def assignClusters(numClusters):
points = track_maps.readTrainMap().values()
km = kmeans_clustering.doKMeans(points,numClusters,True)
clusters = track_maps.readCentroids()
trainMap = track_maps.readTrainMap()
folder_loop(train_loc,km,trainMap,clusters,None,None)
testMap = track_maps.readTestMap()
test_list = []
feature_list = []
folder_loop(test_loc,km,testMap,clusters,test_list,feature_list)
track_maps.writeTestSet(test_list)
track_maps.writeFeatureSet(feature_list)
def rangeKMeans(start=1,end=30,plot=True):
train_map = track_maps.readTrainMap()
points = train_map.values()
k_means_var = []
for k in range(start,end):
result = doKMeans(points,k,False)
k_means_var.append(result)
if plot:
plt.xlabel('Number of Clusters')
plt.ylabel('Inertia')
plt.title('Sum Distance to Closest Cluster')
plt.plot([(x,k_means_var[x-1].inertia_) for x in range(start,end)])
plt.show()
return k_means_var
