8000 ENH add fontname argument in export_graphviz for non-English characters by Zeroto521 · Pull Request #18959 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

ENH add fontname argument in export_graphviz for non-English characters #18959

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 17 commits into from
Jan 10, 2021
Merged

ENH add fontname argument in export_graphviz for non-English characters #18959

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
448a3d5
FIX add fontname argument in plot_tree for non-English characters
Zeroto521 Dec 17, 2020
2cd03cb
Update v0.24.rst
Zeroto521 Dec 17, 2020
bb6e603
Update v0.24.rst
Zeroto521 Dec 17, 2020
47550d7
Merge remote-tracking branch 'upstream/master' into graphviz-font
Zeroto521 Dec 17, 2020
f4741ec
Update v1.0.rst
Zeroto521 Dec 18, 2020
8aaede3
FIX add fontname argument in plot_tree for non-English characters
Zeroto521 Dec 18, 2020
01a2ef7
Add changelog for #18959
Zeroto521 Dec 18, 2020
f3fa121
Update v0.24.rst
Zeroto521 Dec 18, 2020
02ba737
overwrite the default fontname to test the export_graphviz function
Zeroto521 Dec 23, 2020
31021d0
Merge remote-tracking branch 'upstream/master' into graphviz-font
Zeroto521 Dec 23, 2020
384e63f
Remove fontname for tree.plot_tree
Zeroto521 Jan 5, 2021
74bd42a
Doc for tree.export_graphviz
Zeroto521 Jan 6, 2021
b18c0fc
Reduce fontname usage range, only in _DOTTreeExporter
Zeroto521 Jan 6, 2021
3681b68
Fix fontname only used when rounded=True in tree.export_graphviz
Zeroto521 Jan 6, 2021
c115dcf
Update test_graphviz_toy for fontname
Zeroto521 Jan 6, 2021
de4063f
Update test_graphviz_toy for fontname
Zeroto521 Jan 6, 2021
e695405
ENH add fontname in export_graphviz for non-English characters
Zeroto521 Jan 7, 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
7 changes: 7 additions & 0 deletions doc/whats_new/v1.0.rst
View file
Open in desktop
< 8000 template class="js-file-alert-template">
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,13 @@ Changelog
:pr:`123456` by :user:`Joe Bloggs <joeongithub>`.
where 123456 is the *pull request* number, not the issue number.

:mod:`sklearn.tree`
...................

- |Enhancement| Add `fontname` argument in :func:`tree.export_graphviz`
for non-English characters. :pr:`18959` by :user:`Zero <Zeroto521>`
and :user:`wstates <wstates>`.

:mod:`sklearn.cluster`
......................

Expand Down
29 changes: 16 additions & 13 deletions sklearn/tree/_export.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -371,18 +371,17 @@ def __init__(self, out_file=SENTINEL, max_depth=None,
feature_names=None, class_names=None, label='all',
filled=False, leaves_parallel=False, impurity=True,
node_ids=False, proportion=False, rotate=False, rounded=False,
special_characters=False, precision=3):
special_characters=False, precision=3, fontname='helvetica'):

super().__init__(
max_depth=max_depth, feature_names=feature_names,
class_names=class_names, label=label, filled=filled,
impurity=impurity,
node_ids=node_ids, proportion=proportion, rotate=rotate,
rounded=rounded,
precision=precision)
impurity=impurity, node_ids=node_ids, proportion=proportion,
rotate=rotate, rounded=rounded, precision=precision)
self.leaves_parallel = leaves_parallel
self.out_file = out_file
self.special_characters = special_characters
self.fontname = fontname

# PostScript compatibility for special characters
if special_characters:
Expand Down Expand Up @@ -449,16 +448,17 @@ def head(self):
self.out_file.write(
', style="%s", color="black"'
% ", ".join(rounded_filled))
if self.rounded:
self.out_file.write(', fontname=helvetica')

self.out_file.write(', fontname="%s"' % self.fontname)
self.out_file.write('] ;\n')

# Specify graph & edge aesthetics
if self.leaves_parallel:
self.out_file.write(
'graph [ranksep=equally, splines=polyline] ;\n')
if self.rounded:
self.out_file.write('edge [fontname=helvetica] ;\n')

self.out_file.write('edge [fontname="%s"] ;\n' % self.fontname)

if self.rotate:
self.out_file.write('rankdir=LR ;\n')

Expand Down Expand Up @@ -667,7 +667,8 @@ def export_graphviz(decision_tree, out_file=None, *, max_depth=None,
feature_names=None, class_names=None, label='all',
filled=False, leaves_parallel=False, impurity=True,
node_ids=False, proportion=False, rotate=False,
rounded=False, special_characters=False, precision=3):
rounded=False, special_characters=False, precision=3,
fontname='helvetica'):
"""Export a decision tree in DOT format.

This function generates a GraphViz representation of the decision tree,
Expand Down Expand Up @@ -734,8 +735,7 @@ def export_graphviz(decision_tree, out_file=None, *, max_depth=None,
When set to ``True``, orient tree left to right rather than top-down.

rounded : bool, default=False
When set to ``True``, draw node boxes with rounded corners and use
Helvetica fonts instead of Times-Roman.
When set to ``True``, draw node boxes with rounded corners.

special_characters : bool, default=False
When set to ``False``, ignore special characters for PostScript
Expand All @@ -745,6 +745,9 @@ def export_graphviz(decision_tree, out_file=None, *, max_depth=None,
Number of digits of precision for floating point in the values of
impurity, threshold and value attributes of each node.

fontname : str, default='helvetica'
Name of font used to render text.

Returns
-------
dot_data : string
Expand Down Expand Up @@ -784,7 +787,7 @@ def export_graphviz(decision_tree, out_file=None, *, max_depth=None,
filled=filled, leaves_parallel=leaves_parallel, impurity=impurity,
node_ids=node_ids, proportion=proportion, rotate=rotate,
rounded=rounded, special_characters=special_characters,
precision=precision)
precision=precision, fontname=fontname)
exporter.export(decision_tree)

if return_string:
Expand Down
37 changes: 24 additions & 13 deletions sklearn/tree/tests/test_export.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,8 @@ def test_graphviz_toy():
# Test export code
contents1 = export_graphviz(clf, out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box] ;\n' \
'node [shape=box, fontname="helvetica"] ;\n' \
'edge [fontname="helvetica"] ;\n' \
'0 [label="X[0] <= 0.0\\ngini = 0.5\\nsamples = 6\\n' \
'value = [3, 3]"] ;\n' \
'1 [label="gini = 0.0\\nsamples = 3\\nvalue = [3, 0]"] ;\n' \
Expand All @@ -50,7 +51,8 @@ def test_graphviz_toy():
contents1 = export_graphviz(clf, feature_names=["feature0", "feature1"],
out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box] ;\n' \
'node [shape=box, fontname="helvetica"] ;\n' \
'edge [fontname="helvetica"] ;\n' \
'0 [label="feature0 <= 0.0\\ngini = 0.5\\nsamples = 6\\n' \
'value = [3, 3]"] ;\n' \
'1 [label="gini = 0.0\\nsamples = 3\\nvalue = [3, 0]"] ;\n' \
Expand All @@ -66,7 +68,8 @@ def test_graphviz_toy():
# Test with class_names
contents1 = export_graphviz(clf, class_names=["yes", "no"], out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box] ;\n' \
'node [shape=box, fontname="helvetica"] ;\n' \
'edge [fontname="helvetica"] ;\n' \
'0 [label="X[0] <= 0.0\\ngini = 0.5\\nsamples = 6\\n' \
'value = [3, 3]\\nclass = yes"] ;\n' \
'1 [label="gini = 0.0\\nsamples = 3\\nvalue = [3, 0]\\n' \
Expand All @@ -84,11 +87,11 @@ def test_graphviz_toy():
# Test plot_options
contents1 = export_graphviz(clf, filled=True, impurity=False,
proportion=True, special_characters=True,
rounded=True, out_file=None)
rounded=True, out_file=None, fontname="sans")
contents2 = 'digraph Tree {\n' \
'node [shape=box, style="filled, rounded", color="black", ' \
'fontname=helvetica] ;\n' \
'edge [fontname=helvetica] ;\n' \
'fontname="sans"] ;\n' \
'edge [fontname="sans"] ;\n' \
'0 [label=<X<SUB>0</SUB> &le; 0.0<br/>samples = 100.0%<br/>' \
'value = [0.5, 0.5]>, fillcolor="#ffffff"] ;\n' \
'1 [label=<samples = 50.0%<br/>value = [1.0, 0.0]>, ' \
Expand All @@ -107,7 +110,8 @@ def test_graphviz_toy():
contents1 = export_graphviz(clf, max_depth=0,
class_names=True, out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box] ;\n' \
'node [shape=box, fontname="helvetica"] ;\n' \
'edge [fontname="helvetica"] ;\n' \
'0 [label="X[0] <= 0.0\\ngini = 0.5\\nsamples = 6\\n' \
'value = [3, 3]\\nclass = y[0]"] ;\n' \
'1 [label="(...)"] ;\n' \
Expand All @@ -122,7 +126,9 @@ def test_graphviz_toy():
contents1 = export_graphviz(clf, max_depth=0, filled=True,
out_file=None, node_ids=True)
contents2 = 'digraph Tree {\n' \
'node [shape=box, style="filled", color="black"] ;\n' \
'node [shape=box, style="filled", color="black", '\
'fontname="helvetica"] ;\n' \
'edge [fontname="helvetica"] ;\n' \
'0 [label="node #0\\nX[0] <= 0.0\\ngini = 0.5\\n' \
'samples = 6\\nvalue = [3, 3]", fillcolor="#ffffff"] ;\n' \
'1 [label="(...)", fillcolor="#C0C0C0"] ;\n' \
Expand All @@ -143,7 +149,9 @@ def test_graphviz_toy():
contents1 = export_graphviz(clf, filled=True,
impurity=False, out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box, style="filled", color="black"] ;\n' \
'node [shape=box, style="filled", color="black", ' \
'fontname="helvetica"] ;\n' \
'edge [fontname="helvetica"] ;\n' \
'0 [label="X[0] <= 0.0\\nsamples = 6\\n' \
'value = [[3.0, 1.5, 0.0]\\n' \
'[3.0, 1.0, 0.5]]", fillcolor="#ffffff"] ;\n' \
Expand Down Expand Up @@ -174,12 +182,13 @@ def test_graphviz_toy():
clf.fit(X, y)

contents1 = export_graphviz(clf, filled=True, leaves_parallel=True,
out_file=None, rotate=True, rounded=True)
out_file=None, rotate=True, rounded=True,
fontname="sans")
contents2 = 'digraph Tree {\n' \
'node [shape=box, style="filled, rounded", color="black", ' \
'fontname=helvetica] ;\n' \
'fontname="sans"] ;\n' \
'graph [ranksep=equally, splines=polyline] ;\n' \
'edge [fontname=helvetica] ;\n' \
'edge [fontname="sans"] ;\n' \
679A 'rankdir=LR ;\n' \
'0 [label="X[0] <= 0.0\\nmse = 1.0\\nsamples = 6\\n' \
'value = 0.0", fillcolor="#f2c09c"] ;\n' \
Expand All @@ -203,7 +212,9 @@ def test_graphviz_toy():

contents1 = export_graphviz(clf, filled=True, out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box, style="filled", color="black"] ;\n' \
'node [shape=box, style="filled", color="black", '\
'fontname="helvetica"] ;\n' \
'edge [fontname="helvetica"] ;\n' \
'0 [label="gini = 0.0\\nsamples = 6\\nvalue = 6.0", ' \
'fillcolor="#ffffff"] ;\n' \
'}'
Expand Down
0