def test_multi_class_summary_even_targets(self):
# df = DF_TEST_MULTI_CASS
target = np.arange(1, 5)
price = np.arange(0, 5) + 0.5
labels = [
one_hot(np.random.randint(0, len(target)),
len(target) + 1).tolist() for _ in range(len(price))
]
predictions = range(len(price))
expected_losses = [0.0, -0.5, -0.5, 0]
for prediction, expected_loss in zip(predictions, expected_losses):
df = pd.DataFrame([target for _ in range(len(price))])
df.columns = pd.MultiIndex.from_product([[TARGET_COLUMN_NAME],
df.columns])
df[(GROSS_LOSS_COLUMN_NAME, "loss")] = price
df[(PREDICTION_COLUMN_NAME, "prediction")] = [
one_hot(prediction,
len(target) + 1).tolist() for _ in range(len(price))
]
df[(LABEL_COLUMN_NAME, "label")] = labels
print(df)
s = WeightedClassificationSummary(df,
None,
classes=len(target) + 1)
print(s.df_gross_loss)
def test__parabolic_crossentropy(self):
"""when"""
categories = 11
loss_function = ParabolicPenaltyLoss(categories, 1)
"""then"""
for truth in range(categories):
losses = []
for prediction in range(categories):
loss = loss_function(t.tensor(one_hot(prediction, categories)),
t.tensor(one_hot(truth, categories)))
losses.append(loss)
# all predictions left of truth need to increase
for i in range(1, truth):
self.assertGreater(losses[i - 1], losses[i])
# right of truth need to decrease
for i in range(truth, categories - 1):
self.assertLess(losses[i], losses[i + 1])
if truth > 0 and truth < categories - 1:
if truth > categories / 2:
# right tail:
self.assertGreater(losses[truth - 1], losses[truth + 1])
else:
# left tail
self.assertGreater(losses[truth + 1], losses[truth - 1])
def test__tailed_categorical_crossentropy(self):
"""when"""
categories = 11
loss = tailed_categorical_crossentropy(categories, 1)
"""then"""
truth = K.constant(one_hot(3, 11))
prediction = K.softmax(K.constant(one_hot(6, 11)))
l = K.eval(loss(truth, prediction))
pickle
"""then"""
np.testing.assert_almost_equal(l, 11.817837, decimal=5)
save_object(loss, '/tmp/test__tailed_categorical_crossentropy.dill')
def test__tailed_categorical_crossentropy(self):
"""when"""
categories = 11
loss = TailedCategoricalCrossentropyLoss(categories, 1)
"""then"""
truth = one_hot(3, 11)
l = loss(t.tensor([one_hot(6, 11)]), t.tensor([truth]))
l2 = loss(t.tensor([one_hot(6, 11), one_hot(9, 11)]),
t.tensor([truth, truth]))
"""then"""
np.testing.assert_almost_equal(l, 11.817837, decimal=5)
np.testing.assert_array_almost_equal(l2, [11.817837, 42.46247],
decimal=5)
self.assertGreater(l.mean().numpy(), 0)
def test_one_hot(self):
"""given integer numbers"""
x = np.arange(5)
"""when one hot encoded"""
ohx = one_hot(x, None)
"""then x is one hot encoded"""
np.testing.assert_array_equal(ohx, np.eye(5))
def test_multi_class_summary_odd_targets(self):
# df = DF_TEST_MULTI_CASS
target = np.arange(1, 4)
price = np.arange(0, 4) + 0.5
labels = [one_hot(np.arange(0, 4), len(target) + 1).tolist() for _ in range(len(price))]
predictions = range(len(price))
expected_losses = [0.0, -0.5, -0.5, 0]
for prediction, expected_loss in zip(predictions, expected_losses):
df = pd.DataFrame([target for _ in range(len(price))])
df.columns = pd.MultiIndex.from_product([[TARGET_COLUMN_NAME], df.columns])
df[(GROSS_LOSS_COLUMN_NAME, "loss")] = price
df[(PREDICTION_COLUMN_NAME, "prediction")] = [one_hot(prediction, len(target) + 1).tolist() for _ in range(len(price))]
df[(LABEL_COLUMN_NAME, "label")] = labels
s = WeightedClassificationSummary(df, classes= len(target) + 1)
self.assertEqual(s.df_gross_loss["loss"].clip(upper=0).sum(), expected_loss)
print(s._gross_confusion())
def test__differentiable_argmax(self):
"""given"""
args = 10
argmax = DifferentiableArgmax(args)
"""when"""
res = np.array(
[argmax(t.tensor(one_hot(i, args))).numpy() for i in range(args)])
"""then"""
print(res)
np.testing.assert_array_almost_equal(res, np.arange(0, args))
def test_normal_penalized_crossentropy(self):
"""when"""
loss = normal_penalized_crossentropy(11)
"""then"""
for i in range(11):
self.assertLess(
K.eval(
loss(K.variable(one_hot(i, 11)),
K.variable(one_hot(i, 11)))), 0.00001)
self.assertLess(
K.eval(loss(K.variable(one_hot(7, 11)), K.variable(one_hot(8,
11)))),
K.eval(loss(K.variable(one_hot(7, 11)), K.variable(one_hot(6,
11)))))
self.assertLess(
K.eval(loss(K.variable(one_hot(6, 11)), K.variable(one_hot(7,
11)))),
K.eval(loss(K.variable(one_hot(6, 11)), K.variable(one_hot(5,
11)))))
self.assertLess(
K.eval(loss(K.variable(one_hot(3, 11)), K.variable(one_hot(2,
11)))),
K.eval(loss(K.variable(one_hot(3, 11)), K.variable(one_hot(4,
11)))))
