def main():
businesses = features.getBusinesses(DATA)
truthPairs, truthIds = metrics.getGoldTruthPairs()
weights = [START_WEIGHT] * featureDistanceMap.NUM_FEATURES
# weights = featureDistanceMap.DEFAULT_WEIGHTS
featureFunctionMapping = getFeatureMapping()
cache = {}
oldWeights = list(weights)
for iteration in range(MAX_ITERATIONS):
weightsOrder = list(range(len(weights)))
random.shuffle(weightsOrder)
randIndex = probeWeight(weights, weightsOrder, 0, K,
featureFunctionMapping, businesses, truthPairs,
truthIds, cache)
if (oldWeights == weights):
break
oldWeights = list(weights)
id = "\t".join([str(weight) for weight in weights])
print("Converged in %d / %d iterations" % (iteration + 1, MAX_ITERATIONS))
print("Final Weights: %s\t%f" % (id, randIndex), file=sys.stderr)
def run():
businesses = features.getBusinesses(data.DATA_SOURCE_HUMAN_EVAL)
featureDistMap = featureDistanceMap.FeatureDistanceMap(learnWeights.getFeatureMapping(), WEIGHTS)
kMeans = clustering.KMeans(K, featureDistMap)
# kMeans = clustering.KMeans(K, featureDistanceMap.FeatureDistanceMap())
clusters = kMeans.cluster(businesses)
for i in range(len(clusters)):
print("Cluster: %02d, Size: %02d" % (i, len(clusters[i])))
print(" %s" % (", ".join([str(x) for x in sorted([businesses[index].otherInfo['name'] for index in clusters[i]])])))
# Metrics
truthPairs, truthIds = metrics.getHumanTruthPairs()
print("Rand Index: %f" % (metrics.randIndex(clusters, businesses, truthPairs, truthIds)))
def run(businessType):
businesses = features.getBusinesses(businessType)
# Arbitrary K
kMeans = clustering.KMeans(K, featureDistanceMap.FeatureDistanceMap())
clusters = kMeans.cluster(businesses)
for i in range(len(clusters)):
print("Cluster: %02d, Size: %02d" % (i, len(clusters[i])))
print(" %s" % (", ".join([
str(x) for x in sorted(
[businesses[index].otherInfo['name'] for index in clusters[i]])
])))
# Metrics
goldLabel = metrics.readGoldLabel("../data/groundtruth")
b_cluster = metrics.getClusterBusinessID(businesses, clusters)
randIndex = metrics.oldRandIndex(b_cluster, goldLabel)
print("Old Rand Index: " + str(randIndex))
print("New Rand Index: %f" % (metrics.randIndex(clusters, businesses)))
def run(weights, k, scalarNorm, setDistance):
businesses = features.getBusinesses(data.DATA_SOURCE_GROUNDTRUTH_ALL)
featureDistMap = featureDistanceMap.FeatureDistanceMap(
buildFeatureMapping(scalarNorm, setDistance), weights)
kMeans = clustering.KMeans(k, featureDistMap)
clusters = kMeans.cluster(businesses)
for i in range(len(clusters)):
print("Cluster: %02d, Size: %02d" % (i, len(clusters[i])))
print(" %s" % (", ".join([
str(x) for x in sorted([
businesses[index].otherInfo['yelpId'] for index in clusters[i]
])
])))
goldLabel = metrics.readGoldLabel("../data/groundtruth")
b_cluster = metrics.getClusterBusinessID(businesses, clusters)
randIndex = metrics.oldRandIndex(b_cluster, goldLabel)
return randIndex