def test():
points, cluster_ids, centers = make_blobs(n_samples=num_samples,
centers=num_clusters,
n_features=num_features,
center_box=(0, 100),
cluster_std=cluster_std_dev,
return_centers=True,
random_state=4)
data = list(map(tuple, points))
print(data)
# get num_set data points belonging to cluster#1
random.seed(1)
cluster1Indices = [
index for index, val in enumerate(cluster_ids) if val == 1
]
subset1 = random.sample(cluster1Indices, num_set)
set1 = set(subset1[:-1])
dataArray = np.array(data)
print("Instantiating...")
obj1 = ClusteredFunction(n=num_samples,
mode="multi",
f_name="GraphCut",
metric='euclidean',
data=dataArray,
num_clusters=num_internal_clusters,
cluster_lab=cluster_ids.tolist())
print("Instantiated")
eval1 = obj1.evaluate(set1)
print("Instantiating...")
obj2 = ClusteredFunction(n=num_samples,
mode="single",
f_name="GraphCut",
metric='euclidean',
data=dataArray,
num_clusters=num_internal_clusters,
cluster_lab=cluster_ids.tolist())
print("Instantiated")
eval2 = obj2.evaluate(set1)
print("Eval1: ", eval1)
print("Eval2: ", eval2)
def test():
points, cluster_ids, centers = make_blobs(n_samples=num_samples,
centers=num_clusters,
n_features=num_features,
center_box=(0, 100),
cluster_std=cluster_std_dev,
return_centers=True,
random_state=4)
data = list(map(tuple, points))
print(data)
# get num_set data points belonging to cluster#1
random.seed(1)
cluster1Indices = [
index for index, val in enumerate(cluster_ids) if val == 1
]
subset1 = random.sample(cluster1Indices, num_set)
set1 = set(subset1[:-1])
dataArray = np.array(data)
# obj = DisparitySumFunction(n=num_samples, mode="sparse", data=dataArray, metric=metric, num_neighbors=num_sparse_neighbors)
# obj = FeatureBasedFunction(n=num_samples, features=data, numFeatures=num_features, sparse=False)
#obj = GraphCutFunction(n=num_samples, mode="sparse", data=dataArray, metric=metric, num_neighbors=num_sparse_neighbors)
print("Instantiating...")
obj = ClusteredFunction(n=num_samples,
mode="multi",
f_name="DisparitySum",
metric='euclidean',
data=dataArray,
num_clusters=num_internal_clusters)
print("Instantiated")
groundSet = obj.getEffectiveGroundSet()
eval = obj.evaluate(groundSet)
print(f"Eval on groundset = {eval}")
elems = random.sample(set1, num_random)
subset = set(elems[:-1])
elem = elems[-1]
print(f"Setting memoization for {subset}")
obj.setMemoization(subset)
zeroEval = obj.evaluate(subset)
print(f"evaluate(subset) = {zeroEval}")
firstEval = obj.evaluateWithMemoization(subset)
print(f"evaluateWithMemoization(subset) = {firstEval}")
print(f"Element to be added is {elem}")
subset.add(elem)
secondEval = obj.evaluate(subset)
print(f"evaluate(subset++) = {secondEval}")
naiveGain = secondEval - firstEval
print("naiveGain:", naiveGain)
subset.remove(elem)
simpleGain = obj.marginalGain(subset, elem)
print(f"gain(subset,elem) = {simpleGain}")
fastGain = obj.marginalGainWithMemoization(subset, elem)
print(f"gainFast(subset,elem) = {fastGain}")
def test():
num_clusters = 3
cluster_std_dev = 1
num_samples = 8
num_set = 3
budget = 4
points, cluster_ids, centers = make_blobs(n_samples=num_samples, centers=num_clusters, n_features=2, cluster_std=cluster_std_dev, center_box=(0,100), return_centers=True, random_state=4)
data = list(map(tuple, points))
xs = [x[0] for x in data]
ys = [x[1] for x in data]
# get num_set data points belonging to cluster#1
random.seed(1)
cluster1Indices = [index for index, val in enumerate(cluster_ids) if val == 1]
subset1 = random.sample(cluster1Indices, num_set)
subset1xs = [xs[x] for x in subset1]
subset1ys = [ys[x] for x in subset1]
# plt.scatter(xs, ys, s=25, color='black', label="Images")
# plt.scatter(subset1xs, subset1ys, s=25, color='red', label="Subset1")
# plt.show()
set1 = set(subset1[:-1])
# get num_set data points belonging to different clusters
subset2 = []
for i in range(num_set):
#find the index of first point that belongs to cluster i
diverse_index = cluster_ids.tolist().index(i)
subset2.append(diverse_index)
subset2xs = [xs[x] for x in subset2]
subset2ys = [ys[x] for x in subset2]
# plt.scatter(xs, ys, s=25, color='black', label="Images")
# plt.scatter(subset2xs, subset2ys, s=25, color='red', label="Subset2")
# plt.show()
set2 = set(subset2[:-1])
dataArray = np.array(data)
from submodlib.functions.facilityLocation import FacilityLocationFunction
# start = time.process_time()
obj5 = FacilityLocationFunction(n=num_samples, data=dataArray, mode="clustered", metric="euclidean", num_clusters=num_clusters)
# print(f"Time taken by instantiation = {time.process_time() - start}")
print(f"Subset 1's FL value = {obj5.evaluate(set1)}")
print(f"Subset 2's FL value = {obj5.evaluate(set2)}")
print(f"Gain of adding another point ({subset1[-1]}) of same cluster to {set1} = {obj5.marginalGain(set1, subset1[-1])}")
print(f"Gain of adding another point ({subset2[-1]}) of different cluster to {set1} = {obj5.marginalGain(set1, subset2[-1])}")
obj5.setMemoization(set1)
print(f"Subset 1's Fast FL value = {obj5.evaluateWithMemoization(set1)}")
print(f"Fast gain of adding another point ({subset1[-1]}) of same cluster to {set1} = {obj5.marginalGainWithMemoization(set1, subset1[-1])}")
# start = time.process_time()
greedyList = obj5.maximize(budget=budget,optimizer='NaiveGreedy', stopIfZeroGain=False, stopIfNegativeGain=False, verbose=False)
print(f"Greedy vector: {greedyList}")
# print(f"Time taken by maximization = {time.process_time() - start}")
# greedyXs = [xs[x[0]] for x in greedyList]
# greedyYs = [ys[x[0]] for x in greedyList]
# plt.scatter(xs, ys, s=25, color='black', label="Images")
# plt.scatter(greedyXs, greedyYs, s=25, color='blue', label="Greedy Set")
from submodlib import ClusteredFunction
obj7 = ClusteredFunction(n=num_samples, mode="multi", f_name='FacilityLocation', metric='euclidean', data=dataArray, num_clusters=num_clusters)
# print(f"Time taken by instantiation = {time.process_time() - start}")
print(f"Subset 1's FL value = {obj7.evaluate(set1)}")
print(f"Subset 2's FL value = {obj7.evaluate(set2)}")
print(f"Gain of adding another point ({subset1[-1]}) of same cluster to {set1} = {obj7.marginalGain(set1, subset1[-1])}")
print(f"Gain of adding another point ({subset2[-1]}) of different cluster to {set1} = {obj7.marginalGain(set1, subset2[-1])}")
obj7.setMemoization(set1)
print(f"Subset 1's Fast FL value = {obj7.evaluateWithMemoization(set1)}")
print(f"Fast gain of adding another point ({subset1[-1]}) of same cluster to {set1} = {obj7.marginalGainWithMemoization(set1, subset1[-1])}")
# start = time.process_time()
greedyList = obj7.maximize(budget=budget,optimizer='NaiveGreedy', stopIfZeroGain=False, stopIfNegativeGain=False, verbose=False)
print(f"Greedy vector: {greedyList}")
[2,20,6, 2000],
[12,20,68, 200]
])
'''
data = np.array([(4.5, 13.5), (5, 13.5), (5.5, 13.5), (14.5, 13.5), (15, 13.5),
(15.5, 13.5), (4.5, 13), (5, 13), (5.5, 13), (14.5, 13),
(15, 13), (15.5, 13), (4.5, 12.5), (5, 12.5), (5.5, 12.5),
(14.5, 12.5), (15, 12.5), (15.5, 12.5), (4.5, 7.5), (5, 7.5),
(5.5, 7.5), (14.5, 7.5), (15, 7.5), (15.5, 7.5), (4.5, 7),
(5, 7), (5.5, 7), (14.5, 7), (15, 7), (15.5, 7), (4.5, 6.5),
(5, 6.5), (5.5, 6.5), (14.5, 6.5), (15, 6.5), (15.5, 6.5),
(7.5, 10), (12.5, 10), (10, 12.5), (10, 7.5), (4.5, 15.5),
(5, 9.5), (5, 10.5)])
#a, b, c = create_cluster(data.tolist(), 'euclidean', num_cluster = 2)
#print(a)
#print(c)
#print(b)
#obj = ClusteredFunction(43, 'FacilityLocation', a, b, c)
obj = ClusteredFunction(n=43, f_name='FacilityLocation', data=data)
X = {1, 23, 4}
print(obj.evaluate(X))
X = {1, 23, 4}
print(obj.marginalGain(X, 0))
#print(obj.maximize('NaiveGreedy', 10, False, False, False))
print(obj.maximize(10, 'NaiveGreedy', False, False, False))
def create_fl_clustered_user_single():
return ClusteredFunction(n=num_samples, mode="multi", f_name='FacilityLocation', data=dataArray, metric="euclidean", num_clusters=num_clusters, cluster_lab=cluster_ids.tolist())
def create_fl_clustered_birch_single():
return ClusteredFunction(n=num_samples, mode="single", f_name='FacilityLocation', data=dataArray, metric="euclidean", num_clusters=num_clusters)
def fl_clustered_user_single():
obj = ClusteredFunction(n=num_samples, mode="multi", f_name='FacilityLocation', data=dataArray, metric="euclidean", num_clusters=num_clusters, cluster_lab=cluster_ids.tolist())
obj.maximize(budget=budget,optimizer=optimizer, stopIfZeroGain=False, stopIfNegativeGain=False, verbose=False)
def fl_clustered_birch_single():
obj = ClusteredFunction(n=num_samples, mode="single", f_name='FacilityLocation', data=dataArray, metric="euclidean", num_clusters=num_clusters)
obj.maximize(budget=budget,optimizer=optimizer, stopIfZeroGain=False, stopIfNegativeGain=False, verbose=False)