 0) == 10 * 50

lightning/impl/randomkit/tests/test_random.py

@@ -1,22 +1,21 @@
 import pickle
 import numpy as np
-from numpy.testing import (assert_almost_equal, assert_array_equal,
-                           assert_equal)
+
 from lightning.impl.randomkit import RandomState
 from six.moves import xrange
 
 
 def test_randint():
     rs = RandomState(seed=0)
     vals = [rs.randint(10) for t in xrange(10000)]
-    assert_almost_equal(np.mean(vals), 5.018)
+    np.testing.assert_almost_equal(np.mean(vals), 5.018)
 
 
 def test_shuffle():
     ind = np.arange(10)
     rs = RandomState(seed=0)
     rs.shuffle(ind)
-    assert_array_equal(ind, [2, 8, 4, 9, 1, 6, 7, 3, 0, 5])
+    np.testing.assert_array_equal(ind, [2, 8, 4, 9, 1, 6, 7, 3, 0, 5])
 
 
 def test_random_state_pickle():
@@ -25,4 +24,4 @@ def test_random_state_pickle():
     pickle_rs = pickle.dumps(rs)
     pickle_rs = pickle.loads(pickle_rs)
     pickle_random_integer = pickle_rs.randint(5)
-    assert_equal(random_integer, pickle_random_integer)
+    assert random_integer == pickle_random_integer

lightning/impl/tests/test_adagrad.py

@@ -1,8 +1,6 @@
 import numpy as np
 
 from sklearn.datasets import load_iris
-from sklearn.utils.testing import assert_equal
-from sklearn.utils.testing import assert_almost_equal
 
 from lightning.classification import AdaGradClassifier
 from lightning.regression import AdaGradRegressor
@@ -20,44 +18,44 @@ def test_adagrad_elastic_hinge():
     clf = AdaGradClassifier(alpha=0.5, l1_ratio=0.85, n_iter=10, random_state=0)
     clf.fit(X_bin, y_bin)
     assert not hasattr(clf, "predict_proba")
-    assert_equal(clf.score(X_bin, y_bin), 1.0)
+    assert clf.score(X_bin, y_bin) == 1.0
 
 
 def test_adagrad_elastic_smooth_hinge():
     clf = AdaGradClassifier(alpha=0.5, l1_ratio=0.85, loss="smooth_hinge",
                             n_iter=10, random_state=0)
     clf.fit(X_bin, y_bin)
     assert not hasattr(clf, "predict_proba")
-    assert_equal(clf.score(X_bin, y_bin), 1.0)
+    assert clf.score(X_bin, y_bin) == 1.0
 
 
 def test_adagrad_elastic_log():
     clf = AdaGradClassifier(alpha=0.1, l1_ratio=0.85, loss="log", n_iter=10,
                             random_state=0)
     clf.fit(X_bin, y_bin)
-    assert_equal(clf.score(X_bin, y_bin), 1.0)
+    assert clf.score(X_bin, y_bin) == 1.0
     check_predict_proba(clf, X_bin)
 
 
 def test_adagrad_hinge_multiclass():
     clf = AdaGradClassifier(alpha=1e-2, n_iter=100, loss="hinge", random_state=0)
     clf.fit(X, y)
     assert not hasattr(clf, "predict_proba")
-    assert_almost_equal(clf.score(X, y), 0.940, 3)
+    np.testing.assert_almost_equal(clf.score(X, y), 0.940, 3)
 
 
 def test_adagrad_classes_binary():
     clf = AdaGradClassifier()
     assert not hasattr(clf, 'classes_')
     clf.fit(X_bin, y_bin)
-    assert_equal(list(clf.classes_), [-1, 1])
+    assert list(clf.classes_) == [-1, 1]
 
 
 def test_adagrad_classes_multiclass():
     clf = AdaGradClassifier()
     assert not hasattr(clf, 'classes_')
     clf.fit(X, y)
-    assert_equal(list(clf.classes_), [0, 1, 2])
+    assert list(clf.classes_) == [0, 1, 2]
 
 
 def test_adagrad_callback():
@@ -80,12 +78,12 @@ def __call__(self, clf, t):
     clf = AdaGradClassifier(alpha=0.5, l1_ratio=0.85, n_iter=10,
                             callback=cb, random_state=0)
     clf.fit(X_bin, y_bin)
-    assert_equal(cb.acc[-1], 1.0)
+    assert cb.acc[-1] == 1.0
 
 
 def test_adagrad_regression():
     for loss in ("squared", "absolute"):
         reg = AdaGradRegressor(loss=loss)
         reg.fit(X_bin, y_bin)
         y_pred = np.sign(reg.predict(X_bin))
-        assert_equal(np.mean(y_bin == y_pred), 1.0)
+        assert np.mean(y_bin == y_pred) == 1.0

lightning/impl/tests/test_dataset.py

@@ -2,9 +2,6 @@
 import numpy as np
 import scipy.sparse as sp
 
-from sklearn.utils.testing import assert_array_equal
-from sklearn.utils.testing import assert_array_almost_equal
-from sklearn.utils.testing import assert_equal
 from six.moves import xrange
 
 from sklearn.datasets import make_classification
@@ -38,34 +35,34 @@ def test_contiguous_get_row():
     ind = np.arange(X.shape[1])
     for i in xrange(X.shape[0]):
         indices, data, n_nz = cds.get_row(i)
-        assert_array_equal(indices, ind)
-        assert_array_equal(data, X[i])
-        assert_equal(n_nz, X.shape[1])
+        np.testing.assert_array_equal(indices, ind)
+        np.testing.assert_array_equal(data, X[i])
+        assert n_nz == X.shape[1]
 
 
 def test_csr_get_row():
     for i in xrange(X.shape[0]):
         indices, data, n_nz = csr_ds.get_row(i)
         for jj in xrange(n_nz):
             j = indices[jj]
-            assert_equal(X[i, j], data[jj])
+            assert X[i, j] == data[jj]
 
 
 def test_fortran_get_column():
     ind = np.arange(X.shape[0])
     for j in xrange(X.shape[1]):
         indices, data, n_nz = fds.get_column(j)
-        assert_array_equal(indices, ind)
-        assert_array_equal(data, X[:, j])
-        assert_equal(n_nz, X.shape[0])
+        np.testing.assert_array_equal(indices, ind)
+        np.testing.assert_array_equal(data, X[:, j])
+        assert n_nz == X.shape[0]
 
 
 def test_csc_get_column():
     for j in xrange(X.shape[1]):
         indices, data, n_nz = csc_ds.get_column(j)
         for ii in xrange(n_nz):
             i = indices[ii]
-            assert_equal(X[i, j], data[ii])
+            assert X[i, j] == data[ii]
 
 
 def test_picklable_datasets():
@@ -74,5 +71,5 @@ def test_picklable_datasets():
     for dataset in [cds, csr_ds, fds, csc_ds]:
         pds = pickle.dumps(dataset)
         dataset = pickle.loads(pds)
-        assert_equal(dataset.get_n_samples(), X.shape[0])
-        assert_equal(dataset.get_n_features(), X.shape[1])
+        assert dataset.get_n_samples() == X.shape[0]
+        assert dataset.get_n_features() == X.shape[1]

lightning/impl/tests/test_dual_cd.py

@@ -5,10 +5,6 @@
 from sklearn.datasets import make_regression
 from six.moves import xrange
 
-from sklearn.utils.testing import assert_equal
-from sklearn.utils.testing import assert_greater
-from sklearn.utils.testing import assert_array_almost_equal
-
 from lightning.impl.datasets.samples_generator import make_classification
 from lightning.impl.dual_cd import LinearSVC
 from lightning.impl.dual_cd import LinearSVR
@@ -40,16 +36,16 @@ def test_sparse_dot():
                 K2[i, j] = sparse_dot(ds, i, j)
                 K2[j, i] = K[i, j]
 
-    assert_array_almost_equal(K, K2)
+    np.testing.assert_array_almost_equal(K, K2)
 
 
 def test_fit_linear_binary():
     for data in (bin_dense, bin_csr):
         for loss in ("l1", "l2"):
             clf = LinearSVC(loss=loss, random_state=0, max_iter=10)
             clf.fit(data, bin_target)
-            assert_equal(list(clf.classes_), [0, 1])
-            assert_equal(clf.score(data, bin_target), 1.0)
+            assert list(clf.classes_) == [0, 1]
+            assert clf.score(data, bin_target) == 1.0
             y_pred = clf.decision_function(data).ravel()
 
 
@@ -59,17 +55,17 @@ def test_fit_linear_binary_auc():
             clf = LinearSVC(loss=loss, criterion="auc", random_state=0,
                             max_iter=25)
             clf.fit(data, bin_target)
-            assert_equal(clf.score(data, bin_target), 1.0)
+            assert clf.score(data, bin_target) == 1.0
 
 
 def test_fit_linear_multi():
     for data in (mult_dense, mult_sparse):
         clf = LinearSVC(random_state=0)
         clf.fit(data, mult_target)
-        assert_equal(list(clf.classes_), [0, 1, 2])
+        assert list(clf.classes_) == [0, 1, 2]
         y_pred = clf.predict(data)
         acc = np.mean(y_pred == mult_target)
-        assert_greater(acc, 0.85)
+        assert acc > 0.85
 
 
 def test_warm_start():
@@ -79,32 +75,32 @@ def test_warm_start():
 
         clf.fit(bin_dense, bin_target)
         acc = clf.score(bin_dense, bin_target)
-        assert_greater(acc, 0.99)
+        assert acc > 0.99
 
 
 def test_linear_svr():
     reg = LinearSVR(random_state=0)
     reg.fit(reg_dense, reg_target)
-    assert_greater(reg.score(reg_dense, reg_target), 0.99)
+    assert reg.score(reg_dense, reg_target) > 0.99
 
 
 def test_linear_svr_fit_intercept():
     reg = LinearSVR(random_state=0, fit_intercept=True)
     reg.fit(reg_dense, reg_target)
-    assert_greater(reg.score(reg_dense, reg_target), 0.99)
+    assert reg.score(reg_dense, reg_target) > 0.99
 
 
 def test_linear_svr_l2():
     reg = LinearSVR(loss="l2", random_state=0)
     reg.fit(reg_dense, reg_target)
-    assert_greater(reg.score(reg_dense, reg_target), 0.99)
+    assert reg.score(reg_dense, reg_target) > 0.99
 
 
 def test_linear_svr_warm_start():
     reg = LinearSVR(C=1e-3, random_state=0, warm_start=True)
     reg.fit(reg_dense, reg_target)
-    assert_greater(reg.score(reg_dense, reg_target), 0.96)
+    assert reg.score(reg_dense, reg_target) > 0.96
 
     reg.C = 1
     reg.fit(reg_dense, reg_target)
-    assert_greater(reg.score(reg_dense, reg_target), 0.99)
+    assert reg.score(reg_dense, reg_target) > 0.99