本文整理汇总了Python中nltk.Tree方法的典型用法代码示例。如果您正苦于以下问题:Python nltk.Tree方法的具体用法?Python nltk.Tree怎么用?Python nltk.Tree使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类nltk
的用法示例。
在下文中一共展示了nltk.Tree方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: get_edges_in_tree
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def get_edges_in_tree(parent, leaves=[], path='', edges=[], lrb_rrb_fix=False):
for i, node in enumerate(parent):
if type(node) is nltk.Tree:
from_node = path
to_node = '{}-{}-{}'.format(path, node.label(), i)
edges.append((from_node, to_node))
if lrb_rrb_fix:
if node.label() == '-LRB-':
leaves.append('(')
if node.label() == '-RRB-':
leaves.append(')')
edges, leaves = get_edges_in_tree(node, leaves, to_node, edges)
else:
from_node = path
to_node = '{}-{}'.format(node, len(leaves))
edges.append((from_node, to_node))
leaves.append(node)
return edges, leaves
示例2: get_object
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def get_object(tree):
"""Get the object in the tree object.
Method should remove unnecessary letters and words::
the
a/an
's
Args:
tree (Tree): Parsed tree structure
Returns:
Resulting string of tree ``(Ex: "red car")``
"""
if isinstance(tree, Tree):
if tree.label() == 'DT' or tree.label() == 'POS':
return ''
words = []
for child in tree:
words.append(get_object(child))
return ' '.join([_f for _f in words if _f])
else:
return tree
示例3: parse
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def parse(self, chunk_struct, trace=None):
"""
Apply the chunk parser to this input.
:type chunk_struct: Tree
:param chunk_struct: the chunk structure to be (further) chunked
(this tree is modified, and is also returned)
:type trace: int
:param trace: The level of tracing that should be used when
parsing a text. ``0`` will generate no tracing output;
``1`` will generate normal tracing output; and ``2`` or
highter will generate verbose tracing output. This value
overrides the trace level value that was given to the
constructor.
:return: the chunked output.
:rtype: Tree
"""
if trace is None: trace = self._trace
for i in range(self._loop):
for parser in self._stages:
chunk_struct = parser.parse(chunk_struct, trace=trace)
return chunk_struct
示例4: parse_sents
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def parse_sents(self, sents):
"""
Parse multiple sentences
If "sents" is a string, it will be segmented into sentences using NLTK.
Otherwise, each element of "sents" will be treated as a sentence.
sents (str or Iterable[str] or Iterable[List[str]]): sentences to parse
Returns: Iter[nltk.Tree]
"""
if isinstance(sents, STRING_TYPES):
if self._tokenizer_lang is None:
raise ValueError(
"No tokenizer available for this language. "
"Please split into individual sentences and tokens "
"before calling the parser."
)
sents = nltk.sent_tokenize(sents, self._tokenizer_lang)
for parse_raw, tags_raw, sentence in self._batched_parsed_raw(self._nltk_process_sents(sents)):
yield self._make_nltk_tree(sentence, tags_raw, *parse_raw)
示例5: decode
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def decode(self, output_dict ) :
u"""
Constructs an NLTK ``Tree`` given the scored spans. We also switch to exclusive
span ends when constructing the tree representation, because it makes indexing
into lists cleaner for ranges of text, rather than individual indices.
Finally, for batch prediction, we will have padded spans and class probabilities.
In order to make this less confusing, we remove all the padded spans and
distributions from ``spans`` and ``class_probabilities`` respectively.
"""
all_predictions = output_dict[u'class_probabilities'].cpu().data
all_spans = output_dict[u"spans"].cpu().data
all_sentences = output_dict[u"tokens"]
all_pos_tags = output_dict[u"pos_tags"] if all(output_dict[u"pos_tags"]) else None
num_spans = output_dict[u"num_spans"].data
trees = self.construct_trees(all_predictions, all_spans, num_spans, all_sentences, all_pos_tags)
batch_size = all_predictions.size(0)
output_dict[u"spans"] = [all_spans[i, :num_spans[i]] for i in range(batch_size)]
output_dict[u"class_probabilities"] = [all_predictions[i, :num_spans[i], :] for i in range(batch_size)]
output_dict[u"trees"] = trees
return output_dict
示例6: to_nltk_tree_general
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def to_nltk_tree_general(node, attr_list=("dep_", "pos_"), level=99999):
"""Tranforms a Spacy dependency tree into an NLTK tree, with certain spacy tree node attributes serving
as parts of the NLTK tree node label content for uniqueness.
Args:
node: The starting node from the tree in which the transformation will occur.
attr_list: Which attributes from the Spacy nodes will be included in the NLTK node label.
level: The maximum depth of the tree.
Returns:
A NLTK Tree (nltk.tree)
"""
# transforms attributes in a node representation
value_list = [getattr(node, attr) for attr in attr_list]
node_representation = "/".join(value_list)
if level == 0:
return node_representation
if node.n_lefts + node.n_rights > 0:
return Tree(node_representation, [to_nltk_tree_general(child, attr_list, level-1) for child in node.children])
else:
return node_representation
示例7: get_node_representation
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def get_node_representation(tetre_format, token):
"""Given a format and a SpaCy node (spacy.token), returns this node representation using the NLTK tree (nltk.tree).
It recursivelly builds a NLTK tree and returns it, not only the node itself.
Args:
tetre_format: The attributes of this node that will be part of its string representation.
token: The SpaCy node itself (spacy.token).
Returns:
A NLTK Tree (nltk.tree)
"""
params = tetre_format.split(",")
node_representation = token.pos_
if token.n_lefts + token.n_rights > 0:
tree = Tree(node_representation,
[to_nltk_tree_general(child, attr_list=params, level=0) for child in token.children])
else:
tree = Tree(node_representation, [])
return tree
示例8: nltk_tree_to_qtree
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def nltk_tree_to_qtree(tree):
"""Transforms a NLTK Tree in a QTREE. A QTREE is a string representation of a tree.
For details, please see: http://www.ling.upenn.edu/advice/latex/qtree/qtreenotes.pdf
Args:
tree: The NLTK Tree (nltk.tree).
Returns:
A string with the QTREE representation of the NLTK Tree (nltk.tree).
"""
self_result = " [ "
if isinstance(tree, Tree):
self_result += " " + tree.label() + " "
if len(tree) > 0:
self_result += " ".join([nltk_tree_to_qtree(node) for node in sorted(tree)])
else:
self_result += " " + str(tree) + " "
self_result += " ] "
return self_result
示例9: nltk_tree_to_logical_form
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def nltk_tree_to_logical_form(tree: Tree) -> str:
"""
Given an ``nltk.Tree`` representing the syntax tree that generates a logical form, this method
produces the actual (lisp-like) logical form, with all of the non-terminal symbols converted
into the correct number of parentheses.
This is used in the logic that converts action sequences back into logical forms. It's very
unlikely that you will need this anywhere else.
"""
# nltk.Tree actually inherits from `list`, so you use `len()` to get the number of children.
# We're going to be explicit about checking length, instead of using `if tree:`, just to avoid
# any funny business nltk might have done (e.g., it's really odd if `if tree:` evaluates to
# `False` if there's a single leaf node with no children).
if len(tree) == 0:
return tree.label()
if len(tree) == 1:
return tree[0].label()
return "(" + " ".join(nltk_tree_to_logical_form(child) for child in tree) + ")"
示例10: add_words
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def add_words(self, file_name):
# Add words to the dictionary
f_in = open(file_name, 'r')
for line in f_in:
if line.strip() == '':
continue
data = eval(line)
sen_tree = Tree.fromstring(data['sentence1_parse'])
words = self.filter_words(sen_tree)
words = ['<s>'] + words + ['</s>']
for word in words:
self.dictionary.add_word(word)
sen_tree = Tree.fromstring(data['sentence2_parse'])
words = self.filter_words(sen_tree)
words = ['<s>'] + words + ['</s>']
for word in words:
self.dictionary.add_word(word)
f_in.close()
示例11: bft
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def bft(tree):
""" Perform a breadth-first traversal of a tree.
Return the nodes in a list in level-order.
Args:
tree: a tree node
Returns:
lst: a list of tree nodes in left-to-right level-order
"""
lst = []
queue = Queue.Queue()
queue.put(tree)
while not queue.empty():
node = queue.get()
lst.append(node)
for child in node:
if isinstance(child, nltk.Tree):
queue.put(child)
return lst
示例12: traverse_tree
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def traverse_tree(tree, pro):
""" Traverse a tree in a left-to-right, breadth-first manner,
proposing any NP encountered as an antecedent. Returns the
tree and the position of the first possible antecedent.
Args:
tree: the tree being searched
pro: the pronoun being resolved (string)
"""
# Initialize a queue and enqueue the root of the tree
queue = Queue.Queue()
queue.put(tree)
while not queue.empty():
node = queue.get()
# if the node is an NP, return it as a potential antecedent
if "NP" in node.label() and match(tree, get_pos(tree,node), pro):
return tree, get_pos(tree, node)
for child in node:
if isinstance(child, nltk.Tree):
queue.put(child)
# if no antecedent is found, return None
return None, None
示例13: match_rules_context
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def match_rules_context(tree, rules, parent_context={}):
"""Recursively matches a Tree structure with rules and returns context
Args:
tree (Tree): Parsed tree structure
rules (dict): See match_rules
parent_context (dict): Context of parent call
Returns:
dict: Context matched dictionary of matched rules or
None if no match
"""
for template, match_rules in rules.items():
context = parent_context.copy()
if match_template(tree, template, context):
for key, child_rules in match_rules.items():
child_context = match_rules_context(context[key], child_rules, context)
if child_context:
for k, v in child_context.items():
context[k] = v
else:
return None
return context
return None
示例14: match_rules_context_multi
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def match_rules_context_multi(tree, rules, parent_context={}):
"""Recursively matches a Tree structure with rules and returns context
Args:
tree (Tree): Parsed tree structure
rules (dict): See match_rules
parent_context (dict): Context of parent call
Returns:
dict: Context matched dictionary of matched rules or
None if no match
"""
all_contexts = []
for template, match_rules in rules.items():
context = parent_context.copy()
if match_template(tree, template, context):
child_contextss = []
if not match_rules:
all_contexts += [context]
else:
for key, child_rules in match_rules.items():
child_contextss.append(match_rules_context_multi(context[key], child_rules, context))
all_contexts += cross_context(child_contextss)
return all_contexts
示例15: match_template
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import Tree [as 别名]
def match_template(tree, template, args=None):
"""Check if match string matches Tree structure
Args:
tree (Tree): Parsed Tree structure of a sentence
template (str): String template to match. Example: "( S ( NP ) )"
Returns:
bool: If they match or not
"""
tokens = get_tokens(template.split())
cur_args = {}
if match_tokens(tree, tokens, cur_args):
if args is not None:
for k, v in cur_args.items():
args[k] = v
logger.debug('MATCHED: {0}'.format(template))
return True
else:
return False