def load_all(dataset_dir, doc_ids=None, filter_types=None, filter_senses=None):
"""Load whole CoNLL16st dataset by document id."""
# load all provided files untouched
parses = load_parses(dataset_dir, doc_ids=doc_ids)
doc_ids = sorted(parses.keys())
raws = load_raws(dataset_dir, doc_ids=doc_ids)
relations_gold = load_relations_gold(dataset_dir, doc_ids=doc_ids, with_senses=True, filter_types=filter_types, filter_senses=filter_senses)
if relations_gold:
relationsnos_gold = relations_gold
else:
relationsnos_gold = load_relations_gold(dataset_dir, doc_ids=doc_ids, with_senses=False, filter_types=filter_types, filter_senses=filter_senses)
# extract data by document id and token id
words = get_words(parses)
pos_tags = get_pos_tags(parses)
word_metas = get_word_metas(parses, raws)
# extract data by document id and token id pairs
dependencies = get_dependencies(parses)
# extract data by document id
parsetrees = get_parsetrees(parses)
# extract data by relation id
rel_parts = get_rel_parts(relationsnos_gold)
rel_ids = sorted(rel_parts.keys())
rel_types = get_rel_types(relations_gold)
rel_senses = get_rel_senses(relations_gold)
# add extra fields
add_relation_tags(word_metas, rel_types, rel_senses)
return doc_ids, words, word_metas, pos_tags, dependencies, parsetrees, rel_ids, rel_parts, rel_types, rel_senses, relations_gold
def extract_svm_features(vidx, data):
x = scipy.sparse.lil_matrix((len(data), len(vidx)))
for i in range(len(data.BodyMarkdown)):
for w in get_words(data.BodyMarkdown[i]):
if w in vidx:
x[i, vidx[w]] = 1.0
return scipy.sparse.csr_matrix(x)
def extract_words_from_row(row):
"""
This function turns a given row of data for this particular type
of problem into a simple vector of words.
"""
title = row["Title"]
body = row["BodyMarkdown"]
tags = " ".join(filter(istag, [row["Tag%d" % t] for t in range(1, 6)]))
postid = row["PostId"]
text = " ".join([title, body, tags])
return get_words(text)
def get_svm_word_indices(vidx, text):
x = np.zeros(len(vidx), dtype=numpy.double)
for w in get_words(text):
if w in vidx:
x[vidx[w]] = 1.0
return scipy.sparse.csr_matrix(x)
#filename = 'scan\\Jablanica0096_crop.tif' #filename = 'scan\\paragraph_635.tif' #filename = 'scan\\problem_italic.tif' #filename = 'scan\\paragraph_265.tif' #filename = 'scan\\test1.tif' #filename = 'scan\\Dubrovnik0018_crop.tif' #filename = 'scan\\Jablanica0096_crop.tif' #filename = 'scan\\JuznaSrbija0052_crop.tif' #filename = 'scan\\Piva0015_crop.tif' #filename = 'scan\\Proscenje0064_crop.tif' #filename = 'scan\\Uskoci0080_crop.tif' #filename = 'scan\\Vasojevici0033_crop.tif' #filename = 'scan\\line_165.tif' #filename = 'scan\\line_177.tif' filename = 'scan\\Vasojevici0033_crop.tif' cl.clean_all() wp.get_words(filename) el.extract_letters(filename) rl.replace_diacritics(filename) cmp.compare(filename, 'initial') script_end = datetime.datetime.now() print(script_end - script_start)
import os
import words
clear = lambda: os.system("cls" if os.name == "nt" else "clear")
secret_word = list(words.get_words())
hangman_word = ["___" for letter in secret_word]
wrong_guesses = []
num_guesses = 10
while num_guesses > 0 and hangman_word != secret_word:
print(" ".join(hangman_word))
print(f"Du har {num_guesses} forsøk igjen.")
print("\nDu har brukt: " + " ".join(wrong_guesses))
guessed_letter = input("Guess a letter: ").lower()
if (guessed_letter in hangman_word) or (guessed_letter in wrong_guesses):
continue
for index, letter in enumerate(secret_word):
if guessed_letter == letter:
hangman_word[index] = guessed_letter
if guessed_letter not in secret_word:
wrong_guesses.append(guessed_letter)
num_guesses -= 1
clear()
if hangman_word == secret_word:
#See more at https://www.geeksforgeeks.org/python-program-to-print-emojis/
import words
print(words.get_words())
# grinning face
print("\U0001f600")
# grimacing face
print("\N{grimacing face}")
print("😢")
# grinning squinting face
print("\U0001F606")
# rolling on the floor laughing
print("\U0001F923") \
#face with rolling eyes
print("\N{face with rolling eyes}")
print(u"\U0001F97A")
