def test_plot_stacked_bar(self):
exp = ca.Experiment(np.array([[0, 1], [2, 3]]),
pd.DataFrame({'A': ['ab', 'cd'], 'B': ['ef', 'gh']},
index=['s1', 's2']),
pd.DataFrame({'genus': ['bacillus', 'listeria']}))
# bar width used in plot_staked_bar
width = 0.95
fig = exp.plot_stacked_bar(sample_color_bars='A', field='genus', xtick=None)
self.assertEqual(len(fig.axes), 3)
# test bar ax
ax = fig.axes[0]
# test x axis tick labels
obs_xticklabels = [i.get_text() for i in ax.xaxis.get_ticklabels()]
self.assertListEqual(obs_xticklabels, ['s1', 's2'])
# get all the bars
bars = ax.get_children()[:4]
xs = [0 - width / 2, 1 - width / 2]
ys = [0, 0, 0, 2]
heights = [0, 2, 1, 3]
for i, bar in enumerate(bars):
bbox = bar.get_bbox()
# coordinate of lower left corner of the bar: x, y
# width and height of the bar: w, h
x, y, w, h = bbox.bounds
# i % 2 because there are only columns
self.assertAlmostEqual(x, xs[i % 2])
self.assertAlmostEqual(w, width)
self.assertAlmostEqual(y, ys[i])
self.assertAlmostEqual(h, heights[i])
def test_plot_hist(self):
exp = ca.Experiment(np.array([[0, 1], [2, 3]]),
pd.DataFrame({'A': ['ab', 'cd'], 'B': ['ef', 'gh']}))
counts, bins, ax = exp.plot_hist(bins=4)
assert_array_almost_equal(counts, np.array([1] * 4))
assert_array_almost_equal(bins, np.array([0., 0.75, 1.5, 2.25, 3.]))
# test the numbers on top of the histogram bars are correct
self.assertEqual([i.get_text() for i in ax.texts], ['1'] * 4)
def test_join_experiments_featurewise(self):
otu1 = ca.Experiment(np.array([[0, 9], [7, 4]]),
sparse=False,
sample_metadata=pd.DataFrame(
{
'category': ['B', 'A'],
'ph': [7.7, 6.6]
},
index=['s2', 's1']),
feature_metadata=pd.DataFrame(
{'motile': ['y', 'n']},
index=['16S1', '16S2']))
otu2 = ca.Experiment(np.array([[6], [8], [10]]),
sparse=False,
sample_metadata=pd.DataFrame(
{
'category': ['A', 'B', 'C'],
'ph': [6.6, 7.7, 8.8]
},
index=['s1', 's2', 's3']),
feature_metadata=pd.DataFrame({'motile': [None]},
index=['ITS1']))
combined_obs = otu1.join_experiments_featurewise(
otu2, 'origin', ('16S', 'ITS'))
combined_exp = ca.Experiment(np.array([[7, 4, 6], [0, 9, 8]]),
sparse=False,
sample_metadata=pd.DataFrame(
{
'category': ['A', 'B'],
'ph': [6.6, 7.7]
},
index=['s1', 's2']),
feature_metadata=pd.DataFrame(
{
'motile': ['y', 'n', None],
'origin': ['16S', '16S', 'ITS']
},
index=['16S1', '16S2', 'ITS1']))
# reorder the samples
combined_obs = combined_obs.filter_ids(
combined_exp.sample_metadata.index, axis=0)
assert_experiment_equal(combined_obs, combined_exp)
def test_regress(self):
diabetes = datasets.load_diabetes()
X = diabetes.data[:9]
y = diabetes.target[:9]
smd = pd.DataFrame({'diabetes': y})
exp = ca.Experiment(X, smd, sparse=False)
run = exp.regress('diabetes', KNeighborsRegressor(), KFold(3, random_state=0))
res = next(run)
obs = pd.read_table(join(self.test_data_dir, 'diabetes_pred.txt'), index_col=0)
# make sure the column order are the same for comparison
pdt.assert_frame_equal(res.sort_index(axis=1), obs.sort_index(axis=1))
def test_validate_sample(self):
with self.assertRaises(
ValueError,
msg=
'data table must have the same number of samples with sample_metadata table (2 != 1)'
):
ca.Experiment(np.array([[1, 2], [3, 4]]),
sample_metadata=pd.DataFrame({
'foo': ['a'],
'spam': ['A']
}))
def test_classify(self):
iris = datasets.load_iris()
n = len(iris.target)
np.random.seed(0)
i = np.random.randint(0, n, 36)
X = iris.data[i]
y = iris.target[i]
d = dict(enumerate(iris.target_names))
smd = pd.DataFrame({'plant': y}).replace(d)
exp = ca.Experiment(X, smd, sparse=False)
run = exp.classify('plant', KNeighborsClassifier(),
predict='predict_proba',
cv=KFold(3, random_state=0))
res = next(run)
obs = pd.read_table(join(self.test_data_dir, 'iris_pred.txt'), index_col=0)
pdt.assert_frame_equal(res, obs)
def test_subsample_count(self):
exp = ca.Experiment(data=np.array([[1, 2, 3], [4, 5, 6]]),
sample_metadata=pd.DataFrame([['a', 'b', 'c'], ['d', 'e', 'f']]),
sparse=False)
n = 6
obs = exp.subsample_count(n, random_seed=9)
assert_array_equal(obs.data.sum(axis=1), np.array([n, n]))
self.assertTrue(np.all(obs.data <= n))
n = 7
obs = exp.subsample_count(n)
# the 1st row dropped
assert_array_equal(obs.data.sum(axis=1), np.array([n]))
self.assertIsNot(obs, exp)
obs = exp.subsample_count(n, inplace=True)
assert_array_equal(obs.data.sum(axis=1), np.array([n]))
self.assertTrue(np.all(obs.data <= n))
self.assertIs(obs, exp)
n = 10000
obs = exp.subsample_count(n)
assert_array_equal(obs.data.sum(axis=1), np.array([]))