Python tree.draw_trees函数代码示例

def demo(draw_parses=None, print_parses=None):
    """
    A simple demo showing some basic functionality.
    """
    demos = ['aandeelhoudersvergadering', 'hardloopwedstrijd']
    trees = []
    with MBMA() as program:
        for word in demos:
            print 'Parsing: %s' % word
            results = program.classify(word)
            trees.extend(program.trees(results))
    if draw_parses is None:
        print
        print 'Draw parses (y/n)?',
        draw_parses = sys.stdin.readline().strip().lower().startswith('y')
    if draw_parses:
        from nltk.draw.tree import draw_trees
        print '  please wait...'
        draw_trees(*trees)

    if print_parses is None:
        print
        print 'Print parses (y/n)?',
        print_parses = sys.stdin.readline().strip().lower().startswith('y')
    if print_parses:
        for parse in trees:
            print parse

def demo():
    """
    A demonstration showing how each tree transform can be used.
    """

    from nltk.draw.tree import draw_trees
    from nltk import tree, treetransforms
    from copy import deepcopy

    # original tree from WSJ bracketed text
    sentence = """(TOP
  (S
    (S
      (VP
        (VBN Turned)
        (ADVP (RB loose))
        (PP
          (IN in)
          (NP
            (NP (NNP Shane) (NNP Longman) (POS 's))
            (NN trading)
            (NN room)))))
    (, ,)
    (NP (DT the) (NN yuppie) (NNS dealers))
    (VP (AUX do) (NP (NP (RB little)) (ADJP (RB right))))
    (. .)))"""
    t = tree.Tree.parse(sentence, remove_empty_top_bracketing=True)

    # collapse subtrees with only one child
    collapsedTree = deepcopy(t)
    treetransforms.collapse_unary(collapsedTree)

    # convert the tree to CNF
    cnfTree = deepcopy(collapsedTree)
    treetransforms.chomsky_normal_form(cnfTree)

    # convert the tree to CNF with parent annotation (one level) and horizontal smoothing of order two
    parentTree = deepcopy(collapsedTree)
    treetransforms.chomsky_normal_form(parentTree, horzMarkov=2, vertMarkov=1)

    # convert the tree back to its original form (used to make CYK results comparable)
    original = deepcopy(parentTree)
    treetransforms.un_chomsky_normal_form(original)

    # convert tree back to bracketed text
    sentence2 = original.pprint()
    print sentence
    print sentence2
    print "Sentences the same? ", sentence == sentence2

    draw_trees(t, collapsedTree, cnfTree, parentTree, original)

def testTreeFilter(tree=None):
    """

    :param tree: Sample tree string in bracket notation.
    """
    if tree:
        t = Tree(tree)
    else:
        t = Tree(
            '((S(NP-SBJ (PRP They))(ADVP-TMP (RB never))(VP (VBD considered)(S (NP-SBJ (PRP themselves) (VP (TO to) (VP (VB be) (NP-PRD (NN anything) (RB else)))))))))')
    t2 = t.copy(deep=True)
    filterLexical(t2)

    from nltk.draw.tree import draw_trees

    draw_trees(t, t2)

	def parse(self, sentence_string):
		"""Extra credit : parse an arbitrary string
		
		This is actually what we want at the end.
		Given an arbitrary string
		0) split it into sentences (if you want to accept multiple sentences.)
		1) tokenize
		2) POS-tag and other pre-processing technique
		3) parse it!
		4) draw it using nltk draw_trees like in the example
			it does not support labeled arc though :(
		"""
		#draw a tree
		from nltk.draw.tree import draw_trees
		from nltk.tree import Tree
		import nltk
		

		words = nltk.pos_tag(nltk.word_tokenize(sentence_string))
		sentence = {'tokens': ['ROOT'], 'arcs': [], 'pos':['ROOT']}
		for word, pos in words:
			sentence['tokens'].append(word)
			sentence['pos'].append(pos)
		indices = range(len(sentence['tokens']))
		fcg = self.make_fully_connected_graph(sentence)
		weighted = self._featurized_to_weighted(fcg)
		max_spanning_tree = mst(0, weighted)
		wlist = sentence['tokens']
		
		#print the dependencies
		for i in max_spanning_tree.keys():
			for j in max_spanning_tree[i].keys():
				print "%s->%s" % (i, j)
		
		t = self._build_tree(max_spanning_tree, 0, wlist)
		draw_trees(Tree(t))

def demo(choice=None, draw_parses=None, print_parses=None):
    """
    A demonstration of the probabilistic parsers.  The user is
    prompted to select which demo to run, and how many parses should
    be found; and then each parser is run on the same demo, and a
    summary of the results are displayed.
    """
    import sys, time
    from nltk import tokenize, toy_pcfg1, toy_pcfg2
    from nltk.parse import pchart

    # Define two demos.  Each demo has a sentence and a grammar.
    demos = [('I saw John with my telescope', toy_pcfg1),
             ('the boy saw Jack with Bob under the table with a telescope',
              toy_pcfg2)]

    if choice is None:
        # Ask the user which demo they want to use.
        print
        for i in range(len(demos)):
            print '%3s: %s' % (i+1, demos[i][0])
            print '     %r' % demos[i][1]
            print
        print 'Which demo (%d-%d)? ' % (1, len(demos)),
        choice = int(sys.stdin.readline().strip())-1
    try:
        sent, grammar = demos[choice]
    except:
        print 'Bad sentence number'
        return

    # Tokenize the sentence.
    tokens = sent.split()

    # Define a list of parsers.  We'll use all parsers.
    parsers = [
        pchart.InsideChartParser(grammar),
        pchart.RandomChartParser(grammar),
        pchart.UnsortedChartParser(grammar),
        pchart.LongestChartParser(grammar),
        pchart.InsideChartParser(grammar, beam_size = len(tokens)+1)   # was BeamParser
        ]

    # Run the parsers on the tokenized sentence.
    times = []
    average_p = []
    num_parses = []
    all_parses = {}
    for parser in parsers:
        print '\ns: %s\nparser: %s\ngrammar: %s' % (sent,parser,grammar)
        parser.trace(3)
        t = time.time()
        parses = parser.nbest_parse(tokens)
        times.append(time.time()-t)
        if parses: p = reduce(lambda a,b:a+b.prob(), parses, 0)/len(parses)
        else: p = 0
        average_p.append(p)
        num_parses.append(len(parses))
        for p in parses: all_parses[p.freeze()] = 1

    # Print some summary statistics
    print
    print '       Parser      Beam | Time (secs)   # Parses   Average P(parse)'
    print '------------------------+------------------------------------------'
    for i in range(len(parsers)):
        print '%18s %4d |%11.4f%11d%19.14f' % (parsers[i].__class__.__name__,
                                             parsers[i].beam_size,
                                             times[i],num_parses[i],average_p[i])
    parses = all_parses.keys()
    if parses: p = reduce(lambda a,b:a+b.prob(), parses, 0)/len(parses)
    else: p = 0
    print '------------------------+------------------------------------------'
    print '%18s      |%11s%11d%19.14f' % ('(All Parses)', 'n/a', len(parses), p)

    if draw_parses is None:
        # Ask the user if we should draw the parses.
        print
        print 'Draw parses (y/n)? ',
        draw_parses = sys.stdin.readline().strip().lower().startswith('y')
    if draw_parses:
        from nltk.draw.tree import draw_trees
        print '  please wait...'
        draw_trees(*parses)

    if print_parses is None:
        # Ask the user if we should print the parses.
        print
        print 'Print parses (y/n)? ',
        print_parses = sys.stdin.readline().strip().lower().startswith('y')
    if print_parses:
        for parse in parses:
            print parse

def main():
    import sys
    from optparse import OptionParser, OptionGroup
    usage = """%%prog [options] [grammar_file]""" % globals()

    opts = OptionParser(usage=usage)
    opts.add_option("-c", "--components",
        action="store_true", dest="show_components", default=0,
        help="show hole semantics components")
    opts.add_option("-r", "--raw",
        action="store_true", dest="show_raw", default=0,
        help="show the raw hole semantics expression")
    opts.add_option("-d", "--drawtrees",
        action="store_true", dest="draw_trees", default=0,
        help="show formula trees in a GUI window")
    opts.add_option("-v", "--verbose",
        action="count", dest="verbosity", default=0,
        help="show more information during parse")

    (options, args) = opts.parse_args()

    if len(args) > 0:
        filename = args[0]
    else:
        filename = 'grammars/hole.fcfg'

    print 'Reading grammar file', filename
    #grammar = data.load(filename)
    parser = load_earley(filename, trace=options.verbosity)

    # Prompt the user for a sentence.
    print 'Sentence: ',
    line = sys.stdin.readline()[:-1]

    # Parse the sentence.
    tokens = line.split()
    trees = parser.nbest_parse(tokens)
    print 'Got %d different parses' % len(trees)

    for tree in trees:
        # Get the semantic feature from the top of the parse tree.
        sem = tree[0].node['sem'].simplify()

        # Skolemise away all quantifiers.  All variables become unique.
        sem = sem.skolemise()

        # Reparse the semantic representation from its bracketed string format.
        # I find this uniform structure easier to handle.  It also makes the
        # code mostly independent of the lambda calculus classes.
        usr = bracket_parse(str(sem))

        # Break the hole semantics representation down into its components
        # i.e. holes, labels, formula fragments and constraints.
        hole_sem = HoleSemantics(usr)

        # Maybe print the raw semantic representation.
        if options.show_raw:
            print
            print 'Raw expression'
            print usr

        # Maybe show the details of the semantic representation.
        if options.show_components:
            print
            print 'Holes:       ', hole_sem.holes
            print 'Labels:      ', hole_sem.labels
            print 'Constraints: ', hole_sem.constraints
            print 'Top hole:    ', hole_sem.top_hole
            print 'Top labels:  ', hole_sem.top_most_labels
            print 'Fragments:'
            for (l,f) in hole_sem.fragments.items():
                print '\t%s: %s' % (l, f)

        # Find all the possible ways to plug the formulas together.
        pluggings = hole_sem.pluggings()

        # Build FOL formula trees using the pluggings.
        trees = map(hole_sem.formula_tree, pluggings)

        # Print out the formulas in a textual format.
        n = 1
        for tree in trees:
            print
            print '%d. %s' % (n, tree)
            n += 1

        # Maybe draw the formulas as trees.
        if options.draw_trees:
            draw_trees(*trees)

        print
        print 'Done.'

def demo():
    """
    A demonstration of the probabilistic parsers.  The user is
    prompted to select which demo to run, and how many parses should
    be found; and then each parser is run on the same demo, and a
    summary of the results are displayed.
    """
    import sys, time
    import nltk
    from nltk import tokenize
    from nltk.parse import ViterbiParser

    # Define two demos.  Each demo has a sentence and a grammar.
    demos = [('I saw the man with my telescope', nltk.toy_pcfg1),
             ('the boy saw Jack with Bob under the table with a telescope', nltk.toy_pcfg2)]

    # Ask the user which demo they want to use.
    print
    for i in range(len(demos)):
        print '%3s: %s' % (i+1, demos[i][0])
        print '     %r' % demos[i][1]
        print
    print 'Which demo (%d-%d)? ' % (1, len(demos)),
    try:
        snum = int(sys.stdin.readline().strip())-1
        sent, grammar = demos[snum]
    except:
        print 'Bad sentence number'
        return

    # Tokenize the sentence.
    tokens = sent.split()

    parser = ViterbiParser(grammar)
    all_parses = {}

    print '\nsent: %s\nparser: %s\ngrammar: %s' % (sent,parser,grammar)
    parser.trace(3)
    t = time.time()
    parses = parser.nbest_parse(tokens)
    time = time.time()-t
    if parses:
        average = reduce(lambda a,b:a+b.prob(), parses, 0)/len(parses)
    else:
        average = 0
    num_parses = len(parses)
    for p in parses:
        all_parses[p.freeze()] = 1

    # Print some summary statistics
    print
    print 'Time (secs)   # Parses   Average P(parse)'
    print '-----------------------------------------'
    print '%11.4f%11d%19.14f' % (time, num_parses, average)
    parses = all_parses.keys()
    if parses:
        p = reduce(lambda a,b:a+b.prob(), parses, 0)/len(parses)
    else: p = 0
    print '------------------------------------------'
    print '%11s%11d%19.14f' % ('n/a', len(parses), p)

    # Ask the user if we should draw the parses.
    print
    print 'Draw parses (y/n)? ',
    if sys.stdin.readline().strip().lower().startswith('y'):
        from nltk.draw.tree import draw_trees
        print '  please wait...'
        draw_trees(*parses)

    # Ask the user if we should print the parses.
    print
    print 'Print parses (y/n)? ',
    if sys.stdin.readline().strip().lower().startswith('y'):
        for parse in parses:
            print parse

    def draw(self):
        t = self.sem_labeled()
        from nltk.draw.tree import draw_trees

        draw_trees(t)

#.........这里部分代码省略.........
    NP   -> Det N         [.41]
    NP   -> Name          [.28]
    NP   -> NP PP         [.31]
    PP   -> P NP          [1.0]
    V    -> 'saw'         [.21]
    V    -> 'ate'         [.51]
    V    -> 'ran'         [.28]
    N    -> 'boy'         [.11]
    N    -> 'cookie'      [.12]
    N    -> 'table'       [.13]
    N    -> 'telescope'   [.14]
    N    -> 'hill'        [.5]
    Name -> 'Jack'        [.52]
    Name -> 'Bob'         [.48]
    P    -> 'with'        [.61]
    P    -> 'under'       [.39]
    Det  -> 'the'         [.41]
    Det  -> 'a'           [.31]
    Det  -> 'my'          [.28]
    """)

    demos = [('I saw John with my telescope', toy_pcfg1),
             ('the boy saw Jack with Bob under the table with a telescope',
              toy_pcfg2)]

    if choice is None:
        # Ask the user which demo they want to use.
        print()
        for i in range(len(demos)):
            print('%3s: %s' % (i+1, demos[i][0]))
            print('     %r' % demos[i][1])
            print()
        print('Which demo (%d-%d)? ' % (1, len(demos)), end=' ')
        choice = int(sys.stdin.readline().strip())-1
    try:
        sent, grammar = demos[choice]
    except:
        print('Bad sentence number')
        return

    # Tokenize the sentence.
    tokens = sent.split()

    # Define a list of parsers.  We'll use all parsers.
    parsers = [
        pchart.InsideChartParser(grammar),
        pchart.RandomChartParser(grammar),
        pchart.UnsortedChartParser(grammar),
        pchart.LongestChartParser(grammar),
        pchart.InsideChartParser(grammar, beam_size = len(tokens)+1)   # was BeamParser
        ]

    # Run the parsers on the tokenized sentence.
    times = []
    average_p = []
    num_parses = []
    all_parses = {}
    for parser in parsers:
        print('\ns: %s\nparser: %s\ngrammar: %s' % (sent,parser,grammar))
        parser.trace(3)
        t = time.time()
        parses = list(parser.parse(tokens))
        times.append(time.time()-t)
        p = (reduce(lambda a,b:a+b.prob(), parses, 0)/len(parses) if parses else 0)
        average_p.append(p)
        num_parses.append(len(parses))
        for p in parses: all_parses[p.freeze()] = 1

    # Print some summary statistics
    print()
    print('       Parser      Beam | Time (secs)   # Parses   Average P(parse)')
    print('------------------------+------------------------------------------')
    for i in range(len(parsers)):
        print('%18s %4d |%11.4f%11d%19.14f' % (parsers[i].__class__.__name__,
                                             parsers[i].beam_size,
                                             times[i],num_parses[i],average_p[i]))
    parses = all_parses.keys()
    if parses: p = reduce(lambda a,b:a+b.prob(), parses, 0)/len(parses)
    else: p = 0
    print('------------------------+------------------------------------------')
    print('%18s      |%11s%11d%19.14f' % ('(All Parses)', 'n/a', len(parses), p))

    if draw_parses is None:
        # Ask the user if we should draw the parses.
        print()
        print('Draw parses (y/n)? ', end=' ')
        draw_parses = sys.stdin.readline().strip().lower().startswith('y')
    if draw_parses:
        from nltk.draw.tree import draw_trees
        print('  please wait...')
        draw_trees(*parses)

    if print_parses is None:
        # Ask the user if we should print the parses.
        print()
        print('Print parses (y/n)? ', end=' ')
        print_parses = sys.stdin.readline().strip().lower().startswith('y')
    if print_parses:
        for parse in parses:
            print(parse)

 def draw(self):
     """
     Open a new window containing a graphical diagram of this tree.
     """
     from nltk.draw.tree import draw_trees
     draw_trees(self)

def demo():
    """
    A demonstration of the probabilistic parsers.  The user is
    prompted to select which demo to run, and how many parses should
    be found; and then each parser is run on the same demo, and a
    summary of the results are displayed.
    """
    import sys, time
    from nltk import tokenize
    from nltk.parse import ViterbiParser
    from nltk.grammar import toy_pcfg1, toy_pcfg2

    # Define two demos.  Each demo has a sentence and a grammar.
    demos = [('حرك الكرة الخضراء في أسفل الزاوية اليسرى', learned_pcfg),
             ('حرك الكرة', learned_pcfg),
             ('take the green pyramid and put it in the top left corner', learned_pcfg),
              ('move the pink triangle on top of the black square', learned_pcfg),
              ('move the red block and place it on top of the blue block that is on top of a green block', learned_pcfg),
              ('move the green block on top of the blue block', learned_pcfg)]

    # Ask the user which demo they want to use.
    print()
    for i in range(len(demos)):
        print('%3s: %s' % (i+1, demos[i][0]))
        # print('     %r' % demos[i][1])
        print()
    print('Which demo (%d-%d)? ' % (1, len(demos)), end=' ')
    try:
        snum = int(sys.stdin.readline().strip())-1
        sent, grammar = demos[snum]
    except:
        print('Bad sentence number')
        return

    # Tokenize the sentence.
    tokens = sent.split()
    print(grammar)

    parser = ViterbiParser(grammar)
    all_parses = {}

    # print('\nsent: %s\nparser: %s\ngrammar: %s' % (sent,parser,grammar))
    parser.trace(3)
    t = time.time()
    parses = parser.parse_all(tokens)
    time = time.time()-t
    average = (reduce(lambda a,b:a+b.prob(), parses, 0)/len(parses)
               if parses else 0)
    num_parses = len(parses)
    for p in parses:
        all_parses[p.freeze()] = 1

    # Print some summary statistics
    print()
    print('Time (secs)   # Parses   Average P(parse)')
    print('-----------------------------------------')
    print('%11.4f%11d%19.14f' % (time, num_parses, average))
    parses = all_parses.keys()
    if parses:
        p = reduce(lambda a,b:a+b.prob(), parses, 0)/len(parses)
    else: p = 0
    print('------------------------------------------')
    print('%11s%11d%19.14f' % ('n/a', len(parses), p))

    # Ask the user if we should draw the parses.
    print()
    print('Draw parses (y/n)? ', end=' ')
    if sys.stdin.readline().strip().lower().startswith('y'):
        from nltk.draw.tree import draw_trees
        print('  please wait...')
        draw_trees(*parses)

    # Ask the user if we should print the parses.
    print()
    print('Print parses (y/n)? ', end=' ')
    if sys.stdin.readline().strip().lower().startswith('y'):
        for parse in parses:
            print(parse)

VP -> V NP | VP PP
Det -> 'an' | 'my'
N -> 'elephant' | 'pajamas'
V -> 'shot'
P -> 'in'
""")

sent = ['I', 'shot', 'an', 'elephant', 'in', 'my', 'pajamas']
parser = nltk.ChartParser(groucho_grammar)
for tree1 in parser.parse(sent):
    print(tree1)

grammar1 = nltk.CFG.fromstring("""
S -> NP VP
VP -> V NP | V NP PP
PP -> P NP
V -> "saw" | "ate" | "walked"
NP -> "John" | "Mary" | "Bob" | Det N | Det N PP
Det -> "a" | "an" | "the" | "my"
N -> "man" | "dog" | "cat" | "telescope" | "park"
P -> "in" | "on" | "by" | "with"
""")

sent = "Mary saw Bob".split()
rd_parser = nltk.RecursiveDescentParser(grammar1)
for tree2 in rd_parser.parse(sent):
    print(tree2)

from nltk.draw.tree import draw_trees
draw_trees(tree1, tree2)     

    return Tree(t.node, [excise_empty_nodes(st) for st in t])

# nb: returns tree with blank nodes excised
def parse_ccgbank_tree(s):
    t = Tree.parse(s, 
                   parse_node=parse_ccgbank_node, 
                   parse_leaf=parse_ccgbank_leaf, 
                   node_pattern=ccgbank_node_pattern, 
                   leaf_pattern=ccgbank_leaf_pattern)
    return excise_empty_nodes(t)

print
print 'parsing: ' + deriv
t = parse_ccgbank_tree(deriv)
print t

t2 = None
if deriv2 != None:
    print
    print 'parsing: ' + deriv2
    t2 = parse_ccgbank_tree(deriv2)
    print t2

print
if t2 == None:
    print 'drawing tree'
    draw_trees(t)
else:
    print 'drawing trees'
    draw_trees(t,t2)

def parseAllTestXmls(fileList, grammar, allTestSolutionsDict, verbose=False, displayTrees=False):
	testPitchLists = []
	testIntervalLists = []
	totalCorrect = 0
	totalCorrectNonN = 0
	totalProductions = 0
	totalLeaves = 0
	parseTreeStrings = {}
	for filepath in fileList:
		curPitchList = getPitchListFromFile(filepath)
		testPitchLists.append(curPitchList)
		testIntervalLists.append(getIntervalStringsFromPitchList(curPitchList, verbose))
		if verbose:
			print(testIntervalLists[-1])
		listLen = len(testIntervalLists[-1])
		if verbose:
			print(tree)
		parser = ViterbiParser(grammar)
		if verbose:
			parser.trace(0)#3
		else:
			parser.trace(0)
		try:
			parses = parser.parse_all(testIntervalLists[-1])
		except Exception as errorMsg:
			print("error parsing file " + filepath)
			print(errorMsg)
		numTrees = sum(1 for _ in parses)
		if numTrees > 0 and displayTrees == True:
			from nltk.draw.tree import draw_trees
			draw_trees(*parses)
		if numTrees == 0:
			print("Couldn't find a valid parse, this is bad, very very bad")
			return 0,0
		numCorrect = 0
		numCorrectNonN = 0
		bottomCorrect = 0
		bottomCorrectNonN = 0
		solutionTree = None
		try:
			solutionTreeStr = allTestSolutionsDict[filepath]
			solutionTree = Tree.fromstring(solutionTreeStr)
		except Exception as errorMsg:
			print("couldn't find solution for file " + filepath)
			print(errorMsg)
		if solutionTree != None and solutionTree != '':
			parseTreeStrings[filepath] = str(parses[0])
			numCorrect, numCorrectNonN = validate_tree.compareTrees(solutionTree, parses[0])
			numProductions = len(solutionTree.productions())
			totalProductions += numProductions

			#solutionTree.draw()
			#parses[0].draw()
			bottomCorrect, bottomCorrectNonN = validate_tree.compareTreesBottomUp(solutionTree, parses[0])
			parseTreeStrings[filepath+'_afterComparison'] = str(parses[0])
			totalLeaves += len(solutionTree.leaves())
			#parses[0].draw()

		totalCorrect += bottomCorrect
		totalCorrect += numCorrect
		totalCorrectNonN += numCorrectNonN
		totalCorrectNonN += bottomCorrectNonN
	return totalCorrect, totalCorrectNonN, totalProductions, totalLeaves, parseTreeStrings

def make(op):
	if op == 0:
		for name in case.keys():
			if name != "Corpus":
				print name
				print len(inst[name].grammar.productions()), "producciones en grammar"
				print len(inst[name].parser.grammar().productions()), "producciones usadas en parser"
				print "---"
	elif op == 1:
		cant_oraciones = inst["Corpus"].cant_oraciones()
		print CR,"Cantidad de oraciones: "
		print cant_oraciones
	elif op == 2:
		oracion_mas_larga = inst["Corpus"].oracion_mas_larga()
		print CR,"Oracion mas larga:"
		print len(oracion_mas_larga.split(' ')), "palabras"
		print oracion_mas_larga
	elif op == 3:
		largo_promedio_oracion = inst["Corpus"].largo_promedio_oracion()
		print CR,"Largo promedio de oración:"
		print largo_promedio_oracion, "letras"
	elif op == 4:
		palabras_frecs = inst["Corpus"].palabras_frecs()
		print CR,"Palabras frecuentes:"
		print '\n\t'.join(map(str,sorted(palabras_frecs.items(),key=lambda x:x[1],reverse=True)[:20]))
	elif op == 5:
		palabras_frecs_cat = inst["Corpus"].palabras_frecs_cat()
		print CR,"Palabras frecuentes por categoria:"
		print '\n\t'.join(map(str,sorted(palabras_frecs_cat.items(),key=lambda x:len(x[1]),reverse=True)[:20]))
	elif op == 6:
		arbol_min_nodos = inst["Corpus"].arbol_min_nodos()
		print CR,"Arbol con minima cantidad de nodos:"
		print len(arbol_min_nodos.treepositions()), "nodos"
		draw_trees(arbol_min_nodos)
	elif op == 7:
		arbol_max_nodos = inst["Corpus"].arbol_max_nodos()
		print CR,"Arbol con maxima cantidad de nodos:"
		print len(arbol_max_nodos.treepositions()), "nodos"
		draw_trees(arbol_max_nodos) 
	elif op == 8:
		lema = raw_input('\r'+' '*20+'\rLema > ')
		if not lema: lema = "mostrar"
		print "Procesando..."
		arboles_con_lema = inst["Corpus"].arboles_con_lema(lema)
		if arboles_con_lema:
			print CR,"Arboles con lema \'",lema,"\'"
			print len(arboles_con_lema), "arboles"
			if raw_input("Dibujar? [s/n] ") == 's':draw_trees(*arboles_con_lema)
			print "** Ejemplo oracion **"
			print ' '.join(arboles_con_lema[randint(0,len(arboles_con_lema)-1)].leaves())
		else: print CR,"No hay arboles con lema \'",lema,"\'"
	elif op == 9:
		print CR,len(inst["PCFG"].reglas_no_lexicas()), "reglas no lexicas"
	elif op == 10:
		print CR,len(inst["PCFG"].categorias_lexicas()), "categorias lexicas"
	elif op == 11:
		cat = raw_input(CR+'Categoria > ')
		if not cat: cat = "vmip3s0"
		print CR,len(inst["PCFG"].reglas_lexicas(cat)), "reglas lexicas con categoria \'",cat,"\'"
	elif op == 12:
		sent = inst["PCFG"].sents[0]
		parsed = inst["PCFG"].parse(sent)
	elif op == 13:
		sent = inst["PCFG"].sents[1]
		parsed = inst["PCFG"].parse(sent)
	elif op == 14:
		sent = inst["PCFG"].sents[2]
		parsed = inst["PCFG"].parse(sent)
	elif op == 15:
		sent = inst["PCFG_UNK"].sents[0]
		parsed = inst["PCFG_UNK"].parse(sent)
	elif op == 16:
		sent = inst["PCFG_UNK"].sents[1]
		parsed = inst["PCFG_UNK"].parse(sent)
	elif op == 17:
		sent = inst["PCFG_LEX"].sents[0]
		parsed = inst["PCFG"].parse(sent)
	elif op == 18:
		sent = inst["PCFG_LEX"].sents[0]
		parsed = inst["PCFG_LEX"].parse(sent)
	elif op == 19:
		sent = inst["PCFG_LEX_VERB"].sents[0]
		parsed = inst["PCFG_LEX"].parse(sent)
	elif op == 20:
		sent = inst["PCFG_LEX_VERB"].sents[1]
		parsed = inst["PCFG_LEX"].parse(sent)
	elif op == 21:
		sent = inst["PCFG_LEX_VERB"].sents[0]
		parsed = inst["PCFG_LEX_VERB"].parse(sent)
	elif op == 22:
		sent = inst["PCFG_LEX_VERB"].sents[1]
		parsed = inst["PCFG_LEX_VERB"].parse(sent)
	elif op == 23:
		sent = inst["PCFG_LEX_VERB"].sents[2]
		parsed = inst["PCFG_LEX"].parse(sent)
	elif op == 24:
		sent = inst["PCFG_LEX_VERB"].sents[2]
		parsed = inst["PCFG_LEX_VERB"].parse(sent)
	else:
		print "Comando no valido!"
#.........这里部分代码省略.........