我有一个k-means算法的python代码。
我很难理解它的作用。
像这样的线条
C = X[numpy.random.choice(X.shape[0], k, replace=False), :]
我很困惑。
有人能解释一下这段代码到底在做什么吗?
谢谢你
def k_means(data, k, num_of_features):
# Make a matrix out of the data
X = data.as_matrix()
# Get k random points from the data
C = X[numpy.random.choice(X.shape[0], k, replace=False), :]
# Remove the last col
C = [C[j][:-1] for j in range(len(C))]
# Turn it into a numpy array
C = numpy.asarray(C)
# To store the value of centroids when it updates
C_old = numpy.zeros(C.shape)
# Make an array that will assign clusters to each point
clusters = numpy.zeros(len(X))
# Error func. - Distance between new centroids and old centroids
error = dist(C, C_old, None)
# Loop will run till the error becomes zero of 5 tries
tries = 0
while error != 0 and tries < 1:
# Assigning each value to its closest cluster
for i in range(len(X)):
# Get closest cluster in terms of distance
clusters[i] = dist1(X[i][:-1], C)
# Storing the old centroid values
C_old = deepcopy(C)
# Finding the new centroids by taking the average value
for i in range(k):
# Get all of the points that match the cluster you are on
points = [X[j][:-1] for j in range(len(X)) if clusters[j] == i]
# If there were no points assigned to cluster, put at origin
if not points:
C[i][:] = numpy.zeros(C[i].shape)
else:
# Get the average of all the points and put that centroid there
C[i] = numpy.mean(points, axis=0)
# Erro is the distance between where the centroids use to be and where they are now
error = dist(C, C_old, None)
# Increase tries
tries += 1
return sil_coefficient(X,clusters,k)