def test_score_with_nans_ignore(self):
obs = deepcopy(self.observations)
obs[0]['feautre_a'] = np.nan
to_be_scored = {
'feature_a': np.nan,
'feature_b': 'b_val_1',
'feature_c': 'c_val_1'
}
actually_scored = {'feature_b': 'b_val_1', 'feature_c': 'c_val_1'}
# score observation with nan value
self.cbrw = CBRW(ignore_unknown=True)
self.cbrw.add_observations(self.observations)
self.cbrw.fit()
score = self.cbrw.score(to_be_scored)
actual_score = self.cbrw.score(actually_scored)
self.assertFalse(isnan(score[0]))
self.assertEqual(score, actual_score)
# fit includes observation with nan value
self.cbrw = CBRW(ignore_unknown=True)
self.cbrw.add_observations(obs)
self.cbrw.fit()
score = self.cbrw.score(to_be_scored)
actual_score = self.cbrw.score(actually_scored)
self.assertFalse(isnan(score[0]))
self.assertEqual(score, actual_score)
def test_value_scores_unknown_features_ignore(self):
self.cbrw = CBRW(ignore_unknown=True)
self.cbrw.add_observations(self.observations)
self.cbrw.fit()
# score observation where all features but not all
# values have been previously observed
to_be_scored = {
'feature_a': 'a_val_x',
'feature_b': 'b_val_1',
'feature_c': 'c_val_1'
}
actually_scored = {'feature_b': 'b_val_1', 'feature_c': 'c_val_1'}
value_scores = self.cbrw.value_scores(to_be_scored)[0]
actual_value_scores = self.cbrw.value_scores(actually_scored)[0]
self.assertTrue(all(not isnan(vs) for vs in value_scores.values()))
self.assertEqual(value_scores['feature_a'], 0)
self.assertEqual(value_scores['feature_b'],
actual_value_scores['feature_b'])
self.assertEqual(value_scores['feature_c'],
actual_value_scores['feature_c'])
# score observation where a feature has not
# been previously observed
to_be_scored = {
'feature_x': 'x_val_x',
'feature_b': 'b_val_1',
'feature_c': 'c_val_1'
}
actually_scored = {'feature_b': 'b_val_1', 'feature_c': 'c_val_1'}
value_scores = self.cbrw.value_scores(to_be_scored)[0]
actual_value_scores = self.cbrw.value_scores(actually_scored)[0]
self.assertTrue(all(not isnan(vs) for vs in value_scores.values()))
self.assertEqual(value_scores['feature_x'], 0)
self.assertEqual(value_scores['feature_b'],
actual_value_scores['feature_b'])
self.assertEqual(value_scores['feature_c'],
actual_value_scores['feature_c'])
# score observation where no features have
# previously been observed
to_be_scored = {
'feature_x': 'x_val_x',
'feature_y': 'y_val_1',
'feature_z': 'z_val_1'
}
value_scores = self.cbrw.value_scores(to_be_scored)[0]
self.assertTrue(all(not isnan(vs) for vs in value_scores.values()))
self.assertTrue(all(vs == 0 for vs in value_scores.values()))
def test_value_scores_with_nans_ignore(self):
obs = deepcopy(self.observations)
obs[0]['feautre_a'] = np.nan
to_be_scored = {
'feature_a': np.nan,
'feature_b': 'b_val_1',
'feature_c': 'c_val_1'
}
actually_scored = {'feature_b': 'b_val_1', 'feature_c': 'c_val_1'}
# score observation with nan value
self.cbrw = CBRW(ignore_unknown=True)
self.cbrw.add_observations(self.observations)
self.cbrw.fit()
value_scores = self.cbrw.value_scores(to_be_scored)[0]
actual_value_scores = self.cbrw.value_scores(actually_scored)[0]
self.assertTrue(all(not isnan(vs) for vs in value_scores.values()))
self.assertEqual(value_scores['feature_a'], 0)
self.assertEqual(value_scores['feature_b'],
actual_value_scores['feature_b'])
self.assertEqual(value_scores['feature_c'],
actual_value_scores['feature_c'])
# fit includes observation with nan value
self.cbrw = CBRW(ignore_unknown=True)
self.cbrw.add_observations(obs)
self.cbrw.fit()
value_scores = self.cbrw.value_scores(to_be_scored)[0]
actual_value_scores = self.cbrw.value_scores(actually_scored)[0]
self.assertTrue(all(not isnan(vs) for vs in value_scores.values()))
self.assertEqual(value_scores['feature_a'], 0)
self.assertEqual(value_scores['feature_b'],
actual_value_scores['feature_b'])
self.assertEqual(value_scores['feature_c'],
actual_value_scores['feature_c'])
def test_score_unknown_features_ignore(self):
self.cbrw = CBRW(ignore_unknown=True)
self.cbrw.add_observations(self.observations)
self.cbrw.fit()
# score observation where all features but not all
# values have been previously observed
to_be_scored = {
'feature_a': 'a_val_x',
'feature_b': 'b_val_1',
'feature_c': 'c_val_1'
}
actually_scored = {
'feature_b': 'b_val_1',
'feature_c': 'c_val_1'
}
score = self.cbrw.score(to_be_scored)
actual_score = self.cbrw.score(actually_scored)
self.assertFalse(isnan(score[0]))
self.assertEqual(score, actual_score)
# score observation where a feature has not
# been previously observed
to_be_scored = {
'feature_x': 'x_val_x',
'feature_b': 'b_val_1',
'feature_c': 'c_val_1'
}
actually_scored = {
'feature_b': 'b_val_1',
'feature_c': 'c_val_1'
}
score = self.cbrw.score(to_be_scored)
actual_score = self.cbrw.score(actually_scored)
self.assertFalse(isnan(score[0]))
self.assertEqual(score, actual_score)
# score observation where all features not
# previously observed
to_be_scored = {
'feature_x': 'x_val_x',
'feature_y': 'y_val_1',
'feature_z': 'z_val_1'
}
score = self.cbrw.score(to_be_scored)
self.assertFalse(isnan(score[0]))
self.assertEqual(score[0], 0)
def test_value_scores_with_nans_default(self):
obs = deepcopy(self.observations)
obs[0]['feautre_a'] = np.nan
to_be_scored = {
'feature_a': np.nan,
'feature_b': 'b_val_1',
'feature_c': 'c_val_1'
}
# score observation with nan value
self.cbrw.fit()
value_scores = self.cbrw.value_scores(to_be_scored)
self.assertTrue(isnan(value_scores[0]['feature_a']))
# fit includes observation with nan value
self.cbrw = CBRW()
self.cbrw.add_observations(obs)
self.cbrw.fit()
value_scores = self.cbrw.value_scores(to_be_scored)
self.assertTrue(isnan(value_scores[0]['feature_a']))
def test_fit_no_data(self):
self.cbrw = CBRW()
with self.assertRaises(CBRWFitError):
self.cbrw.fit()
def setUp(self):
self.cbrw = CBRW()
self.cbrw.add_observations(self.observations)