def test_classify_samples_ncv_accuracy(self):
dat = biom.Table(np.array(
[[4446, 9828, 3208, 776, 118, 4175, 657, 251, 7505, 617],
[1855, 8716, 3257, 1251, 3205, 2557, 4251, 7405, 1417, 1215],
[6616, 281, 8616, 291, 261, 253, 9075, 252, 7385, 4068]]),
observation_ids=['o1', 'o2', 'o3'],
sample_ids=['s1', 's2', 's3', 's4', 's5',
's6', 's7', 's8', 's9', 's10'])
md = qiime2.CategoricalMetadataColumn(pd.Series(
['red', 'red', 'red', 'red', 'red',
'blue', 'blue', 'blue', 'blue', 'blue'],
index=pd.Index(['s1', 's2', 's3', 's4', 's5',
's6', 's7', 's8', 's9', 's10'],
name='sample-id'), name='color'))
y_pred, importances, probabilities = classify_samples_ncv(
dat, md, random_state=123, n_estimators=2, n_jobs=1,
missing_samples='ignore')
exp_pred = pd.Series(
['blue', 'red', 'red', 'blue', 'blue',
'blue', 'blue', 'red', 'blue', 'blue'],
index=pd.Index(['s4', 's6', 's1', 's10', 's5', 's8', 's2', 's9',
's3', 's7'], dtype='object', name='SampleID'),
name='prediction')
exp_importances = pd.DataFrame(
[0.595111111111111, 0.23155555555555551, 0.17333333333333334],
index=pd.Index(['o3', 'o1', 'o2']), columns=['importance'])
exp_probabilities = pd.DataFrame(
[[0.5, 0.5], [0., 1.], [0., 1.], [0.5, 0.5], [0.5, 0.5],
[0.5, 0.5], [0.5, 0.5], [0., 1.], [1., 0.], [1., 0.]],
index=pd.Index(['s4', 's6', 's1', 's10', 's5', 's8', 's2', 's9',
's3', 's7'], name='SampleID'),
columns=['blue', 'red'])
pdt.assert_series_equal(y_pred, exp_pred)
pdt.assert_frame_equal(importances, exp_importances)
pdt.assert_frame_equal(probabilities, exp_probabilities)
def test_classify_samples_ncv(self):
y_pred, importances, probabilities = classify_samples_ncv(
self.table_chard_fp,
self.mdc_chard_fp,
random_state=123,
n_estimators=2,
n_jobs=1,
missing_samples='ignore')