Python generate.generate函数代码示例

    def generate_sentence(self, depth=9, num=30000):
        if num > 30000:
            num = 30000
        gen_num = 0
        done = False
        sentences_list = list()

        for dep in range(1, depth):
            sentences = generate(self.grammar, depth=dep)
            for s in sentences:
                sentences_list.append(' '.join(s) + '\n')
                gen_num += 1
                if gen_num > num:
                    done = True
                    break
            if done:
                break

        # sentences = generate(self.grammar, depth=depth, n=4)
        # for s in sentences:
        #     # file.write(' '.join(s) + '\n')
        #     sentences_list.append(' '.join(s) + '\n')
        # sentences_list = sentences_list[0:num]
        random.shuffle(sentences_list)
        with open(self.origin_file, 'w') as file:
            for s in sentences_list:
                file.write(s)

def gen_grammar3_past_plural(verb, direct_object, count):
	g1 ="""
	S -> W TR SUB V '?' | WA TR SUB V DO '?' 
	W -> 'who' | 'what' | 'when' | 'where' | 'why' | 'how'
	WA -> 'when' | 'where' | 'why' | 'how'
	TR -> 'have'
	SUB -> PRO
	PRO -> 'they' |'you'
	V -> '%s'
	DO -> 'the %s'
	"""%(verb, direct_object)
	grammar1 = CFG.fromstring(g1)
	multiplier = 0
	with open('sentences.csv', 'ab') as csvwriter:
		writer = csv.writer(csvwriter)
		for sentence in generate(grammar1, n=999):
			if sentence.find('who') == 0:
				multiplier = 1
			if sentence.find('what') == 0:
				multiplier = 1
			if sentence.find('when') == 0:
				multiplier = 2
			if sentence.find('where') == 0:
				multiplier = 2
			if sentence.find('why') == 0:
				multiplier = 4
			if sentence.find('how') == 0:
				multiplier = 4
			writer.writerow((' '.join(sentence) , multiplier*count))

def Tweet_content1():
  grammar = CFG.fromstring(demo_grammar)

  for sentence in generate(grammar, n=4): """generating sentence of 4 words depth"""
    print(' '.join(sentence))
    
    return sentence

def gen_grammar_plural(verb, direct_object, count):
	try:
		verb = en.verb.present_participle(verb)
	except KeyError:
		return
	if verb != "":
		g1 ="""
		S -> WA TR SUB V DO '?' | W TR SUB V '?' 
		W -> 'who' | 'what' | 'when' | 'where' | 'why' | 'how'
		WA -> 'when' | 'where' | 'why' | 'how'
		TR -> 'are' | 'were'
		SUB -> 'they' | 'you'
		V -> '%s'
		DO -> 'the %s'
		"""%(verb, direct_object)
		grammar1 = CFG.fromstring(g1)
		multiplier = 1
		with open('sentences.csv', 'ab') as csvwriter:
			writer = csv.writer(csvwriter)
			for sentence in generate(grammar1, n=999):
				sentence = ' '.join(sentence)
				if sentence.find('who') == 0:
					multiplier = 1
				if sentence.find('what') == 0:
					multiplier = 1
				if sentence.find('when') == 0:
					multiplier = 2
				if sentence.find('where') == 0:
					multiplier = 2
				if sentence.find('why') == 0:
					multiplier = 4
				if sentence.find('how') == 0:
					multiplier = 4
				writer.writerow((' '.join(sentence) , multiplier*count))

def generate_text(grammar,N):
    from nltk.grammar import CFG
    import nltk.parse.generate as gen

    print('Generating the first %d sentences for demo grammar:' % (N,))
    print(grammar)
    grammar = CFG.fromstring(grammar)

    grm_list = gen.generate(grammar, n=N)
    for n, sent in enumerate(grm_list):
        print('%3d. %s' % (n, ' '.join(sent)))

def respondQuestion(sentence, keyWord, POS):
	if "Tell me" not in sentence:
		grammar = ""

		if POS == "NNPS" or POS == "NNS":
			grammar = CFG.fromstring("""
			S -> H-NP1 Adj VP'?' | Wh-NP VP'?'
			H-NP1 -> 'How'
			Wh-NP -> 'Who' | 'What' | 'Where' | 'What'
			Adj -> 'big' | 'small' | 'happy' | 'sad' | 'large' | 'difficult' | 'emotional' | 'old' | 'healthy' | 'strong' | 'cute' | 'hungry'
			NP -> Pronoun | Proper-Noun | Noun
			Pronoun -> 'they' | 'those'
			Proper-Noun -> '[]'
			Noun -> 'the <>'
			VP -> Verb NP  
			Verb -> 'are' 
			""")
		elif POS == "NN" or "NNP":
			grammar = CFG.fromstring("""
			S -> H-NP1 Adj VP'?' | Wh-NP VP'?'
			H-NP1 -> 'How'
			Wh-NP -> 'Who' | 'What' | 'Where' | 'What'
			Adj -> 'big' | 'small' | 'happy' | 'sad' | 'large' | 'difficult' | 'emotional' | 'old' | 'healthy' | 'strong' | 'cute' | 'hungry'
			NP -> Pronoun | Proper-Noun | Noun
			Pronoun -> 'it' | 'that'
			Proper-Noun -> '[]'
			Noun -> 'the <>'
			VP -> Verb NP  
			Verb -> 'is' 
			""")

		rand_sent_list = []
                response = ""
		for sentence in generate(grammar):
		    rand_sent_list.append(' '.join(sentence))
		while True:
			num = randint(0, len(rand_sent_list)-1)
			response = rand_sent_list[num]
			if "<>" in response and (POS == "NNS" or POS == "NN"):
				index = response.index("<>")
				response = response[:index] + keyWord + response[index+2:]
				break
			if "[]" in response and (POS == "NNPS" or POS == "NNP"):
				index = response.index("[]")
				response = response[:index] + keyWord + response[index+2:]
				break
			if "<>" not in response and "[]" not in response:
				break
		return response
	else:
		knowledgeRep(sentence)

def generateRawTemplates(depth):
    gram = CFG.fromstring(grammarstring)
    rawTemplates = generate(gram, depth=depth)
    templatefiles = []

    for index, state in enumerate(rawTemplates):
        filename = os.path.join("./templates","template"+str(index))
        with open(filename, 'w') as templatefile:
            templatefile.write(' '.join(state))
            templatefiles.append(filename)

    print str(len(templatefiles))+" template files generated"

    return templatefiles

def generate_tweet(grammar):
    from nltk.grammar import CFG
    import nltk.parse.generate as gen

    print(grammar)
    grammar = CFG.fromstring(grammar)
    grm_list = gen.generate(grammar, n=SIZE) # TODO voir la taille max ? moyen de la recuperer ?
    from random import randint
    rd = randint(0,SIZE)
    cpt = 0
    for n, sent in enumerate(grm_list):
        if rd == cpt:
            print ("Your tweet : ")
            print('%3d. %s' % (n, ' '.join(sent)))
        cpt += 1

def main():
    zen = """ Beautiful is better than ugly.
    Explicit is better than implicit.
    Simple is better than complex.
    Complex is better than complicated.
    Flat is better than nested.
    Sparse is better than dense.
    Readability counts.
    Special cases aren't special enough to break the rules.
    Although practicality beats purity.
    Errors should never pass silently.
    Unless explicitly silenced.
    In the face of ambiguity, refuse the temptation to guess.
    There should be one-- and preferably only one --obvious way to do it.
    Although that way may not be obvious at first unless you're Dutch.
    Now is better than never.
    Although never is often better than *right* now.
    If the implementation is hard to explain, it's a bad idea.
    If the implementation is easy to explain, it may be a good idea.
    Namespaces are one honking great idea -- let's do more of those!"""
        
    tagged = nltk.pos_tag(nltk.word_tokenize(zen))
    tagged = [(tag, word) for word, tag in tagged]
    #
    #tag_word_map = defaultdict(list)
    #[(tag, word) for word, tag in tagged]
    tags = set([tag for tag, _  in tagged])
    tag_word_map = {tag: {word for key, word in tagged if key == tag} for tag in tags}
                
           
    gram_head = """
      S -> NNP VBZ JJR IN RB
    """
    cats = ['NNP', 'VBZ', 'JJR', 'IN', 'RB']
    gram = [cat + ' -> ' + '|'.join([repr(x) for x in tag_word_map[cat]]) for cat in cats]
    
    grammar = gram_head + '\n'.join(gram)
    grammar = nltk.CFG.fromstring(grammar)
    
    poem = []    
    for sentence2 in generate(grammar, depth=5):
        poem.append(' '.join(sentence2))
        
    out =  "\n".join(choice(poem, size=10))
    print(out)

import nltk
from nltk.parse import generate
from nltk.grammar import Nonterminal


cfg = nltk.CFG.fromstring("""
root -> who_player has the most runs
who_player -> who
who_player -> which player
who_player -> which team player
who -> 'who'
which -> 'which'
player -> 'player'
team -> 'indian' | 'australian' | 'england' | 'sri' 'lankan'
has -> 'has'
the -> 'the'
this -> 'this'
most -> 'most'
runs -> 'runs'
""")

print(list((n,sent) for n, sent in enumerate(generate.generate(cfg, n=100, start=Nonterminal('root')), 1)))

result1 = nltk.ChartParser(cfg).parse('which england player has the most runs'.split())
result2 = nltk.ChartParser(cfg).parse(['which', 'sri', 'lankan', 'player', 'has', 'the', 'most',  'runs'])
print(list(result1))
print(list(result2))

from nltk.parse.generate import generate
from nltk import CFG
from nltk.data import load

for gg in [ 'grammar_2.cfg']:
    grammar = load( 'file:' + gg)
    for  sentence in generate(grammar, depth=6, n=1000000):
        print(' '.join(sentence))

#.........这里部分代码省略.........
            # Create the grammar
            #P:prepositions, DET:articles, adverbs
            DET = ["'the'","'a'","'some'"]
            # P = ["'in'","'at'","'since'","'for'","'to'","'past'","'to'""'by'","'in'","'at'","'on'","'under'","'below'","'over'","'above'","'into'","'from'","'of'","'on'","'at'"]
            VB = ["'talks'","'does'","'has'","'cries'", "'fights'", "'traps'", "'bakes'", "'fondles'", "'cooks'", "'sees'", "'calls'", "'smells'", "'tastes'", "'hears'"]
            
            
            assignments = pos_tag(tokens) # tagset='universal' for ADJ, NOUN, etc.
            
            # pos_tags = []
            pos_words = {}
            pos_words['DET'] = DET
            #pos_words['P'] = P
            pos_words['VB'] = VB
            
            for tuple in assignments:
                word = tuple[0]
                pos = tuple[1]
                if pos in pos_words:
                    pos_words[pos].append("\'" + word + "\'")
                else:
                    pos_words[pos] = []
                    pos_words[pos].append("\'" + word + "\'")
                # pos_tags.append(pos)

            #grammar = """
            #S -> NP VP
            #PP -> P NP
            #NP -> Det N
            #VP -> V Det N | V Det N PP
            
            #"""
            
            grammar = """
            S -> NP VP
            NP -> Det N
            VP -> V Det N
            """
            #Det -> 'DT'
            # N -> 'NN'
            # V -> 'VBZ'
            # P -> 'PP'
            
            
            # adverb is RB
            
            if 'DET' in pos_words:
                grammar += 'Det ->' + ' | '.join(pos_words['DET']) + '\n'
                
            if 'P' in pos_words:
                grammar += 'P ->' + ' | '.join(pos_words['P']) + '\n'
                
            if 'NN' in pos_words:
                grammar += 'N ->' + ' | '.join(pos_words['NN']) + '\n'
            #change to VB for nltk
            if 'VB' in pos_words:
                grammar += 'V ->' + ' | '.join(pos_words['VB']) + '\n'
            
            
            #if 'JJ' in pos_words:
            #    grammar += 'A ->' + ' | '.join(pos_words['JJ']) + '\n'
                
            simple_grammar = CFG.fromstring(grammar)
            #  simple_grammar.start()
            # simple_grammar.productions()
            
            sentences = []
            sentence_validity = []
         
            for sentence in generate(simple_grammar, depth=4):
                sentences.append(' '.join(sentence))
            
            
            sentence_validity = get_validity(sentences)
            
            #get_validity(sentences)
            
            # parser = nltk.ChartParser(simple_grammar)
            # tree = parser.parse(pos_tags)
            
            story = ""
            for i in range(0, 10):
                tuple = sentence_validity[i]
                string = tuple[1]
                start_letter = string[0].upper()
                story += start_letter
                story += string[1:]
                story += ". "
            
            return render(request, 'makestory/output.html',
                {
                'imageURL_output': imageURL,
                'story_output': story,
                'grammar_test_output': simple_grammar,
                'sentences_test_output': sentences,
                }
            )
        else:
            return fail(request)
    return fail(request)

def choose_line(some_lines):#5
    return a_random.choice(#7
                    some_lines).lower() #5

############################################

############################################
choose = choose_line #5

g = G.fromstring(#7
                    this_is_the_grammar) #5
############################################

############################################
while not len(pentas):#5
    for poem in generate(g, #7
                           start=N('five')): #5
############################################

############################################
      pentas.append(#5
                    with_blank_spaces.join(poem))#7

fives = pentas #5
############################################

############################################
third = choose(fives) #5
first = choose(fives) #7

def display_the(poem):#5
############################################

    [1. if i == b else 0. for i in xrange(len(code_for))])

# list of codes of symbols to predict
to_predict_codes = [onehot(code_for[s]) for s in to_predict]


# function to test if a symbol code is in list to predict
def in_predict_codes(code):
    for i in xrange(len(to_predict_codes)):
        if ((code == to_predict_codes[i]).all()):
            return True
    return False


# sample_strings = all strings from grammar of depth at most sample_depth
sample_strings = list(generate(grammar, depth=sample_depth))

# report #, min length and max length for strings in sample_strings
print("number of sample strings = {}".format(len(sample_strings)))
sample_lengths = [len(s) for s in sample_strings]
print("min length = {}, max length = {}".format(min(sample_lengths),
                                                max(sample_lengths)))

# sanity check: report one random string from sample_strings
print "random sample string = {}".format(random.choice(sample_strings))

#################################

model = VanillaModel(len(code_for), READ_SIZE, len(code_for))
try:
    model.cuda()

from nltk.parse.generate import generate #, demo_grammar
from nltk import CFG


demo_grammar = """
  S -> NP VP
  NP -> Det N
  PP -> P NP
  VP -> 'slept' | 'saw' NP | 'walked' PP
  Det -> 'the' | 'a'
  N -> 'man' | 'park' | 'dog'
  P -> 'in' | 'with'
"""
grammar = CFG.fromstring(demo_grammar)
print(grammar)


#Join words and generate based off of grammar - for n 
for sentence in generate(grammar, n=12):
    print(' '.join(sentence))

'''
Notes: 
Need to symbolize the grammar
Have the machine process the language
Need to integrate with Markov chain - file 'agiliq-markov.py'
'''
for sentence in generate(grammar, depth=4):
    print(' '.join(sentence))