def test_add_rows_svd(self):
test_cases = [(self.space2, np.vstack([self.us2[0], self.us2[0]]),
self.m1, ["e"], ["f"], {"e":0, "f":1})]
red1 = Svd(2)
red2 = Svd(1)
for in_s, expected_mat, data, id2row1, id2row2, row2id in test_cases:
in_s = in_s.apply(red1)
in_s = in_s.apply(red2)
per_s = PeripheralSpace(in_s, DenseMatrix(data), id2row1)
per_s.add_rows(DenseMatrix(data), id2row2)
np.testing.assert_array_almost_equal(expected_mat,
per_s.cooccurrence_matrix.mat,
2)
self.assertListEqual(per_s.id2row, id2row1 + id2row2)
self.assertListEqual(per_s.id2column, [])
self.assertDictEqual(per_s.row2id, row2id)
self.assertDictEqual(per_s.column2id, {})
self.assertEqual(2, len(per_s.operations))
def test_add_rows(self):
test_cases = [(self.space1, self.m2, self.row2, np.array([[4, 2,
6]]), ["c"],
np.array([[4, 2, 6], [4, 2, 6]]),
np.array([[0.69314718, 0, 0], [0.69314718, 0, 0]]), {
"b": 0,
"c": 1
}, ["b", "c"])]
for (core_sp, per_mat1, id2row1, per_mat2, id2row2, per_exp_mat1,
per_exp_mat2, per_exp_row2id, per_exp_id2row) in test_cases:
per_sp = PeripheralSpace(core_sp, DenseMatrix(per_mat1), id2row1)
per_sp.add_rows(DenseMatrix(per_mat2), id2row2)
np.testing.assert_array_almost_equal(
per_sp.cooccurrence_matrix.mat, per_exp_mat1, 7)
self.assertDictEqual(per_sp.row2id, per_exp_row2id)
self.assertListEqual(per_sp.id2row, per_exp_id2row)
self.assertDictEqual(per_sp.column2id, core_sp.column2id)
self.assertListEqual(per_sp.id2column, core_sp.id2column)
core_sp2 = core_sp.apply(PpmiWeighting())
per_sp2 = PeripheralSpace(core_sp2, DenseMatrix(per_mat1), id2row1)
per_sp2.add_rows(DenseMatrix(per_mat2), id2row2)
np.testing.assert_array_almost_equal(
per_sp2.cooccurrence_matrix.mat, per_exp_mat2, 7)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), id2row1)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), id2row2)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), ["d", "e"])
def test_add_rows_svd(self):
test_cases = [(self.space2, np.vstack([self.us2[0], self.us2[0]]),
self.m1, ["e"], ["f"], {
"e": 0,
"f": 1
})]
red1 = Svd(2)
red2 = Svd(1)
for in_s, expected_mat, data, id2row1, id2row2, row2id in test_cases:
in_s = in_s.apply(red1)
in_s = in_s.apply(red2)
per_s = PeripheralSpace(in_s, DenseMatrix(data), id2row1)
per_s.add_rows(DenseMatrix(data), id2row2)
np.testing.assert_array_almost_equal(expected_mat,
per_s.cooccurrence_matrix.mat,
2)
self.assertListEqual(per_s.id2row, id2row1 + id2row2)
self.assertListEqual(per_s.id2column, [])
self.assertDictEqual(per_s.row2id, row2id)
self.assertDictEqual(per_s.column2id, {})
self.assertEqual(2, len(per_s.operations))
def test_add_rows(self):
test_cases = [(self.space1, self.m2, self.row2,
np.array([[4,2,6]]), ["c"],
np.array([[4,2,6],[4,2,6]]),
np.array([[0.69314718,0,0],[0.69314718,0,0]]),
{"b":0,"c":1},
["b", "c"])]
for (core_sp, per_mat1, id2row1, per_mat2, id2row2, per_exp_mat1,
per_exp_mat2, per_exp_row2id, per_exp_id2row) in test_cases:
per_sp = PeripheralSpace(core_sp, DenseMatrix(per_mat1), id2row1)
per_sp.add_rows(DenseMatrix(per_mat2), id2row2)
np.testing.assert_array_almost_equal(per_sp.cooccurrence_matrix.mat,
per_exp_mat1, 7)
self.assertDictEqual(per_sp.row2id, per_exp_row2id)
self.assertListEqual(per_sp.id2row, per_exp_id2row)
self.assertDictEqual(per_sp.column2id, core_sp.column2id)
self.assertListEqual(per_sp.id2column, core_sp.id2column)
core_sp2 = core_sp.apply(PpmiWeighting())
per_sp2 = PeripheralSpace(core_sp2, DenseMatrix(per_mat1), id2row1)
per_sp2.add_rows(DenseMatrix(per_mat2), id2row2)
np.testing.assert_array_almost_equal(per_sp2.cooccurrence_matrix.mat,
per_exp_mat2, 7)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), id2row1)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), id2row2)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), ["d", "e"])
def test_per_space_top_feat_selection(self):
test_cases = [(self.space_d, 1, ["f3"], {"f3":0},
np.mat([[3],[5]])),
(self.space_d, 2, ["f3", "f1"], {"f3":0, "f1":1},
np.mat([[3,1],[5,4]])),
(self.space_d, 4, ["f3", "f1", "f2"],
{"f3":0, "f1":1, "f2":2},
np.mat([[3,1,2],[5,4,0]]))
]
for space_d, no_dim, id2col, col2id, mat in test_cases:
trans = TopFeatureSelection(no_dim)
new_space = space_d.apply(trans)
#peripheral test simple test
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a), ["c","d"])
self.assertListEqual(per_sp.id2row, ["c","d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_equal(per_sp.cooccurrence_matrix.mat,
mat)
#peripheral test with add rows
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a[0,:]), ["c"])
per_sp.add_rows(DenseMatrix(self.a[1,:]), ["d"])
self.assertListEqual(per_sp.id2row, ["c","d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_equal(per_sp.cooccurrence_matrix.mat,
mat)
#peripheral test, with plog applied to core BEFORE feat selection
plogmat = mat.copy()
plogmat[plogmat==0] = 1
plogmat = np.log(plogmat)
new_space = space_d.apply(PlogWeighting())
trans = TopFeatureSelection(no_dim)
new_space = new_space.apply(trans)
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a), ["c","d"])
self.assertListEqual(per_sp.id2row, ["c","d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_almost_equal(per_sp.cooccurrence_matrix.mat,
plogmat, 7)
#peripheral test, with plog applied to core AFTER feat selection
trans = TopFeatureSelection(no_dim)
new_space = space_d.apply(trans)
new_space = new_space.apply(PlogWeighting())
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a), ["c","d"])
self.assertListEqual(per_sp.id2row, ["c","d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_almost_equal(per_sp.cooccurrence_matrix.mat,
plogmat, 7)
def test_per_space_top_feat_selection(self):
test_cases = [(self.space_d, 1, ["f3"], {
"f3": 0
}, np.mat([[3], [5]])),
(self.space_d, 2, ["f3", "f1"], {
"f3": 0,
"f1": 1
}, np.mat([[3, 1], [5, 4]])),
(self.space_d, 4, ["f3", "f1", "f2"], {
"f3": 0,
"f1": 1,
"f2": 2
}, np.mat([[3, 1, 2], [5, 4, 0]]))]
for space_d, no_dim, id2col, col2id, mat in test_cases:
trans = TopFeatureSelection(no_dim)
new_space = space_d.apply(trans)
#peripheral test simple test
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a),
["c", "d"])
self.assertListEqual(per_sp.id2row, ["c", "d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_equal(per_sp.cooccurrence_matrix.mat, mat)
#peripheral test with add rows
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a[0, :]),
["c"])
per_sp.add_rows(DenseMatrix(self.a[1, :]), ["d"])
self.assertListEqual(per_sp.id2row, ["c", "d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_equal(per_sp.cooccurrence_matrix.mat, mat)
#peripheral test, with plog applied to core BEFORE feat selection
plogmat = mat.copy()
plogmat[plogmat == 0] = 1
plogmat = np.log(plogmat)
new_space = space_d.apply(PlogWeighting())
trans = TopFeatureSelection(no_dim)
new_space = new_space.apply(trans)
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a),
["c", "d"])
self.assertListEqual(per_sp.id2row, ["c", "d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_almost_equal(
per_sp.cooccurrence_matrix.mat, plogmat, 7)
#peripheral test, with plog applied to core AFTER feat selection
trans = TopFeatureSelection(no_dim)
new_space = space_d.apply(trans)
new_space = new_space.apply(PlogWeighting())
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a),
["c", "d"])
self.assertListEqual(per_sp.id2row, ["c", "d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_almost_equal(
per_sp.cooccurrence_matrix.mat, plogmat, 7)
