import timeit
from bktree import BKTree
business_dictionary = [a.strip() for a in open('business-names.txt')]
tree = BKTree(sanitize=True)
tree.add(business_dictionary)
setup = """
from bktree import BKTree
business_dictionary = [a.strip() for a in open('business-names.txt')]
tree = BKTree(sanitize=True)
tree.add(business_dictionary)
"""
def test_word(word, radius):
perf = timeit.timeit(f'tree.search("{word}", {radius})',
number=100,
setup=setup)
print(f'Performance of tree.search("{word}", {radius}) = {perf}')
print(tree.search(f"{word}", 1))
if __name__ == "__main__":
for w, r in [
('walmart', 1),
('walmartt', 1),
('walmarttt', 2),
('walllrt', 2),
str1 += "v" + str(vertex)
features[i][str1] = qualityEdges[i][j]
values = [build_by_features(features[i]) for i in range(l)]
valuesRevDict = {}
for i in range(len(values)):
if values[i] in valuesRevDict:
valuesRevDict[values[i]].append(i)
else:
valuesRevDict[values[i]] = [i]
tree = BKTree()
for value in values:
tree.add(value)
# for i in range(l):
# for j in range(i+1,l):
# score = computeScore(values[i], values[j])
# print str(graphs[i]["label"]) + " " + str(graphs[j]["label"]) + " " + str(score)
for i in range(l):
closest_pairs = tree.find(values[i], MAX_DISTANCE)
final_pairs = []
for pair in closest_pairs:
a, b = pair
a = 1 - float(a) / F
b = valuesRevDict[b]
final_pairs.append((a, b))
print str(i) + " " + str(final_pairs)