def test_get_coefs(self, data):
model = VW()
model.fit(data.x, data.y)
weights = model.get_coefs()
print weights.data
assert np.allclose(weights.indices,
[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 116060])
def test_nn(self):
vw = VW(convert_to_vw=False, nn=3)
pos = '1.0 | a b c'
neg = '-1.0 | d e f'
vw.fit([pos] * 10 + [neg] * 10)
assert vw.predict(['| a b c']) > 0
assert vw.predict(['| d e f']) < 0
def test_predict(self, data):
raw_model = VW(oaa=2, loss_function='logistic')
raw_model.fit(data.x, data.y)
model = VWMultiClassifier(oaa=2, loss_function='logistic')
model.fit(data.x, data.y)
assert np.allclose(raw_model.predict(data.x), model.predict(data.x))
def test_oaa(self):
X = ['1 | feature1:2.5',
'2 | feature1:0.11 feature2:-0.0741',
'3 | feature3:2.33 feature4:0.8 feature5:-3.1',
'1 | feature2:-0.028 feature1:4.43',
'2 | feature5:1.532 feature6:-3.2']
model = VW(convert_to_vw=False, oaa=3)
model.fit(X)
assert np.allclose(model.predict(X), [ 1., 2., 3., 1., 2.])
def test_oaa(self):
X = ['1 | feature1:2.5',
'2 | feature1:0.11 feature2:-0.0741',
'3 | feature3:2.33 feature4:0.8 feature5:-3.1',
'1 | feature2:-0.028 feature1:4.43',
'2 | feature5:1.532 feature6:-3.2']
model = VW(convert_to_vw=False, oaa=3)
model.fit(X)
assert np.allclose(model.predict(X), [ 1., 2., 3., 1., 2.])
def test_oaa_probs(self):
X = ['1 | feature1:2.5',
'2 | feature1:0.11 feature2:-0.0741',
'3 | feature3:2.33 feature4:0.8 feature5:-3.1',
'1 | feature2:-0.028 feature1:4.43',
'2 | feature5:1.532 feature6:-3.2']
model = VW(convert_to_vw=False, oaa=3, loss_function='logistic')
model.fit(X)
prediction = model.predict(X)
assert np.allclose(prediction, [1., 2., 3., 1., 2.])
def test_bfgs(self):
data_file = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'resources', 'train.dat')
model = VW(convert_to_vw=False, oaa=3, passes=30, bfgs=True, data=data_file, cache=True, quiet=False)
X = ['1 | feature1:2.5',
'2 | feature1:0.11 feature2:-0.0741',
'3 | feature3:2.33 feature4:0.8 feature5:-3.1',
'1 | feature2:-0.028 feature1:4.43',
'2 | feature5:1.532 feature6:-3.2']
actual = model.predict(X)
assert np.allclose(actual, [1., 2., 3., 1., 2.])
def test_oaa_probs(self):
X = ['1 | feature1:2.5',
'2 | feature1:0.11 feature2:-0.0741',
'3 | feature3:2.33 feature4:0.8 feature5:-3.1',
'1 | feature2:-0.028 feature1:4.43',
'2 | feature5:1.532 feature6:-3.2']
model = VW(convert_to_vw=False, oaa=3, loss_function='logistic')
model.fit(X)
prediction = model.predict(X)
assert np.allclose(prediction, [1., 2., 3., 1., 2.])
def test_set_params(self):
model = VW()
assert 'l' not in model.params
model.set_params(l=0.1)
assert model.params['l'] == 0.1
# confirm model params reset with new construction
model = VW()
assert 'l' not in model.params
def test_bfgs(self):
data_file = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'resources', 'train.dat')
model = VW(convert_to_vw=False, oaa=3, passes=30, bfgs=True, data=data_file, cache=True, quiet=False)
X = ['1 | feature1:2.5',
'2 | feature1:0.11 feature2:-0.0741',
'3 | feature3:2.33 feature4:0.8 feature5:-3.1',
'1 | feature2:-0.028 feature1:4.43',
'2 | feature5:1.532 feature6:-3.2']
actual = model.predict(X)
assert np.allclose(actual, [1., 2., 3., 1., 2.])
def test_predict(self, data):
raw_model = VW()
raw_model.fit(data.x, data.y)
model = VWRegressor()
model.fit(data.x, data.y)
assert np.allclose(raw_model.predict(data.x), model.predict(data.x))
# ensure model can make multiple calls to predict
assert np.allclose(raw_model.predict(data.x), model.predict(data.x))
def test_oaa_probs(self):
X = ['1 | feature1:2.5',
'2 | feature1:0.11 feature2:-0.0741',
'3 | feature3:2.33 feature4:0.8 feature5:-3.1',
'1 | feature2:-0.028 feature1:4.43',
'2 | feature5:1.532 feature6:-3.2']
model = VW(convert_to_vw=False, oaa=3, loss_function='logistic', probabilities=True)
model.fit(X)
prediction = model.predict(X)
assert prediction.shape == [5, 3]
assert prediction[0, 0] > 0.1
def test_oaa_probs(self):
X = ['1 | feature1:2.5',
'2 | feature1:0.11 feature2:-0.0741',
'3 | feature3:2.33 feature4:0.8 feature5:-3.1',
'1 | feature2:-0.028 feature1:4.43',
'2 | feature5:1.532 feature6:-3.2']
model = VW(convert_to_vw=False, oaa=3, loss_function='logistic', probabilities=True)
model.fit(X)
prediction = model.predict(X)
assert prediction.shape == [5, 3]
assert prediction[0, 0] > 0.1
def test_lrq(self):
X = ['1 |user A |movie 1',
'2 |user B |movie 2',
'3 |user C |movie 3',
'4 |user D |movie 4',
'5 |user D |movie 1']
model = VW(convert_to_vw=False, lrq='um4', lrqdropout=True, loss_function='quantile')
assert model.params['lrq'] == 'um4'
assert model.params['lrqdropout']
model.fit(X)
prediction = model.predict([' |user C |movie 1'])
assert np.allclose(prediction, [3.], atol=1)
def test_decision_function(self, data):
classes = np.array([-1., 1.])
raw_model = VW(loss_function='logistic')
raw_model.fit(data.x, data.y)
predictions = raw_model.predict(data.x)
class_indices = (predictions > 0).astype(np.int)
class_predictions = classes[class_indices]
model = VWClassifier()
model.fit(data.x, data.y)
assert np.allclose(class_predictions, model.predict(data.x))
def test_passes(self, data):
n_passes = 2
model = VW(loss_function='logistic', passes=n_passes)
assert model.passes_ == n_passes
model.fit(data.x, data.y)
weights = model.get_coefs()
model = VW(loss_function='logistic')
# first pass weights should not be the same
model.fit(data.x, data.y)
assert not np.allclose(weights.data, model.get_coefs().data)
def test_decision_function(self, data):
classes = np.array([-1., 1.])
raw_model = VW(loss_function='logistic')
raw_model.fit(data.x, data.y)
predictions = raw_model.predict(data.x)
class_indices = (predictions > 0).astype(np.int)
class_predictions = classes[class_indices]
model = VWClassifier()
model.fit(data.x, data.y)
assert np.allclose(class_predictions, model.predict(data.x))
def test_lrq(self):
X = ['1 |user A |movie 1',
'2 |user B |movie 2',
'3 |user C |movie 3',
'4 |user D |movie 4',
'5 |user E |movie 1']
model = VW(convert_to_vw=False, lrq='um4', lrqdropout=True, loss_function='quantile')
assert getattr(model, 'lrq') == 'um4'
assert getattr(model, 'lrqdropout')
model.fit(X)
prediction = model.predict([' |user C |movie 1'])
assert np.allclose(prediction, [3.], atol=1)
def test_passes(self, data):
n_passes = 2
model = VW(loss_function='logistic', passes=n_passes)
assert model.passes_ == n_passes
model.fit(data.x, data.y)
weights = model.get_coefs()
model = VW(loss_function='logistic')
# first pass weights should not be the same
model.fit(data.x, data.y)
assert not np.allclose(weights.data, model.get_coefs().data)
def test_repr():
model = VW()
expected = "VW('convert_labels:False', 'quiet:True', 'sgd:False')"
assert expected == model.__repr__()
model = VWClassifier()
expected = "VWClassifier('convert_labels:False', "\
"'loss_function:logistic', 'quiet:True', 'sgd:False')"
assert expected == model.__repr__()
model = VWRegressor()
expected = "VWRegressor('convert_labels:False', 'quiet:True', 'sgd:False')"
assert expected == model.__repr__()
model = VW(convert_to_vw=False,
oaa=3,
loss_function='logistic',
probabilities=True)
expected = "VW('convert_labels:False', 'loss_function:logistic', "\
"'oaa:3', 'probabilities:True', 'quiet:True', 'sgd:False')"
assert expected == model.__repr__()
def test_set_params(self):
model = VW()
assert 'l' not in model.params
model.set_params(l=0.1)
assert model.params['l'] == 0.1
# confirm model params reset with new construction
model = VW()
assert 'l' not in model.params
def test_predict(self, data):
raw_model = VW()
raw_model.fit(data.x, data.y)
model = VWRegressor()
model.fit(data.x, data.y)
assert np.allclose(raw_model.predict(data.x), model.predict(data.x))
# ensure model can make multiple calls to predict
assert np.allclose(raw_model.predict(data.x), model.predict(data.x))
def test_set_params(self):
model = VW()
assert getattr(model, 'l') is None
model.set_params(l=0.1)
assert getattr(model, 'l') == 0.1
assert getattr(model, 'vw_') is None
# confirm model params reset with new construction
model = VW()
assert getattr(model, 'l') is None
def test_predict_proba(self, data):
raw_model = VW(probabilities=True, oaa=2, loss_function='logistic')
raw_model.fit(data.x, data.y)
model = VWMultiClassifier(oaa=2, loss_function='logistic')
model.fit(data.x, data.y)
assert np.allclose(raw_model.predict(data.x),
model.predict_proba(data.x))
# ensure model can make multiple calls to predict
assert np.allclose(raw_model.predict(data.x),
model.predict_proba(data.x))
def test_fit(self, data):
model = VW(loss_function='logistic')
assert model.vw_ is None
model.fit(data.x, data.y)
assert model.vw_ is not None
def test_fit(self, data):
model = VW(loss_function='logistic')
assert not hasattr(model, 'fit_')
model.fit(data.x, data.y)
assert model.fit_
def test_init(self):
assert isinstance(VW(), VW)
def test_delete(self):
raw_model = VW()
del raw_model
def test_save_load(self, data):
file_name = "tmp_sklearn.model"
model_before = VW(l=100)
model_before.fit(data.x, data.y)
before_saving = model_before.predict(data.x)
model_before.save(file_name)
model_after = VW(l=100)
model_after.load(file_name)
after_loading = model_after.predict(data.x)
assert np.allclose(before_saving, after_loading)
def test_predict(self, data):
model = VW(loss_function='logistic')
model.fit(data.x, data.y)
assert np.isclose(model.predict(data.x[:1][:1])[0], 0.406929)
def test_save_load(self, data):
f = NamedTemporaryFile()
model_before = VW(l=100)
model_before.fit(data.x, data.y)
before_saving = model_before.predict(data.x)
model_before.save(f.name)
model_after = VW(l=100)
model_after.load(f.name)
after_loading = model_after.predict(data.x)
assert np.allclose(before_saving, after_loading)
f.close()
def test_predict_no_convert(self):
model = VW(loss_function='logistic', convert_to_vw=False)
model.fit(['-1 | bad', '1 | good'])
assert np.isclose(model.predict(['| good'])[0], 0.245515)
def test_del(self, data):
model = VW()
model.fit(data.x, data.y)
del model
def test_bfgs_no_data(self):
with pytest.raises(RuntimeError):
VW(convert_to_vw=False, oaa=3, passes=30, bfgs=True)
def test_get_coefs(self, data):
model = VW()
model.fit(data.x, data.y)
weights = model.get_coefs()
print weights.data
assert np.allclose(weights.indices, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 116060])
def test_get_intercept(self, data):
model = VW()
model.fit(data.x, data.y)
intercept = model.get_intercept()
assert isinstance(intercept, float)
def test_predict_no_convert(self):
model = VW(loss_function='logistic', convert_to_vw=False)
model.fit(['-1 | bad', '1 | good'])
assert np.isclose(model.predict(['| good'])[0], 0.245515)
def test_predict_not_fit(self, data):
model = VW(loss_function='logistic')
with pytest.raises(ValueError):
model.predict(data.x[0])
def test_fit(self, data):
model = VW(loss_function='logistic')
assert not hasattr(model, 'fit_')
model.fit(data.x, data.y)
assert model.fit_
def test_predict(self, data):
model = VW(loss_function='logistic')
model.fit(data.x, data.y)
assert np.isclose(model.predict(data.x[:1][:1])[0], 0.406929)
def test_predict_not_fit(self, data):
model = VW(loss_function='logistic')
with pytest.raises(NotFittedError):
model.predict(data.x[0])
def test_get_intercept(self, data):
model = VW()
model.fit(data.x, data.y)
intercept = model.get_intercept()
assert isinstance(intercept, float)
def test_predict(self, data):
model = VW(loss_function='logistic')
model.fit(data.x, data.y)
actual = model.predict(data.x[:1][:1])[0]
assert np.isclose(actual, 0.406929, atol=1e-4)
