BUG SparseDataFrame with dense Series (#19374) #19377
Conversation
| def test_constructor_from_unknown_type(self): | ||
| class Unknown: | ||
| pass | ||
| pytest.raises(TypeError, SparseDataFrame, Unknown()) |
There was a problem hiding this comment.
Let's check error message for all of your pytest.raises calls.
| @@ -199,6 +199,31 @@ def test_constructor_from_series(self): | |||
| # without sparse value raises error | |||
| # df2 = SparseDataFrame([x2_sparse, y]) | |||
|
|
|||
| def test_constructor_from_dense_series(self): | |||
There was a problem hiding this comment.
Reference issue number under all of your added tests.
|
@datapythonista : Looks pretty good so far. Don't forget to add a |
| x = Series(np.random.randn(10000), name='a') | ||
| assert isinstance(x, Series) | ||
| df = SparseDataFrame(x) | ||
| assert isinstance(df, SparseDataFrame) |
There was a problem hiding this comment.
construct an expected SDF and compare
There was a problem hiding this comment.
construct a DataFrame and use .to_sparse() to construct an expected frame. we do not want to do all of these little checks, we already have well established comparison functions, e.g. tm.assert_sparse_equal for this
| assert isinstance(df, SparseDataFrame) | ||
| assert df.columns == ['b'] | ||
|
|
||
| # No column name available |
pandas/core/sparse/frame.py
Outdated
| @@ -95,6 +95,13 @@ def __init__(self, data=None, index=None, columns=None, default_kind=None, | |||
| dtype=dtype, copy=copy) | |||
| elif isinstance(data, DataFrame): | |||
| mgr = self._init_dict(data, data.index, data.columns, dtype=dtype) | |||
| elif isinstance(data, Series): | |||
| if columns is None and data.name is None: | |||
There was a problem hiding this comment.
need a test to hit this case
|
Thanks a lot for the comments. Sorry about the whatsnew, I added it when opening the PR, but forgot to add it to the commit. @jreback, I didn't find a way to construct the expected Addressed all the other comments, let me know if you see anything else. Thanks! |
pandas/core/sparse/frame.py
Outdated
| elif len(columns) != 1: | ||
| raise ValueError('columns must be of length one ' | ||
| 'if data is of type Series') | ||
| mgr = self._init_dict(data.to_frame(columns[0]), |
There was a problem hiding this comment.
don't construct like this, actually make dict
| x = Series(np.random.randn(10000), name='a') | ||
| assert isinstance(x, Series) | ||
| df = SparseDataFrame(x) | ||
| assert isinstance(df, SparseDataFrame) |
There was a problem hiding this comment.
construct a DataFrame and use .to_sparse() to construct an expected frame. we do not want to do all of these little checks, we already have well established comparison functions, e.g. tm.assert_sparse_equal for this
pandas/core/sparse/frame.py
Outdated
| if columns is None: | ||
| if data.name is None: | ||
| raise ValueError('cannot pass a series ' | ||
| 'w/o a name or columns') |
There was a problem hiding this comment.
I don't think you need any of this, you can simply all to_manager with the column (in a list)
|
Thanks for the feedback @jreback, I misunderstood what the columns argument had to do, and I was overcomplicating the code. Now it simply creates the I'm not 100% sure I understood what you mean by "actually contruct dic", please let me know if this new version doesn't address this too. |
| # GH 19393 | ||
| # series with name | ||
| x = Series(np.random.randn(10000), name='a') | ||
| assert isinstance(x, Series) |
There was a problem hiding this comment.
you don't need this assert
| # series with name | ||
| x = Series(np.random.randn(10000), name='a') | ||
| assert isinstance(x, Series) | ||
| res = SparseDataFrame(x) |
There was a problem hiding this comment.
I prefer result and expected
| x = Series(np.random.randn(10000), name='a') | ||
| assert isinstance(x, Series) | ||
| res = SparseDataFrame(x) | ||
| assert isinstance(res, SparseDataFrame) |
| # series with no name | ||
| x = Series(np.random.randn(10000)) | ||
| assert isinstance(x, Series) | ||
| res = SparseDataFrame(x) |
There was a problem hiding this comment.
same w.r.t naming & asserts
…r, and providing useful error messages for other types (#19374)
|
Thanks once again for the comments @jreback, seems that I followed the conventions of an old test. Addressed your comments, should be all right now. |
|
thanks @datapythonista |
git diff upstream/master -u -- "*.py" | flake8 --diff