Skip to content

Pandas 1 fixes #268

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
nbokulich merged 4 commits into from
Feb 14, 2020
Merged

Pandas 1 fixes #268

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0d3333f
Use MultiIndex.codes instead of labels (no longer support)
andrewsanchez Feb 12, 2020
b0cc0df
Unpack and name values returned by _reindex_with_metadata
andrewsanchez Feb 12, 2020
552152f
Initial patch to handle new pandas error
andrewsanchez Feb 12, 2020
b9ddead
Avoid mutating `merged` in place by assigning to new variable
andrewsanchez Feb 13, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 9 additions & 6 deletions q2_diversity/_alpha/_visualizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,12 +237,15 @@ def alpha_correlation(output_dir: str,


def _reindex_with_metadata(column, columns, merged):
merged.set_index(column, inplace=True)
merged.sort_index(axis=0, ascending=True, inplace=True)
merged = merged.groupby(level=[column])
counts = merged.count()
counts.drop(columns, axis=1, inplace=True, level=0)
median_ = merged.median()
reindexed = merged.set_index(column)
Copy link
Contributor Author

@andrewsanchez andrewsanchez Feb 13, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Avoid mutating merged by assigning to a new DataFrame reindexed.

reindexed.sort_index(axis=0, ascending=True, inplace=True)
grouped = reindexed.groupby(level=[column])
counts = grouped.count()
# Removes the column name used to set the index of `merged` above
col_diff = set(columns) - set([column])
if col_diff:
counts.drop(col_diff, axis=1, inplace=True, level=0)
Copy link
Contributor Author

@andrewsanchez andrewsanchez Feb 13, 2020 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The first kwarg taken by DataFrame.drop is labels and it accepts a single label or list-like. Passing the set directly seems to work fine here, but we can make it a pd.Index or list if that is preferable.

Copy link
Member

@nbokulich nbokulich Feb 14, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nah, this looks good to me

median_ = grouped.median()
return median_, counts


Expand Down
38 changes: 19 additions & 19 deletions q2_diversity/tests/test_alpha_rarefaction.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -418,21 +418,21 @@ def test_unique_metadata_groups(self):
[9, 10, 11, 12, 'peanut']],
columns=columns, index=['S1', 'S2', 'S3'])

obs = _reindex_with_metadata('pet', ['pet'], data)
median, counts = _reindex_with_metadata('pet', ['pet'], data)

exp_col = pd.MultiIndex(levels=[[1, 200, 'pet'], [1, 2, '']],
labels=[[0, 0, 1, 1], [0, 1, 0, 1]],
codes=[[0, 0, 1, 1], [0, 1, 0, 1]],
names=['depth', 'iter'])
exp_ind = pd.Index(['milo', 'peanut', 'russ'], name='pet')
exp = pd.DataFrame(data=[[5, 6, 7, 8], [9, 10, 11, 12], [1, 2, 3, 4]],
columns=exp_col, index=exp_ind)

pdt.assert_frame_equal(exp, obs[0])
pdt.assert_frame_equal(exp, median)

exp = pd.DataFrame(data=[[1, 1, 1, 1], [1, 1, 1, 1], [1, 1, 1, 1]],
columns=exp_col, index=exp_ind)

pdt.assert_frame_equal(exp, obs[1])
pdt.assert_frame_equal(exp, counts)

def test_some_duplicates_in_column(self):
columns = pd.MultiIndex.from_tuples([(1, 1), (1, 2), (200, 1),
Expand All @@ -442,21 +442,21 @@ def test_some_duplicates_in_column(self):
[9, 10, 11, 12, 'russ']],
columns=columns, index=['S1', 'S2', 'S3'])

obs = _reindex_with_metadata('pet', ['pet'], data)
median, counts = _reindex_with_metadata('pet', ['pet'], data)

exp_col = pd.MultiIndex(levels=[[1, 200, 'pet'], [1, 2, '']],
labels=[[0, 0, 1, 1], [0, 1, 0, 1]],
codes=[[0, 0, 1, 1], [0, 1, 0, 1]],
names=['depth', 'iter'])
exp_ind = pd.Index(['milo', 'russ'], name='pet')
exp = pd.DataFrame(data=[[5, 6, 7, 8], [5, 6, 7, 8]],
columns=exp_col, index=exp_ind)

pdt.assert_frame_equal(exp, obs[0])
pdt.assert_frame_equal(exp, median)

exp = pd.DataFrame(data=[[1, 1, 1, 1], [2, 2, 2, 2]],
columns=exp_col, index=exp_ind)

pdt.assert_frame_equal(exp, obs[1])
pdt.assert_frame_equal(exp, counts)

def test_all_identical(self):
columns = pd.MultiIndex.from_tuples([(1, 1), (1, 2), (200, 1),
Expand All @@ -466,21 +466,21 @@ def test_all_identical(self):
[9, 10, 11, 12, 'russ']],
columns=columns, index=['S1', 'S2', 'S3'])

obs = _reindex_with_metadata('pet', ['pet'], data)
median, counts = _reindex_with_metadata('pet', ['pet'], data)

exp_col = pd.MultiIndex(levels=[[1, 200, 'pet'], [1, 2, '']],
labels=[[0, 0, 1, 1], [0, 1, 0, 1]],
codes=[[0, 0, 1, 1], [0, 1, 0, 1]],
names=['depth', 'iter'])
exp_ind = pd.Index(['russ'], name='pet')
exp = pd.DataFrame(data=[[5, 6, 7, 8]],
columns=exp_col, index=exp_ind)

pdt.assert_frame_equal(exp, obs[0])
pdt.assert_frame_equal(exp, median)

exp = pd.DataFrame(data=[[3, 3, 3, 3]],
columns=exp_col, index=exp_ind)

pdt.assert_frame_equal(exp, obs[1])
pdt.assert_frame_equal(exp, counts)

def test_multiple_columns(self):
columns = pd.MultiIndex.from_tuples([(1, 1), (1, 2), (200, 1),
Expand All @@ -492,34 +492,34 @@ def test_multiple_columns(self):
[9, 10, 11, 12, 'peanut', 'stick']],
columns=columns, index=['S1', 'S2', 'S3'])

obs = _reindex_with_metadata('pet', ['pet', 'toy'], data)
median, counts = _reindex_with_metadata('pet', ['pet', 'toy'], data)

exp_col = pd.MultiIndex(levels=[[1, 200, 'pet', 'toy'], [1, 2, '']],
labels=[[0, 0, 1, 1], [0, 1, 0, 1]],
codes=[[0, 0, 1, 1], [0, 1, 0, 1]],
names=['depth', 'iter'])
exp_ind = pd.Index(['milo', 'peanut', 'russ'], name='pet')
exp = pd.DataFrame(data=[[5, 6, 7, 8], [9, 10, 11, 12], [1, 2, 3, 4]],
columns=exp_col, index=exp_ind)

pdt.assert_frame_equal(exp, obs[0])
pdt.assert_frame_equal(exp, median)

exp = pd.DataFrame(data=[[1, 1, 1, 1], [1, 1, 1, 1], [1, 1, 1, 1]],
columns=exp_col, index=exp_ind)

pdt.assert_frame_equal(exp, obs[1])
pdt.assert_frame_equal(exp, counts)

obs = _reindex_with_metadata('toy', ['pet', 'toy'], data)
median, counts = _reindex_with_metadata('toy', ['pet', 'toy'], data)

exp_ind = pd.Index(['stick', 'yeti'], name='toy')
exp = pd.DataFrame(data=[[5, 6, 7, 8], [5, 6, 7, 8]],
columns=exp_col, index=exp_ind)

pdt.assert_frame_equal(exp, obs[0])
pdt.assert_frame_equal(exp, median)

exp = pd.DataFrame(data=[[2, 2, 2, 2], [1, 1, 1, 1]],
columns=exp_col, index=exp_ind)

pdt.assert_frame_equal(exp, obs[1])
pdt.assert_frame_equal(exp, counts)


class AlphaRarefactionJSONPTests(unittest.TestCase):
Expand Down