Skip to content

Nested list multi index (#14467) #32812

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.

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

Closed
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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: 10 additions & 5 deletions pandas/core/internals/construction.py
Original file line number Diff line number Diff line change
Expand Up @@ -576,11 +576,16 @@ def _convert_object_array(content, columns, coerce_float=False, dtype=None):
else:
if len(columns) != len(content): # pragma: no cover
# caller's responsibility to check for this...
raise AssertionError(
f"{len(columns)} columns passed, passed data had "
f"{len(content)} columns"
)

# Its possible that the user may be trying to pass a MultiIndex here.
# Attempt to convert columns to MultiIndex, and check length again.
# This conversion should be safe to do, as the input expects an Index
# and the colums are left unmodified throughout the rest of this function.
columns = ensure_index(columns)
if len(columns) != len(content):
raise AssertionError(
f"{len(columns)} columns passed, passed data had "
f"{len(content)} columns"
)
# provide soft conversion of object dtypes
def convert(arr):
if dtype != object and dtype != np.object:
Expand Down
42 changes: 42 additions & 0 deletions pandas/tests/indexes/multi/test_nested_list_data.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,42 @@
import pandas as pd
import pandas._testing as tm
import numpy as np
import pytest


'''
This code is meant to test the fix implemented for issue #14467.
https://github.com/pandas-dev/pandas/issues/14467
'''

class TestNestedListDataMultiIndex:
Copy link
Member

Choose a reason for hiding this comment

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

Instead of creating a new file, could you put these tests in an existing file like pandas/tests/frame/test_constructor.py


def test_nested_list(self):
# Case from issue, creating data from np.array works, and should match this case
result = pd.DataFrame([[1, 2, 3], [4, 5, 6]],
index=[['gibberish']*2, [0, 1]],
columns=[['baldersash']*3, [10, 20, 30]])

expected = pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6]]),
index=[['gibberish']*2, [0, 1]],
columns=[['baldersash']*3, [10, 20, 30]])
tm.assert_index_equal(result.columns, expected.columns)

def test_nest_list_with_multiIndex(self):
# Creating from a multiIndex should also still work
m = pd.MultiIndex.from_arrays([['baldersash']*3, [10, 20, 30]])
result = pd.DataFrame([[1, 2, 3], [4, 5, 6]],
index=[['gibberish']*2, [0, 1]],
columns=m)

expected = pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6]]),
index=[['gibberish']*2, [0, 1]],
columns=[['baldersash']*3, [10, 20, 30]])
tm.assert_index_equal(result.columns, expected.columns)

def test_wrong_length_raises_error(self):
# Make sure the code raises an error if the nested lists have the wrong length
with pytest.raises(ValueError):
result = pd.DataFrame([[1, 2, 3], [4, 5, 6]],
index=[['gibberish']*2, [0, 1]],
columns=[['baldersash']*2, [10, 20]])