本文之編寫程序涉及到API介紹，程序的完整實(shí)現(xiàn)，具體算法原理請(qǐng)查看之前所寫的K-Means算法介紹

一、基礎(chǔ)準(zhǔn)備

1、python 基礎(chǔ)

2、numpy 基礎(chǔ)

3、tensorflow 基礎(chǔ)

initialized_value
作用：
返回已經(jīng)初始化變量的值.你應(yīng)該使用這個(gè)函數(shù)來(lái)代替使用變量自己來(lái)初始化依賴這個(gè)變量的值的其他變量。

# 原始的變量
weights = tf.Variable(tf.random_normal([784, 200], stddev=0.35),name="weights")
# 創(chuàng)造相同內(nèi)容的變量
w2 = tf.Variable(weights.initialized_value(), name="w2")
# 也可以直接乘以比例
w_twice = tf.Variable(weights.initialized_value() * 0.2, name="w_twice")

tf.slice:
切割數(shù)組

y=np.arange(36).reshape([3,3,4])

sess=tf.Session()

begin_y=[1,1,0]  #切割的起始位置
size_y=[2,2,2]  # 2：第一個(gè)維度取幾個(gè)數(shù)據(jù), 2：第一個(gè)維度取幾個(gè)數(shù)據(jù),  3：第一個(gè)維度取幾個(gè)數(shù)據(jù),

###
#y[1+0, 1+0, 0+0], y[1+0, 1+0, 0+1], y[1+0, 1+0, 0+3] =  [16 17 18]
#y[1+0, 1+1, 0+0], y[1+0, 1+0, 0+1], y[1+0, 1+0, 0+3] =  [20 21 22]

#y[1+1, 1+0, 0+0], y[1+0, 1+0, 0+1], y[1+0, 1+0, 0+3] =  [28 29 30]
#y[1+1, 1+1, 0+0], y[1+0, 1+0, 0+1], y[1+0, 1+0, 0+3] =  [28 29 30]
print("y")
print(y)
out=tf.slice(y,begin_y,size_y)
print(sess.run(out))  # 結(jié)果:[[[16 17 18][20 21 22]][[28 29 30][32 33 34]]]
print("---------------")

tf.tile
復(fù)制數(shù)組
tf.tile(input, multiples, name = None)

sess = tf.Session()
data = tf.constant([[1, 2, 3, 4], [9, 8, 7, 6]])
d = tf.tile(data, [2,2])
print(sess.run(d))
----------
[[1 2 3 4 1 2 3 4]
 [9 8 7 6 9 8 7 6]
 [1 2 3 4 1 2 3 4]
 [9 8 7 6 9 8 7 6]]
 
 sess = tf.Session()
data = tf.constant([1, 2, 3, 4])
d = tf.tile(data, [2)
print(sess.run(d))
----------
[1 2 3 4 1 2 3 4]

tf.reduce_sum
分組計(jì)算tensor中各數(shù)組的和，reduction_indices等于0和1時(shí)取的維度值就不一樣。

inputs = [[1,0,2],[3,2,4]]
B = tf.reduce_sum(inputs, reduction_indices=0)
with tf.Session() as sess:
    print(sess.run(B))
# >> [4 2 6]

B = tf.reduce_sum(inputs, reduction_indices=1)
with tf.Session() as sess:
    print(sess.run(B))
# >> [3 9]

tf.arg_min
求數(shù)組最小值的下標(biāo),如axis=0，代表第一維度],如axis=1，代表第二維度

data = tf.constant([[8,1,2],[2,3,4]])
sess = tf.Session()
print(sess.run(tf.arg_min(data,0)))
# >> [1 0 0]
print(sess.run(tf.arg_min(data,1)))
# >>[1 0]

tf.reduce_any
計(jì)算tensor中各個(gè)元素的邏輯或（or運(yùn)算）

inputs = [[True,False],[True,False]]
with tf.Session() as sess:
    inputs = np.array(inputs)
    A = tf.reduce_any(inputs,0)
    print(sess.run(A))
# >>[ True False]
    A = tf.reduce_any(inputs,1)
    print(sess.run(A))
# >>[ True  True]

tf.unsorted_segment_sum
根據(jù)segment_ids的分段計(jì)算各個(gè)片段的和,
num_segments, name=None) 與tf.segment_sum函數(shù)類似，
不同在于segment_ids中id順序可以是無(wú)序的

t1 = tf.constant([[1,2,3,4], [-1,-2,-3,-4],[-1,-2,-8,-4]])
t2 = tf.unsorted_segment_sum(t1, tf.constant([0, 1,0]),2)
with tf.Session() as sess1:
    print(sess1.run(t2))
實(shí)際上就把對(duì)應(yīng)下表的數(shù)組進(jìn)行計(jì)算
如[0, 1,0],則是0:[1,2,3,4] + [-1,-2,-8,-4]，1: [-1,-2,-3,-4]

assign
tf.assign是用來(lái)更新模型中變量的值的。ref是待賦值的變量，value是要更新的值。即效果等同于 ref = value

sess =  tf.Session()
a = tf.Variable(0.0)
b = tf.placeholder(dtype=tf.float32,shape=[])
op = tf.assign(a,b)

sess.run(tf.initialize_all_variables())
print(sess.run(a))
# 0.0
sess.run(op,feed_dict={b:5.})
print(sess.run(a))
# 5.0

二、完整程序

# -*- coding: utf-8 -*-
import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np

K = 4 # 類別數(shù)目
MAX_ITERS = 1000 # 最大迭代次數(shù)
# MAX_ITERS = 2 # 最大迭代次數(shù)
N = 200 # 樣本點(diǎn)數(shù)目

centers = [[-2, -2], [-2, 1.5], [1.5, -2], [2, 1.5]] # 簇中心

print("1、加載數(shù)據(jù)")
dataSet = []
fileIn = open('data\\testData.txt')
for line in fileIn.readlines():
    lineArr = line.strip().split(' ')
    dataSet.append([float(lineArr[0]), float(lineArr[1])])

N = len(dataSet)

# print("2、數(shù)據(jù)歸一化")
# print(dataSet[0])
# # dataSet = np.mat(dataSet)
# # print(dataSet[0])

#展示數(shù)據(jù)
def showCluster(dataSet, k, clusterAssment):
    dataSet = np.array(dataSet)

    numSamples= np.shape(dataSet)[0]
    dim = np.shape(dataSet)[1]
    if dim != 2:
        print("Sorry! I can not draw because the dimension of your data is not 2!")
        return 1

    mark = ['or', 'ob', 'og', 'ok', '^r', '+r', 'sr', 'dr', '<r', 'pr']
    if k > len(mark):
        print("")
        return 1

    # draw all samples
    for i in range(numSamples):
        markIndex = int(clusterAssment[i])
        plt.plot(dataSet[i, 0], dataSet[i, 1], mark[markIndex])

    plt.show()

# 計(jì)算類內(nèi)平均值函數(shù)
def clusterMean(data, id, num):
    # 第一個(gè)參數(shù)是tensor，第二個(gè)參數(shù)是簇標(biāo)簽，第三個(gè)是簇?cái)?shù)目
    total = tf.unsorted_segment_sum(data, id, num)
    count = tf.unsorted_segment_sum(tf.ones_like(data), id, num)
    return total/count

# 構(gòu)建graph
points = tf.Variable(dataSet)
cluster = tf.Variable(tf.zeros([N], dtype=tf.int64))
# 將原始數(shù)據(jù)前k個(gè)點(diǎn)當(dāng)做初始中心
centers = tf.Variable(tf.slice(points.initialized_value(), [0, 0], [K, 2]))

# 復(fù)制操作，便于矩陣批量計(jì)算距離
repCenters = tf.reshape(tf.tile(centers, [N, 1]), [N, K, 2])
repPoints = tf.reshape(tf.tile(points, [1, K]), [N, K, 2])
# 計(jì)算距離
sumSqure = tf.reduce_sum(tf.square(repCenters-repPoints), reduction_indices=2)
# 尋找最近的簇中心
bestCenter = tf.argmin(sumSqure, axis=1)
# 檢測(cè)簇中心是否還在變化
change = tf.reduce_any(tf.not_equal(bestCenter, cluster))
# 計(jì)算簇內(nèi)均值
means = clusterMean(points, bestCenter, K)
# 將粗內(nèi)均值變成新的簇中心，同時(shí)分類結(jié)果也要更新
with tf.control_dependencies([change]):
    # 復(fù)制函數(shù)
    update = tf.group(centers.assign(means), cluster.assign(bestCenter))

with tf.Session() as sess:
    sess.run(tf.initialize_all_variables())
    changed = True
    iterNum = 0
    while changed and iterNum < MAX_ITERS:
        iterNum += 1
        # 運(yùn)行g(shù)raph
        [changed, _] = sess.run([change, update])
        [centersArr, clusterArr] = sess.run([centers, cluster])

    print(clusterArr)
    print(centersArr)
    showCluster(dataSet, K, clusterArr)
        # # 顯示圖像
        # fig, ax = plt.subplots()
        # ax.scatter(dataSet.transpose()[0], dataSet.transpose()[1], marker='o', s=100, c=clusterArr)
        # plt.plot()
        # plt.show()