Commit fd22427b authored by Mathieu Valois's avatar Mathieu Valois
Browse files

Some benchmarks

parent e60eb311

distances.py

+13 −4
Original line number Diff line number Diff line
@@ -45,6 +45,7 @@ class Robustness: 
		yield w0



		for i in range(1, d):

			before = time.time()

			lowest_distance = self.distance(w0, self.l[i])

			lowest_index = i

			for j in range(i+1, d):
@@ -53,9 +54,11 @@ class Robustness: 
					lowest_distance = dist

					lowest_index = j

			self.swap(i, j)

			after = time.time()

			print("Found the %dth closest word in %d seconds" % (i, after-before))

			yield self.l[i]



	def closest_among_m_permutation(self, m=10):

	def closest_word_among(self, m=10):

		"""

		generates a permutation where w_0 is randomly choosen and w_n+1

		is the closest neighbor of w_n among m randomly choosen words.
@@ -70,6 +73,7 @@ class Robustness: 
		# select all the remaining ones

		for i in range(1, d):

			# pick the closest one among m random ones

			before = time.time()

			i_n = random.randint(i, d-1)

			w_n = self.l[i_n]

			lowest_distance = self.distance(w0, w_n)
@@ -82,6 +86,8 @@ class Robustness: 
					lowest_distance = dist

					lowest_index = i_n

			self.swap(i, lowest_index)

			after = time.time()

			print("Found the %dth closest word in " %i, after-before, "seconds")

			yield self.l[i]



	def cost_rate(self):
@@ -133,8 +139,11 @@ class Robustness: 
			print(w, after-before)



if __name__ == '__main__':

	before = time.time()

	R = Robustness(sys.argv[1])

	R.algo = R.closest_word

	# R.distance = jaro.jaro_winkler_metric

	# R.k = int(len(R.l)/10)

	after = time.time()

	print("File loaded in %d seconds" % (after-before))

	R.algo = R.closest_word_among

	# R.k = int(len(R.l)/10**7)

	print(R.k)

	print(R.min_cost(n=10))