Last active
August 29, 2015 14:10
-
-
Save wy36101299/5a8024fa7c26db235e97 to your computer and use it in GitHub Desktop.
k-means
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
%pylab inline | |
import math | |
import random | |
import numpy as np | |
import pandas as pd | |
import matplotlib.pyplot as plt | |
class point: | |
def __init__(self,dimension,pmin,pmax): | |
self.feature = [] | |
self.label = None | |
for a in range(dimension): | |
a = random.randint(pmin,pmax) | |
self.feature.append(a) | |
class label: | |
def __init__(self,dimension,pmin,pmax): | |
self.feature = [] | |
self.cluster = [] | |
for a in range(dimension): | |
a = random.randint(pmin,pmax) | |
self.feature.append(a) | |
# 初始化點 預設 dimension=2,min=1,max=1000 | |
def initialization_point(sumpoint): | |
points=[] | |
for a in range(sumpoint): | |
a = point(2,1,1000) | |
points.append(a) | |
return points | |
# 初始化label 預設 dimension=2,min=1,max=1000 | |
def initialization_label(k): | |
labels=[] | |
for a in range(k): | |
a = label(2,1,1000) | |
labels.append(a) | |
return labels | |
# 預設 200的點 | |
points = initialization_point(10) | |
# 預設 k = 2 | |
labels = initialization_label(2) | |
def plot(): | |
lll=[] | |
lll2=[] | |
for g in range(len(labels)): | |
num = len(labels[g].cluster) | |
if g ==0: | |
for v in labels[g].cluster: | |
lll.append([v.feature[0],v.feature[1]]) | |
if g ==1: | |
for v in labels[g].cluster: | |
lll2.append([v.feature[0],v.feature[1]]) | |
df = pd.DataFrame(lll, columns=['a', 'b']) | |
df2 = pd.DataFrame(lll2, columns=['c', 'd']) | |
ax = df.plot(kind='scatter', x='a', y='b',color='DarkBlue', label='Group 1'); | |
df2.plot(kind='scatter', x='c', y='d',color='DarkGreen', label='Group 2',ax=ax); | |
def kmeans(): | |
# 比較收斂之list | |
pre=[] | |
# step1: cluster assignment | |
for a in range(len(points)): | |
# 計算最小的距離之list | |
tp=[] | |
for b in range(len(labels)): | |
# hypot(x,y) = sqrt(x*x + y*y) | |
tpoints = math.hypot(labels[b].feature[0]-points[a].feature[0] , labels[b].feature[1]-points[a].feature[1]) | |
tp.append(tpoints) | |
points[a].label = tp.index(min(tp)) | |
# labes 加入 被分配的點 | |
labels[ tp.index(min(tp)) ].cluster.append(points[a]) | |
# 把所有label加進去,藉由比對label是否有更新來決定converge | |
pre.append(points[a].label) | |
plot() | |
# step2: move centroid | |
for a in range(len(labels)): | |
if len(labels[a].cluster) !=0: | |
temp1=0 | |
temp2=0 | |
for b in range(len( labels[a].cluster )): | |
temp1+=labels[a].cluster[b].feature[0] | |
temp2+=labels[a].cluster[b].feature[1] | |
labels[a].feature[0]=float(temp1)/float(len(labels[a].cluster)) | |
labels[a].feature[1]=float(temp2)/float(len(labels[a].cluster)) | |
# 清空 label 的 cluster 便於之後重新分配點的label | |
labels[a].cluster=[] | |
# for g in range(len(label)): | |
# print(str(g)+':'+str(label[g].points[0])+str(label[g].points[1])) | |
return pre | |
pre = kmeans() | |
# plot() | |
count=1 | |
while pre != kmeans(): | |
# plot() | |
count+=1 | |
pre = kmeans() | |
print(count) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment