def generate_phrase(self):
random_length = randrange(self.min_words, self.max_words + 1)
# filtered_words = [w for w in words if en.is_noun(w)] #filter nouns
selection = []
for i in range(random_length):
word = choice(self.blackboard.pool.nouns)
selection.append(word)
return en.quantify(selection) # make enumeration
def lookAround(self):
"""Print a description of the scene location, including a list
of all the items it contains."""
readable = termToReadable(self.location)
print("You are in a {}.".format(readable), end=" ")
describeLocation(self.location)
item_names = [termToReadable(x) for x in self.items]
print("There's {} in the {}.".format(en.quantify(item_names),
readable))
def test_quantify(self):
# Assert quantification algorithm.
for a, s in (
( 2 * ["carrot"], "a pair of carrots"),
( 4 * ["carrot"], "several carrots"),
( 9 * ["carrot"], "a number of carrots"),
( 19 * ["carrot"], "a score of carrots"),
( 23 * ["carrot"], "dozens of carrots"),
( 201 * ["carrot"], "hundreds of carrots"),
(1001 * ["carrot"], "thousands of carrots"),
({"carrot": 4, "parrot": 2}, "several carrots and a pair of parrots")):
self.assertEqual(en.quantify(a), s)
print("pattern.en.quantify()")
def test_quantify(self):
# Assert quantification algorithm.
for a, s in (
( 2 * ["carrot"], "a pair of carrots"),
( 4 * ["carrot"], "several carrots"),
( 9 * ["carrot"], "a number of carrots"),
( 19 * ["carrot"], "a score of carrots"),
( 23 * ["carrot"], "dozens of carrots"),
( 201 * ["carrot"], "hundreds of carrots"),
(1001 * ["carrot"], "thousands of carrots"),
({"carrot": 4, "parrot": 2}, "several carrots and a pair of parrots")):
self.assertEqual(en.quantify(a), s)
print "pattern.en.quantify()"
def random_imperative(noun=None, get_related=True, verb=None, adj=None):
if noun:
n = get_related_or_not(noun, True, 'NN') if get_related else noun
else:
n = random.choice(NOUNS)
if verb:
v = get_related_or_not(verb, True, 'VB')
if v is None:
v = verb
else:
v = random.choice(VERBS)
if not adj:
adj = random.choice(ADJS) if coin_flip(0.5) else ''
c = ''
if coin_flip(0.7):
n = pluralize(n)
c = random.choice(C2)
else:
i = random.randint(1, 5)
n = quantify(adj + ' ' + n, amount=i)
adj = ''
if coin_flip(0.25):
a = ''
v = conjugate(v)
elif coin_flip(0.33):
v = conjugate(v, 'part') # present participle
a = random.choice(A1)
c = random.choice(C)
elif coin_flip(0.5):
v = conjugate(v)
a = random.choice(A2)
else:
v = conjugate(v)
a = random.choice(A3)
phrase = '{0} {1} {2} {3} {4}'.format(a, v, c, adj, n)
phrase = phrase[1:] if phrase.startswith(' ') else phrase
return re.sub(' +', ' ', phrase)
from pattern.en import suggest
print(suggest("Fracture"))
# ### Working with Numbers
from pattern.en import number, numerals
print(number("one hundred and twenty two"))
print(numerals(256.390, round=2))
from pattern.en import quantify
print(
quantify([
'apple', 'apple', 'apple', 'banana', 'banana', 'banana', 'mango',
'mango'
]))
from pattern.en import quantify
print(quantify({'strawberry': 200, 'peach': 15}))
print(quantify('orange', amount=1200))
# ## Pattern Library Functions for Data Mining
# For macOS SSL issue when downloading file(s) from external sources
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
# ### Accessing Web Pages
# The number() command returns an int or float from a written representation.
# This is useful, for example, in combination with a parser
# to transform "CD" parts-of-speech to actual numbers.
# The algorithm ignores words that aren't recognized as numerals.
print(number("two thousand five hundred and eight"))
print(number("two point eighty-five"))
print("")
# The numerals() command returns a written representation from an int or float.
print(numerals(1.249, round=2))
print(numerals(1.249, round=3))
print("")
# The quantify() commands uses pluralization + approximation to enumerate words.
# This is useful to generate a human-readable summary of a set of strings.
print(quantify(["goose", "goose", "duck", "chicken", "chicken", "chicken"]))
print(quantify(["penguin", "polar bear"]))
print(quantify(["carrot"] * 1000))
print(quantify("parrot", amount=1000))
print(quantify({"carrot": 100, "parrot": 20}))
print("")
# The quantify() command only works with words (strings).
# To quantify a set of Python objects, use reflect().
# This will first create a human-readable name for each object and then quantify these.
print(reflect([0, 1, {}, False, reflect]))
print(reflect(os.path))
print(reflect([False, True], quantify=False))
print(quantify(["bunny rabbit"] + reflect([False, True], quantify=False)))
#singularity
print pluralize('child')
print singularize('wolves')
#
print
print lexeme('run')
print lemma('running')
print conjugate('purred', '3sg')
print PAST in tenses('purred') # 'p' in tenses() also works.
print (PAST, 1, PL) in tenses('purred')
print 'Quantification'
print quantify(['goose', 'goose', 'duck', 'chicken', 'chicken', 'chicken'])
print quantify('carrot', amount=90)
print quantify({'carrot': 100, 'parrot': 20})
print 'ngrams'
print ngrams("I am eating a pizza.", n=2)
#parse
s = parse('I eat pizza with a fork.')
pprint(s)
#tag
for word, t in tag('The cat felt happy.'):
print word +' is ' +t
# The number() command returns an int or float from a written representation.
# This is useful, for example, in combination with a parser
# to transform "CD" parts-of-speech to actual numbers.
# The algorithm ignores words that aren't recognized as numerals.
print number("two thousand five hundred and eight")
print number("two point eighty-five")
print
# The numerals() command returns a written representation from an int or float.
print numerals(1.249, round=2)
print numerals(1.249, round=3)
print
# The quantify() commands uses pluralization + approximation to enumerate words.
# This is useful to generate a human-readable summary of a set of strings.
print quantify(["goose", "goose", "duck", "chicken", "chicken", "chicken"])
print quantify(["penguin", "polar bear"])
print quantify(["carrot"] * 1000)
print quantify("parrot", amount=1000)
print quantify({"carrot": 100, "parrot": 20})
print
# The quantify() command only works with words (strings).
# To quantify a set of Python objects, use reflect().
# This will first create a human-readable name for each object and then quantify these.
print reflect([0, 1, {}, False, reflect])
print reflect(os.path)
print reflect([False, True], quantify=False)
print quantify(
["bunny rabbit"] + \
reflect([False, True], quantify=False))
from pattern.de import gender, MALE, FEMALE, NEUTRAL
print(gender('Katze'))
print(gender('Mesa'))
from pattern.en import verbs, conjugate, PARTICIPLE
print('google') in verbs.infinitives
print('googled') in verbs.inflections
print(conjugate('googled', tense=PARTICIPLE, parse=False))
print(conjugate('googled', tense=PARTICIPLE, parse=True))
from pattern.en import quantify
print(quantify(['goose', 'goose', 'duck', 'chicken', 'chicken', 'chicken']))
print(quantify({'carrot': 100, 'parrot': 20}))
print(quantify('carrot', amount=1000))
from pattern.en import quantify
print(quantify(['goose', 'goose', 'duck', 'chicken', 'chicken', 'chicken']))
print(quantify({'carrot': 100, 'parrot': 20}))
print(quantify('carrot', amount=1000))
from pattern.en import ngrams
print(ngrams("I am eating pizza.", n=2)) # bigrams
from pattern.en import parse
print(parse('I ate pizza.').split())
print(suggest("Heroi"))
print(suggest("Whitle"))
#In the script above we have a word Whitle which is incorrectly spelled. In the output, you will see possible suggestions for this word.
#According to the suggest method, there is a 0.64 probability that the word is "While", similarly there is a probability of 0.29 that the word is "White", and so on.
print(suggest("Fracture"))
#From the output, you can see that there is a 100% chance that the word is spelled correctly.
#%%% Quantify
#Quantify function is used to provide a word count estimation of the words given.
#quantify function is used to get a word count estimation of the items in the list, which provides a phrase for referring to the group. If a list has 3-8 similar items, the quantify function will quantify it to "several". Two items are quantified to a "couple".
from pattern.en import quantify
print(
quantify([
'apple', 'apple', 'apple', 'banana', 'banana', 'banana', 'mango',
'mango'
]))
#In the list, we have three apples, three bananas, and two mangoes. The output of the quantify function for this list looks like this:
#demonstrates the other word count estimations.
from pattern.en import quantify
print(quantify({'strawberry': 200, 'peach': 15}))
print(quantify('orange', amount=1200))
from pattern.en import quantify
a = quantify([
'Pencil', 'Pencil', 'Eraser', 'Sharpener', 'Sharpener', 'Sharpener',
'Scale', 'Compass'
])
a
def assemble():
# actually make the thing
global credits
credits = {
'nouns':[],
'houses':[],
'characters':[],
'concepts':[],
'raw_txt':'',
'chapter_count':7,
'chapter_titles':[],
'character_icons':[]
}
page_counter = 6
# first, make the chapters
animals = pycorpora.get_file("animals","common")['animals']
for chapter_counter in range(credits['chapter_count']):
result = 0
while (result == 0):
animal = random.randrange(0,len(animals))
result = stack(animals[animal], 55)
del animals[animal]
a_chapter = prepare_chapter(result,int(page_counter) + 2,int(chapter_counter) + 1)
page_counter = a_chapter
# to make a chapter
# pick an animal to stack
# make sure it created a valid set
# prepare_chapter should return a number, the next chapter should start two pages after, so 10 + 2 = 12, e.g.
# prepare the frontmatter
# 1r = frontcover
# 2l = blank
# 3r = title page
# 4l = dedication
# 5r = toc
# 6l = blank
# 7r = introduction
# 8l = blank, chapter 1 page 0
booktitle = book_title()
print "This book is called " + booktitle
tpl("templates/frontcover.html","pages/00001r.html",[("book_title",booktitle)])
# blank page
tpl("templates/template.html","pages/00002l.html",[("","")])
# title page
tpl("templates/titlepage.html","pages/00003r.html",[("book_title",booktitle)])
# dedication page
kid_icons = '<div id="kids">'
for kid in ["Cecily","Daniel","Serena","Wendy"]:
a_kid = re.sub(r"style=\".+?\"","",get_icon(kid,"333333"))
kid_icons += a_kid
kid_icons += "</div>"
tpl("templates/dedication.html","pages/00004l.html",[("kids",kid_icons)])
# toc -- this one has to be a bit more manual
toc = ''
for ch in range(len(credits['chapter_titles'])):
toc_string = '<div class="toc-entry"><span>Chapter ' + str(ch + 1) + '</span><span>' + credits['chapter_titles'][ch][0] + '</span><span>' + str(credits['chapter_titles'][ch][1] - 8) + '</span></div>'
toc += toc_string
toc += '<div class="toc-entry"><span> </span><span>Credits</span><span>' + str(int(page_counter) - 3) + '</span></div>'
tpl("templates/toc.html","pages/00005r.html",[("toc",toc)])
# blank page
tpl("templates/template.html","pages/00006l.html",[("","")])
# introduction
housecount = quantify("house",amount=len(credits['chapter_titles']))
peoplecount = quantify("person",amount=len(credits['characters']))
tpl("templates/preface.html","pages/00007r.html",[("house_count",housecount),("people_count",peoplecount),("character_names", ", ".join(list(credits['characters']))),("word_count",str(len(re.compile(r" +").split(credits['raw_txt']))))])
# make a The End
tpl("templates/last_page.html","pages/" + str(int(page_counter) + 2).zfill(5) + ".html",[("character_names", ", ".join(list(credits['characters'])))])
tpl("templates/the_end.html","pages/" + str(int(page_counter) + 3).zfill(5) + ".html",[("character_icons"," ".join(list(credits['character_icons'])))])
# make the credits
make_credits(credits,str(int(page_counter) + 2))
print "Generation complete"
def book_title ():
global credits
people = list(credits['characters'])
people[-1] = "and " + people[-1]
return "The " + quantify("house",amount=len(credits['chapter_titles'])) + " of " + ", ".join(people)
#singularity
print pluralize('child')
print singularize('wolves')
#
print
print lexeme('run')
print lemma('running')
print conjugate('purred', '3sg')
print PAST in tenses('purred') # 'p' in tenses() also works.
print(PAST, 1, PL) in tenses('purred')
print 'Quantification'
print quantify(['goose', 'goose', 'duck', 'chicken', 'chicken', 'chicken'])
print quantify('carrot', amount=90)
print quantify({'carrot': 100, 'parrot': 20})
print 'ngrams'
print ngrams("I am eating a pizza.", n=2)
#parse
s = parse('I eat pizza with a fork.')
pprint(s)
#tag
for word, t in tag('The cat felt happy.'):
print word + ' is ' + t
s = "The movie attempts to be surreal by incorporating various time paradoxes, but it's presented in such a ridiculous way it's seriously boring."