I have my own algorithm to classify kmeans
# parameter c is for how many cluster do you want
def kmeans(data, c, iter, state):
np.random.seed(state)
m=data.shape[0] #number of training examples
n=data.shape[1] #number of features
Centroids=np.array([]).reshape(n,0)
for i in range(c):
rand=np.random.randint(0,m-1)
Centroids=np.c_[Centroids,data[rand]]
result = {}
for i in range(iter):
distance=np.array([]).reshape(m,0) #Euclidian distance
for k in range(c):
tempDist=np.sum((data-Centroids[:,k])**2,axis=1)
distance=np.c_[distance,tempDist]
C=np.argmin(distance,axis=1) 1
Y={}
for k in range(c):
Y[k 1]=np.array([]).reshape(2,0)
for i in range(m):
Y[C[i]]=np.c_[Y[C[i]],X[i]]
for k in range(c):
Y[k 1]=Y[k 1].T
for k in range(c):
Centroids[:,k]=np.mean(Y[k 1],axis=0)
result=Y
return result
I've tested my code to classify kmeans of 2 dimensional data and it succeed
# This 2 dimensional data is just for example
Xd = [[7,0],[0,3],[3,4],[4,6],[7,1],[2,4]]
Z=kmeans(Xd,3,500,0)
print(Z)
>>>Z = {1: [[7,0],[7,1]],
2: [[3,4],[2,4]],
3: [[0,3],[4,6]]}
But when I replace Xd with variable that has 784 dimension, it shows error on this line:
Y[C[i]]=np.c_[Y[C[i]],X[i]]
>>>all the input array dimensions for the concatenation axis must match exactly,
but along dimension 0, the array at index 0 has size 2 and the array at index 1 has size 784
What should I do?
CodePudding user response:
Y[k 1]=np.array([]).reshape(2,0)
Instead of 2
, this array should match the dimension of the
one you're concatenating against.