def setUp(self):
super().setUp()
def _load_biom(table_fp):
table_fp = self.get_data_path(table_fp)
table = qiime2.Artifact.load(table_fp)
table = table.view(biom.Table)
return table
def _load_cmc(md_fp, column):
md_fp = self.get_data_path(md_fp)
md = pd.read_csv(md_fp, sep='\t', header=0, index_col=0)
md = qiime2.CategoricalMetadataColumn(md[column])
return md
table_chard_fp = _load_biom('chardonnay.table.qza')
mdc_chard_fp = _load_cmc('chardonnay.map.txt', 'Region')
pipeline, importances = fit_classifier(table_chard_fp,
mdc_chard_fp,
random_state=123,
n_estimators=2,
n_jobs=1,
optimize_feature_selection=True,
parameter_tuning=True,
missing_samples='ignore')
transformer = self.get_transformer(Pipeline, SampleEstimatorDirFmt)
self._sklp = transformer(pipeline)
sklearn_pipeline = self._sklp.sklearn_pipeline.view(PickleFormat)
self.sklearn_pipeline = str(sklearn_pipeline)
self.pipeline = pipeline
def test_predict_classifications(self):
for classifier in [
'RandomForestClassifier', 'ExtraTreesClassifier',
'GradientBoostingClassifier', 'AdaBoostClassifier',
'LinearSVC', 'SVC', 'KNeighborsClassifier'
]:
estimator, importances = fit_classifier(self.table_chard_fp,
self.mdc_chard_fp,
random_state=123,
n_estimators=2,
estimator=classifier,
n_jobs=1,
missing_samples='ignore')
pred, prob = predict_classification(self.table_chard_fp, estimator)
exp = self.mdc_chard_fp.to_series().reindex(pred.index).dropna()
# reindex both pred and exp because not all samples present in pred
# are present in the metadata! (hence missing_samples='ignore')
sample_ids = pred.index.intersection(exp.index)
pred = pred.loc[sample_ids]
exp = exp.loc[sample_ids]
# test that expected number of correct results is achieved (these
# are mostly quite high as we would expect (total n=21))
correct_results = np.sum(pred == exp)
self.assertEqual(
correct_results,
seeded_predict_results[classifier],
msg='Accuracy of %s classifier was %f, but expected %f' %
(classifier, correct_results,
seeded_predict_results[classifier]))
def test_fit_classifier(self):
pipeline, importances = fit_classifier(self.table_ecam_fp,
self.mdc_ecam_fp,
random_state=123,
n_estimators=2,
n_jobs=1,
optimize_feature_selection=True,
parameter_tuning=True,
missing_samples='ignore')
def test_predict_classifications(self):
for classifier in [
'RandomForestClassifier', 'ExtraTreesClassifier',
'GradientBoostingClassifier', 'AdaBoostClassifier',
'LinearSVC', 'SVC', 'KNeighborsClassifier'
]:
estimator, importances = fit_classifier(self.table_chard_fp,
self.mdc_chard_fp,
random_state=123,
n_estimators=2,
estimator=classifier,
n_jobs=1,
missing_samples='ignore')
pred, prob = predict_classification(self.table_chard_fp, estimator)
exp = self.mdc_chard_fp.to_series().reindex(pred.index).dropna()
# reindex both pred and exp because not all samples present in pred
# are present in the metadata! (hence missing_samples='ignore')
sample_ids = pred.index.intersection(exp.index)
pred = pred.loc[sample_ids]
exp = exp.loc[sample_ids]
# verify predictions:
# test that expected number of correct results is achieved (these
# are mostly quite high as we would expect (total n=21))
correct_results = np.sum(pred == exp)
self.assertEqual(
correct_results,
seeded_predict_results[classifier],
msg='Accuracy of %s classifier was %f, but expected %f' %
(classifier, correct_results,
seeded_predict_results[classifier]))
# verify probabilities
# test whether all are in correct range (0 to 1)
ls_pred_classes = prob.columns.tolist()
ls_correct_range = [
col for col in ls_pred_classes
if prob[col].between(0, 1, inclusive=True).all()
]
self.assertEqual(len(ls_correct_range),
prob.shape[1],
msg='Predicted probabilities of class {}'
'are not in range [0,1]'.format([
col for col in ls_pred_classes
if col not in ls_correct_range
]))
