def as_tuples(strs): res = [] for line in strs: page_nos = [int(x) for x in words(line)] for link in group2(page_nos): res += [link] return res
def frequency_count(filename): word_count = Counter() with open(filename) as inp: for line in inp: for word in words(line): word_count[word] += 1 return word_count
def index_of_words(filename): index = defaultdict(list) with open(filename) as inp: i = 0 for line in inp: for word in words(line): i += 1 index[word] += [i] return index
def main(): filename = '/usr/share/dict/words' words_list = [] with open(filename) as inp: for line in inp: words_list += words(line) reversed_words = reverse_strings(words_list) res = reverse_strings(sorted(reversed_words)) for word in res: print(word)
def evaluate(string): operand_stack = LinkedStack() operator_stack = LinkedStack() tokens = (tok.strip() for tok in words(string)) for tok in tokens: if is_operator(tok): operator_stack.push(tok) elif tok == ')': evaluate_single(operand_stack, operator_stack) else: operand_stack.push(tok) print(operand_stack)
def index_of_words_(filename): index = BinarySearchTree() with open(filename) as inp: i = 0 for line in inp: for word in words(line): i += 1 if word in index: index[word] = index[word] + [i] else: index[word] = [i] return index
def main(): corrections = {} with open('../misspellings.txt') as misspellings_corrrections: for line in misspellings_corrrections: misspelling, correct = split_line(line) corrections[misspelling] = correct for line in stdin: for word in words(line): if word in corrections: print(corrections[word]) else: print(word)
def readFloatMatrixOrVector(): dimens = words(readStringArray(1)[0]) dimens = [int(n) for n in dimens] if len(dimens) == 1: line = readStringArray(1)[0] return line_as_floats(line) [nb_row, nb_col] = dimens array = readStringArray(nb_row) res = [] for row in array: res += [line_as_floats(row)] return res
def infix_to_postfix(string): operand_stack = LinkedStack() operator_stack = LinkedStack() tokens = (tok.strip() for tok in words(string)) for tok in tokens: print(operator_stack) print(operand_stack) if tok == '(': continue # operand_stack.push(tok) elif is_operator(tok): operator_stack.push(tok) elif tok == ')': b, a = operand_stack.pop(), operand_stack.pop() op = operator_stack.pop() # res = '[' + a + ' ' + b + op + ']' res = a + ' ' + b + ' ' + op operand_stack.push(res) else: operand_stack.push(tok) print(operand_stack)
q = Queue() q.enqueue(val) queue.enqueue(q) while len(queue) > 1: q1 = queue.dequeue() q2 = queue.dequeue() queue.enqueue(merge(q1, q2)) return tuple(queue.dequeue()) if __name__ == "__main__": a = Queue() a.enqueue(1) a.enqueue(2) a.enqueue(4) b = Queue() b.enqueue(2) b.enqueue(5) b.enqueue(6) print(merge(a, b)) a = [random.randrange(10) for i in range(100)] print(merge_sort(a)) filename = sys.argv[1] with open(filename) as lines: wordslist = [word for line in lines for word in words(line)] print(merge_sort(wordslist))
import sys from distance import squared_distance from ioutils import read_strings from strutils import words if __name__ == "__main__": x = float(sys.argv[1]) y = float(sys.argv[2]) z = float(sys.argv[3]) array = read_strings() res = [] def closest(x, y, z, v1, v2): if squared_distance([x, y, z], v1) < squared_distance([x, y, z], v2): return v1 return v2 for line in array: [xi, yi, zi] = words(line)[0:3] [xi, yi, zi] = [float(xi), float(yi), float(zi)] if res == []: res = [xi, yi, zi] else: res = closest(x, y, z, res, [xi, yi, xi]) print(res)
import sys import re from strutils import words from array_utils import shannon_entropy_list filename = sys.argv[1] with open(filename) as corpus: wordlist = [] for line in corpus: for word in words(line): word = word.lower() word = re.sub(r'[^a-z]', '', word) wordlist += [word] print(shannon_entropy_list(wordlist))
def line_as_floats(line): return [float(x) for x in words(line)]
from ioutils import read_strings from strutils import words if __name__ == "__main__": array = read_strings() for line in array: words_array = words(line) name = ' '.join(words_array[0:-2]) a = int(words_array[-2]) b = int(words_array[-1]) res = a / b print('%25s' % name, '%3d' % a, '%3d' % b, '%3.3f' % res)
from ioutils import read_strings from strutils import words array = read_strings() mtot = 0 mxtot = 0 mytot = 0 for line in array: [m, x, y] = words(line)[0:3] m, x, y = float(m), float(x), float(y) mtot += m mxtot += (m * x) mytot += (m * y) print(mxtot / mtot, mytot / mtot)
def main(): lexicon = build_lexicon('../words.utf-8.txt') for line in stdin: for word in words(line): if word not in lexicon: print(word)