def test_populate_class_weight(self):
# should populate the class weight of a pipeline
weights = Artifact.import_data(
'FeatureTable[RelativeFrequency]',
self.get_data_path('class_weight.biom'),
view_type='BIOMV100Format')
table = weights.view(biom.Table)
svc_spec = [['feat_ext',
{'__type__': 'feature_extraction.text.HashingVectorizer',
'analyzer': 'char_wb',
'n_features': 8192,
'ngram_range': [8, 8],
'alternate_sign': False}],
['classify',
{'__type__': 'naive_bayes.GaussianNB'}]]
pipeline1 = pipeline_from_spec(svc_spec)
populate_class_weight(pipeline1, table)
classes = table.ids('observation')
class_weights = []
for wts in table.iter_data():
class_weights.append(zip(classes, wts))
svc_spec[1][1]['priors'] = list(zip(*sorted(class_weights[0])))[1]
pipeline2 = pipeline_from_spec(svc_spec)
for a, b in zip(pipeline1.get_params()['classify__priors'],
pipeline2.get_params()['classify__priors']):
self.assertAlmostEqual(a, b)
def test_populate_class_weight(self):
# should populate the class weight of a pipeline
weights = Artifact.import_data(
'FeatureTable[RelativeFrequency]',
self.get_data_path('class_weight.biom'),
view_type='BIOMV100Format')
table = weights.view(biom.Table)
svc_spec = [['feat_ext',
{'__type__': 'feature_extraction.text.HashingVectorizer',
'analyzer': 'char_wb',
'n_features': 8192,
'ngram_range': [8, 8],
'alternate_sign': False}],
['classify',
{'__type__': 'naive_bayes.GaussianNB'}]]
pipeline1 = pipeline_from_spec(svc_spec)
populate_class_weight(pipeline1, table)
classes = table.ids('observation')
class_weights = []
for wts in table.iter_data():
class_weights.append(zip(classes, wts))
svc_spec[1][1]['priors'] = list(zip(*sorted(class_weights[0])))[1]
pipeline2 = pipeline_from_spec(svc_spec)
for a, b in zip(pipeline1.get_params()['classify__priors'],
pipeline2.get_params()['classify__priors']):
self.assertAlmostEqual(a, b)
def test_pipeline_serialisation(self):
# pipeline inflation and deflation should be inverse operations
for name, spec in _specific_fitters:
pipeline = pipeline_from_spec(spec)
spec_one = spec_from_pipeline(pipeline)
pipeline = pipeline_from_spec(spec_one)
spec_two = spec_from_pipeline(pipeline)
self.assertEqual(spec_one, spec_two)
def test_pipeline_serialisation(self):
# pipeline inflation and deflation should be inverse operations
for name, spec in _specific_fitters:
pipeline = pipeline_from_spec(spec)
spec_one = spec_from_pipeline(pipeline)
pipeline = pipeline_from_spec(spec_one)
spec_two = spec_from_pipeline(pipeline)
self.assertEqual(spec_one, spec_two)
def precalculate_nearest_neighbors(
reference_taxonomy: Series, reference_sequences: DNAIterator,
max_centroids_per_class: int=10,
feature_extractor_specification: str=_default_feature_extractor,
knn_classifier_specification: str=_default_knn_classifier,
n_jobs: int=1, random_state: int=42) -> dict:
spec = json.loads(feature_extractor_specification)
feat_ext = pipeline_from_spec(spec)
if not isinstance(feat_ext.steps[-1][-1], TransformerMixin):
raise ValueError('feature_extractor_specification must specify a '
'transformer')
spec = json.loads(knn_classifier_specification)
nn = pipeline_from_spec(spec)
if not isinstance(nn.steps[-1][-1], KNeighborsMixin):
raise ValueError('knn_classifier_specification must specifiy a '
'KNeighbors classifier')
seq_ids, X = _extract_reads(reference_sequences)
data = [(reference_taxonomy[s], x)
for s, x in zip(seq_ids, X) if s in reference_taxonomy]
y, X = list(zip(*data))
X = feat_ext.transform(X)
if max_centroids_per_class > 0:
class_counts = Counter(y)
undersample_classes = {t: max_centroids_per_class
for t, c in class_counts.items()
if c > max_centroids_per_class}
cc = ClusterCentroids(random_state=random_state, n_jobs=n_jobs,
ratio=undersample_classes, voting='hard')
X_resampled, y_resampled = cc.fit_sample(X, y)
else:
X_resampled, y_resampled = X, y
if 'n_jobs' in nn.steps[-1][-1].get_params():
nn.steps[-1][-1].set_params(n_jobs=n_jobs)
nn.fit(X_resampled)
nn = nn.steps[-1][-1]
if n_jobs != 1 and hasattr(X_resampled, 'todense'):
indices = nn.kneighbors(X_resampled.todense(), return_distance=False)
else:
indices = nn.kneighbors(X_resampled, return_distance=False)
return {'neighbors': indices.tolist(), 'taxonomies': y_resampled.tolist()}
