def bracket_parse(files=items):
if type(files) is str: files = (files, )
for file in files:
path = os.path.join(get_basedir(), "ycoe/psd", file + ".psd")
s = open(path).read()
data = _parse(s)
for sent in data:
yield tree.bracket_parse(sent)
def bracket_parse(files = items):
if type(files) is str: files = (files,)
for file in files:
path = os.path.join(get_basedir(), "ycoe/psd", file + ".psd")
s = open(path).read()
data = _parse(s)
for sent in data:
yield tree.bracket_parse(sent)
def parsed(files = 'parsed'):
"""
@param files: One or more treebank files to be processed
@type files: L{string} or L{tuple(string)}
@rtype: iterator over L{tree}
"""
# Just one file to process? If so convert to a tuple so we can iterate
if type(files) is str: files = (files,)
for file in files:
path = os.path.join(get_basedir(), "sinica_treebank", file)
for sent in open(path).readlines():
yield tree.bracket_parse(sent)
def parsed(files = 'parsed'):
"""
@param files: One or more treebank files to be processed
@type files: L{string} or L{tuple(string)}
@rtype: iterator over L{tree}
"""
# Just one file to process? If so convert to a tuple so we can iterate
if type(files) is str: files = (files,)
for file in files:
path = os.path.join(get_basedir(), "sinica_treebank", file)
for sent in open(path).readlines():
yield tree.bracket_parse(sent)
def demo():
"""
A demonstration showing how C{Tree}s and C{Tree}s can be
used. This demonstration creates a C{Tree}, and loads a
C{Tree} from the L{treebank<nltk.corpus.treebank>} corpus,
and shows the results of calling several of their methods.
"""
from en.parser.nltk_lite.parse import tree
# Demonstrate tree parsing.
s = '(S (NP (DT the) (NN cat)) (VP (VBD ate) (NP (DT a) (NN cookie))))'
t = tree.bracket_parse(s)
print "Convert bracketed string into tree:"
print t
print "Display tree properties:"
print t.node # tree's constituent type
print t[0] # tree's first child
print t[1] # tree's second child
print t.height()
print t.leaves()
print t[1]
print t[1,1]
print t[1,1,0]
# Demonstrate tree modification.
the_cat = t[0]
the_cat.insert(1, tree.bracket_parse('(JJ big)'))
print "Tree modification:"
print t
t[1,1,1] = tree.bracket_parse('(NN cake)')
print t
print
# Demonstrate probabilistic trees.
pt = tree.ProbabilisticTree('x', ['y', 'z'], prob=0.5)
print "Probabilistic Tree:"
print pt
print
# Demonstrate parsing of treebank output format.
t = tree.bracket_parse(t.pp_treebank())[0]
print "Convert tree to bracketed string and back again:"
print t.pp_treebank()
print t
print
# Demonstrate LaTeX output
print "LaTeX output:"
print t.pp_latex_qtree()
print
# Demonstrate Productions
print "Production output:"
print t.productions()
print
# Demonstrate chunk parsing
s = "[ Pierre/NNP Vinken/NNP ] ,/, [ 61/CD years/NNS ] old/JJ ,/, will/MD join/VB [ the/DT board/NN ] ./."
from tree import chunk
print "Chunk Parsing:"
print chunk(s, chunk_node='NP').pp()
print
s = """
These DT B-NP
research NN I-NP
protocols NNS I-NP
offer VBP B-VP
to TO B-PP
the DT B-NP
patient NN I-NP
not RB O
only RB O
the DT B-NP
very RB I-NP
best JJS I-NP
therapy NN I-NP
which WDT B-NP
we PRP B-NP
have VBP B-VP
established VBN I-VP
today NN B-NP
but CC B-NP
also RB I-NP
the DT B-NP
hope NN I-NP
of IN B-PP
something NN B-NP
still RB B-ADJP
better JJR I-ADJP
. . O
"""
print conll_chunk(s, chunk_types=('NP', 'PP', 'VP')).pp()
# Demonstrate tree nodes containing objects other than strings
t.node = ('test', 3)
print t
def demo():
"""
A demonstration showing how C{Tree}s and C{Tree}s can be
used. This demonstration creates a C{Tree}, and loads a
C{Tree} from the L{treebank<nltk.corpus.treebank>} corpus,
and shows the results of calling several of their methods.
"""
from en.parser.nltk_lite.parse import tree
# Demonstrate tree parsing.
s = '(S (NP (DT the) (NN cat)) (VP (VBD ate) (NP (DT a) (NN cookie))))'
t = tree.bracket_parse(s)
print("Convert bracketed string into tree:")
print(t)
print("Display tree properties:")
print(t.node) # tree's constituent type
print(t[0]) # tree's first child
print(t[1]) # tree's second child
print(t.height())
print(t.leaves())
print(t[1])
print(t[1, 1])
print(t[1, 1, 0])
# Demonstrate tree modification.
the_cat = t[0]
the_cat.insert(1, tree.bracket_parse('(JJ big)'))
print("Tree modification:")
print(t)
t[1, 1, 1] = tree.bracket_parse('(NN cake)')
print(t)
print()
# Demonstrate probabilistic trees.
pt = tree.ProbabilisticTree('x', ['y', 'z'], prob=0.5)
print("Probabilistic Tree:")
print(pt)
print()
# Demonstrate parsing of treebank output format.
t = tree.bracket_parse(t.pp_treebank())[0]
print("Convert tree to bracketed string and back again:")
print(t.pp_treebank())
print(t)
print()
# Demonstrate LaTeX output
print("LaTeX output:")
print(t.pp_latex_qtree())
print()
# Demonstrate Productions
print("Production output:")
print(t.productions())
print()
# Demonstrate chunk parsing
s = "[ Pierre/NNP Vinken/NNP ] ,/, [ 61/CD years/NNS ] old/JJ ,/, will/MD join/VB [ the/DT board/NN ] ./."
from .tree import chunk
print("Chunk Parsing:")
print(chunk(s, chunk_node='NP').pp())
print()
s = """
These DT B-NP
research NN I-NP
protocols NNS I-NP
offer VBP B-VP
to TO B-PP
the DT B-NP
patient NN I-NP
not RB O
only RB O
the DT B-NP
very RB I-NP
best JJS I-NP
therapy NN I-NP
which WDT B-NP
we PRP B-NP
have VBP B-VP
established VBN I-VP
today NN B-NP
but CC B-NP
also RB I-NP
the DT B-NP
hope NN I-NP
of IN B-PP
something NN B-NP
still RB B-ADJP
better JJR I-ADJP
. . O
"""
print(conll_chunk(s, chunk_types=('NP', 'PP', 'VP')).pp())
# Demonstrate tree nodes containing objects other than strings
t.node = ('test', 3)
print(t)
def demo():
import random
def fill(cw):
cw['fill'] = '#%06d' % random.randint(0, 999999)
cf = CanvasFrame(width=550, height=450, closeenough=2)
t = tree.bracket_parse('''
(S (NP the very big cat)
(VP (Adv sorta) (V saw) (NP (Det the) (N dog))))''')
tc = TreeWidget(cf.canvas(),
t,
draggable=1,
node_font=('helvetica', -14, 'bold'),
leaf_font=('helvetica', -12, 'italic'),
roof_fill='white',
roof_color='black',
leaf_color='green4',
node_color='blue2')
cf.add_widget(tc, 10, 10)
def boxit(canvas, text):
big = ('helvetica', -16, 'bold')
return BoxWidget(canvas,
TextWidget(canvas, text, font=big),
fill='green')
def ovalit(canvas, text):
return OvalWidget(canvas, TextWidget(canvas, text), fill='cyan')
treetok = tree.bracket_parse(
'(S (NP this tree) (VP (V is) (AdjP shapeable)))')
tc2 = TreeWidget(cf.canvas(), treetok, boxit, ovalit, shapeable=1)
def color(node):
node['color'] = '#%04d00' % random.randint(0, 9999)
def color2(treeseg):
treeseg.node()['fill'] = '#%06d' % random.randint(0, 9999)
treeseg.node().child()['color'] = 'white'
tc.bind_click_trees(tc.toggle_collapsed)
tc2.bind_click_trees(tc2.toggle_collapsed)
tc.bind_click_nodes(color, 3)
tc2.expanded_tree(1).bind_click(color2, 3)
tc2.expanded_tree().bind_click(color2, 3)
paren = ParenWidget(cf.canvas(), tc2)
cf.add_widget(paren, tc.bbox()[2] + 10, 10)
tree3 = tree.bracket_parse('''
(S (NP this tree) (AUX was)
(VP (V built) (PP (P with) (NP (N tree_to_treesegment)))))''')
tc3 = tree_to_treesegment(cf.canvas(),
tree3,
tree_color='green4',
tree_xspace=2,
tree_width=2)
tc3['draggable'] = 1
cf.add_widget(tc3, 10, tc.bbox()[3] + 10)
def orientswitch(treewidget):
if treewidget['orientation'] == 'horizontal':
treewidget.expanded_tree(1, 1).subtrees()[0].set_text('vertical')
treewidget.collapsed_tree(1, 1).subtrees()[0].set_text('vertical')
treewidget.collapsed_tree(1).subtrees()[1].set_text('vertical')
treewidget.collapsed_tree().subtrees()[3].set_text('vertical')
treewidget['orientation'] = 'vertical'
else:
treewidget.expanded_tree(1, 1).subtrees()[0].set_text('horizontal')
treewidget.collapsed_tree(1,
1).subtrees()[0].set_text('horizontal')
treewidget.collapsed_tree(1).subtrees()[1].set_text('horizontal')
treewidget.collapsed_tree().subtrees()[3].set_text('horizontal')
treewidget['orientation'] = 'horizontal'
text = """
Try clicking, right clicking, and dragging
different elements of each of the trees.
The top-left tree is a TreeWidget built from
a Tree. The top-right is a TreeWidget built
from a Tree, using non-default widget
constructors for the nodes & leaves (BoxWidget
and OvalWidget). The bottom-left tree is
built from tree_to_treesegment."""
twidget = TextWidget(cf.canvas(), text.strip())
textbox = BoxWidget(cf.canvas(), twidget, fill='white', draggable=1)
cf.add_widget(textbox, tc3.bbox()[2] + 10, tc2.bbox()[3] + 10)
tree4 = tree.bracket_parse(
'(S (NP this tree) (VP (V is) (Adj horizontal)))')
tc4 = TreeWidget(cf.canvas(),
tree4,
draggable=1,
line_color='brown2',
roof_color='brown2',
node_font=('helvetica', -12, 'bold'),
node_color='brown4',
orientation='horizontal')
tc4.manage()
cf.add_widget(tc4, tc3.bbox()[2] + 10, textbox.bbox()[3] + 10)
tc4.bind_click(orientswitch)
tc4.bind_click_trees(tc4.toggle_collapsed, 3)
# Run mainloop
cf.mainloop()
def demo():
import random
def fill(cw):
cw['fill'] = '#%06d' % random.randint(0,999999)
cf = CanvasFrame(width=550, height=450, closeenough=2)
t = tree.bracket_parse('''
(S (NP the very big cat)
(VP (Adv sorta) (V saw) (NP (Det the) (N dog))))''')
tc = TreeWidget(cf.canvas(), t, draggable=1,
node_font=('helvetica', -14, 'bold'),
leaf_font=('helvetica', -12, 'italic'),
roof_fill='white', roof_color='black',
leaf_color='green4', node_color='blue2')
cf.add_widget(tc,10,10)
def boxit(canvas, text):
big = ('helvetica', -16, 'bold')
return BoxWidget(canvas, TextWidget(canvas, text,
font=big), fill='green')
def ovalit(canvas, text):
return OvalWidget(canvas, TextWidget(canvas, text),
fill='cyan')
treetok = tree.bracket_parse('(S (NP this tree) (VP (V is) (AdjP shapeable)))')
tc2 = TreeWidget(cf.canvas(), treetok, boxit, ovalit, shapeable=1)
def color(node):
node['color'] = '#%04d00' % random.randint(0,9999)
def color2(treeseg):
treeseg.node()['fill'] = '#%06d' % random.randint(0,9999)
treeseg.node().child()['color'] = 'white'
tc.bind_click_trees(tc.toggle_collapsed)
tc2.bind_click_trees(tc2.toggle_collapsed)
tc.bind_click_nodes(color, 3)
tc2.expanded_tree(1).bind_click(color2, 3)
tc2.expanded_tree().bind_click(color2, 3)
paren = ParenWidget(cf.canvas(), tc2)
cf.add_widget(paren, tc.bbox()[2]+10, 10)
tree3 = tree.bracket_parse('''
(S (NP this tree) (AUX was)
(VP (V built) (PP (P with) (NP (N tree_to_treesegment)))))''')
tc3 = tree_to_treesegment(cf.canvas(), tree3, tree_color='green4',
tree_xspace=2, tree_width=2)
tc3['draggable'] = 1
cf.add_widget(tc3, 10, tc.bbox()[3]+10)
def orientswitch(treewidget):
if treewidget['orientation'] == 'horizontal':
treewidget.expanded_tree(1,1).subtrees()[0].set_text('vertical')
treewidget.collapsed_tree(1,1).subtrees()[0].set_text('vertical')
treewidget.collapsed_tree(1).subtrees()[1].set_text('vertical')
treewidget.collapsed_tree().subtrees()[3].set_text('vertical')
treewidget['orientation'] = 'vertical'
else:
treewidget.expanded_tree(1,1).subtrees()[0].set_text('horizontal')
treewidget.collapsed_tree(1,1).subtrees()[0].set_text('horizontal')
treewidget.collapsed_tree(1).subtrees()[1].set_text('horizontal')
treewidget.collapsed_tree().subtrees()[3].set_text('horizontal')
treewidget['orientation'] = 'horizontal'
text = """
Try clicking, right clicking, and dragging
different elements of each of the trees.
The top-left tree is a TreeWidget built from
a Tree. The top-right is a TreeWidget built
from a Tree, using non-default widget
constructors for the nodes & leaves (BoxWidget
and OvalWidget). The bottom-left tree is
built from tree_to_treesegment."""
twidget = TextWidget(cf.canvas(), text.strip())
textbox = BoxWidget(cf.canvas(), twidget, fill='white', draggable=1)
cf.add_widget(textbox, tc3.bbox()[2]+10, tc2.bbox()[3]+10)
tree4 = tree.bracket_parse('(S (NP this tree) (VP (V is) (Adj horizontal)))')
tc4 = TreeWidget(cf.canvas(), tree4, draggable=1,
line_color='brown2', roof_color='brown2',
node_font=('helvetica', -12, 'bold'),
node_color='brown4', orientation='horizontal')
tc4.manage()
cf.add_widget(tc4, tc3.bbox()[2]+10, textbox.bbox()[3]+10)
tc4.bind_click(orientswitch)
tc4.bind_click_trees(tc4.toggle_collapsed, 3)
# Run mainloop
cf.mainloop()
