Skip to content

REF: add internal mechanics to separate index/columns sparsification in Styler #41391

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
merged 6 commits into from
May 12, 2021
Merged

REF: add internal mechanics to separate index/columns sparsification in Styler #41391

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
d29cac1
add separate index/columns sparsify mechanics
attack68 May 9, 2021
5465953
fix docstring
attack68 May 11, 2021
7c0f687
Merge remote-tracking branch 'upstream/master' into sparisfy_separate
attack68 May 11, 2021
0a57c1a
Merge remote-tracking branch 'upstream/master' into sparisfy_separate
attack68 May 12, 2021
1744a5e
type _get_level_lengths
attack68 May 12, 2021
08b5174
add docs and typing to _translates
attack68 May 12, 2021
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
111 changes: 95 additions & 16 deletions pandas/io/formats/style_render.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,11 +132,33 @@ def _compute(self):
r = func(self)(*args, **kwargs)
return r

def _translate(self):
def _translate(
self, sparsify_index: bool | None = None, sparsify_cols: bool | None = None
):
"""
Convert the DataFrame in `self.data` and the attrs from `_build_styles`
into a dictionary of {head, body, uuid, cellstyle}.
Process Styler data and settings into a dict for template rendering.

Convert data and settings from ``Styler`` attributes such as ``self.data``,
``self.tooltips`` including applying any methods in ``self._todo``.

Parameters
----------
sparsify_index : bool, optional
Whether to sparsify the index or print all hierarchical index elements
sparsify_cols : bool, optional
Whether to sparsify the columns or print all hierarchical column elements

Returns
-------
d : dict
The following structure: {uuid, table_styles, caption, head, body,
cellstyle, table_attributes}
"""
if sparsify_index is None:
sparsify_index = get_option("display.multi_sparse")
if sparsify_cols is None:
sparsify_cols = get_option("display.multi_sparse")

ROW_HEADING_CLASS = "row_heading"
COL_HEADING_CLASS = "col_heading"
INDEX_NAME_CLASS = "index_name"
Expand All @@ -153,14 +175,14 @@ def _translate(self):
}

head = self._translate_header(
BLANK_CLASS, BLANK_VALUE, INDEX_NAME_CLASS, COL_HEADING_CLASS
BLANK_CLASS, BLANK_VALUE, INDEX_NAME_CLASS, COL_HEADING_CLASS, sparsify_cols
)
d.update({"head": head})

self.cellstyle_map: DefaultDict[tuple[CSSPair, ...], list[str]] = defaultdict(
list
)
body = self._translate_body(DATA_CLASS, ROW_HEADING_CLASS)
body = self._translate_body(DATA_CLASS, ROW_HEADING_CLASS, sparsify_index)
d.update({"body": body})

cellstyle: list[dict[str, CSSList | list[str]]] = [
Expand All @@ -185,20 +207,47 @@ def _translate(self):
return d

def _translate_header(
self, blank_class, blank_value, index_name_class, col_heading_class
self,
blank_class: str,
blank_value: str,
index_name_class: str,
col_heading_class: str,
sparsify_cols: bool,
):
"""
Build each <tr> within table <head>, using the structure:
Build each <tr> within table <head> as a list

Using the structure:
+----------------------------+---------------+---------------------------+
| index_blanks ... | column_name_0 | column_headers (level_0) |
1) | .. | .. | .. |
| index_blanks ... | column_name_n | column_headers (level_n) |
+----------------------------+---------------+---------------------------+
2) | index_names (level_0 to level_n) ... | column_blanks ... |
+----------------------------+---------------+---------------------------+

Parameters
----------
blank_class : str
CSS class added to elements within blank sections of the structure.
blank_value : str
HTML display value given to elements within blank sections of the structure.
index_name_class : str
CSS class added to elements within the index_names section of the structure.
col_heading_class : str
CSS class added to elements within the column_names section of structure.
sparsify_cols : bool
Whether column_headers section will add colspan attributes (>1) to elements.

Returns
-------
head : list
The associated HTML elements needed for template rendering.
"""
# for sparsifying a MultiIndex
col_lengths = _get_level_lengths(self.columns, self.hidden_columns)
col_lengths = _get_level_lengths(
self.columns, sparsify_cols, self.hidden_columns
)

clabels = self.data.columns.tolist()
if self.data.columns.nlevels == 1:
Expand Down Expand Up @@ -268,18 +317,36 @@ def _translate_header(

return head

def _translate_body(self, data_class, row_heading_class):
def _translate_body(
self, data_class: str, row_heading_class: str, sparsify_index: bool
):
"""
Build each <tr> in table <body> in the following format:
Build each <tr> within table <body> as a list

Use the following structure:
+--------------------------------------------+---------------------------+
| index_header_0 ... index_header_n | data_by_column |
+--------------------------------------------+---------------------------+

Also add elements to the cellstyle_map for more efficient grouped elements in
<style></style> block

Parameters
----------
data_class : str
CSS class added to elements within data_by_column sections of the structure.
row_heading_class : str
CSS class added to elements within the index_header section of structure.
sparsify_index : bool
Whether index_headers section will add rowspan attributes (>1) to elements.

Returns
-------
body : list
The associated HTML elements needed for template rendering.
"""
# for sparsifying a MultiIndex
idx_lengths = _get_level_lengths(self.index)
idx_lengths = _get_level_lengths(self.index, sparsify_index)

rlabels = self.data.index.tolist()
if self.data.index.nlevels == 1:
Expand Down Expand Up @@ -520,14 +587,26 @@ def _element(
}


def _get_level_lengths(index, hidden_elements=None):
def _get_level_lengths(
index: Index, sparsify: bool, hidden_elements: Sequence[int] | None = None
):
"""
Given an index, find the level length for each element.

Optional argument is a list of index positions which
should not be visible.
Parameters
----------
index : Index
Index or columns to determine lengths of each element
sparsify : bool
Whether to hide or show each distinct element in a MultiIndex
hidden_elements : sequence of int
Index positions of elements hidden from display in the index affecting
length

Result is a dictionary of (level, initial_position): span
Returns
-------
Dict :
Result is a dictionary of (level, initial_position): span
"""
if isinstance(index, MultiIndex):
levels = index.format(sparsify=lib.no_default, adjoin=False)
Expand All @@ -546,7 +625,7 @@ def _get_level_lengths(index, hidden_elements=None):

for i, lvl in enumerate(levels):
for j, row in enumerate(lvl):
if not get_option("display.multi_sparse"):
if not sparsify:
lengths[(i, j)] = 1
elif (row is not lib.no_default) and (j not in hidden_elements):
last_label = j
Expand Down
34 changes: 32 additions & 2 deletions pandas/tests/io/formats/style/test_style.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -844,7 +844,24 @@ def test_get_level_lengths(self):
(1, 4): 1,
(1, 5): 1,
}
result = _get_level_lengths(index)
result = _get_level_lengths(index, sparsify=True)
tm.assert_dict_equal(result, expected)

expected = {
(0, 0): 1,
(0, 1): 1,
(0, 2): 1,
(0, 3): 1,
(0, 4): 1,
(0, 5): 1,
(1, 0): 1,
(1, 1): 1,
(1, 2): 1,
(1, 3): 1,
(1, 4): 1,
(1, 5): 1,
}
result = _get_level_lengths(index, sparsify=False)
tm.assert_dict_equal(result, expected)

def test_get_level_lengths_un_sorted(self):
Expand All @@ -858,7 +875,20 @@ def test_get_level_lengths_un_sorted(self):
(1, 2): 1,
(1, 3): 1,
}
result = _get_level_lengths(index)
result = _get_level_lengths(index, sparsify=True)
tm.assert_dict_equal(result, expected)

expected = {
(0, 0): 1,
(0, 1): 1,
(0, 2): 1,
(0, 3): 1,
(1, 0): 1,
(1, 1): 1,
(1, 2): 1,
(1, 3): 1,
}
result = _get_level_lengths(index, sparsify=False)
tm.assert_dict_equal(result, expected)

def test_mi_sparse(self):
Expand Down