from __future__ import print_function, division
import numpy as np
from mlfromscratch.utils import normalize, euclidean_distance, Plot
from mlfromscratch.unsupervised_learning import PCA
class PAM():
"""A simple clustering method that forms k clusters by first assigning
samples to the closest medoids, and then swapping medoids with non-medoid
samples if the total distance (cost) between the cluster members and their medoid
is smaller than prevoisly.
Parameters:
-----------
k: int
The number of clusters the algorithm will form.
"""
def __init__(self, k=2):
self.k = k
def _init_random_medoids(self, X):
""" Initialize the medoids as random samples """
n_samples, n_features = np.shape(X)
medoids = np.zeros((self.k, n_features))
for i in range(self.k):
medoid = X[np.random.choice(range(n_samples))]
medoids[i] = medoid
return medoids
def _closest_medoid(self, sample, medoids):
""" Return the index of the closest medoid to the sample """
closest_i = None
closest_distance = float("inf")
for i, medoid in enumerate(medoids):
distance = euclidean_distance(sample, medoid)
if distance < closest_distance:
closest_i = i
closest_distance = distance
return closest_i
def _create_clusters(self, X, medoids):
""" Assign the samples to the closest medoids to create clusters """
clusters = [[] for _ in range(self.k)]
for sample_i, sample in enumerate(X):
medoid_i = self._closest_medoid(sample, medoids)
clusters[medoid_i].append(sample_i)
return clusters
def _calculate_cost(self, X, clusters, medoids):
""" Calculate the cost (total distance between samples and their medoids) """
cost = 0
# For each cluster
for i, cluster in enumerate(clusters):
medoid = medoids[i]
for sample_i in cluster:
# Add distance between sample and medoid as cost
cost += euclidean_distance(X[sample_i], medoid)
return cost
def _get_non_medoids(self, X, medoids):
""" Returns a list of all samples that are not currently medoids """
non_medoids = []
for sample in X:
if not sample in medoids:
non_medoids.append(sample)
return non_medoids
def _get_cluster_labels(self, clusters, X):
""" Classify samples as the index of their clusters """
# One prediction for each sample
y_pred = np.zeros(np.shape(X)[0])
for cluster_i in range(len(clusters)):
cluster = clusters[cluster_i]
for sample_i in cluster:
y_pred[sample_i] = cluster_i
return y_pred
def predict(self, X):
""" Do Partitioning Around Medoids and return the cluster labels """
# Initialize medoids randomly
medoids = self._init_random_medoids(X)
# Assign samples to closest medoids
clusters = self._create_clusters(X, medoids)
# Calculate the initial cost (total distance between samples and
# corresponding medoids)
cost = self._calculate_cost(X, clusters, medoids)
# Iterate until we no longer have a cheaper cost
while True:
best_medoids = medoids
lowest_cost = cost
for medoid in medoids:
# Get all non-medoid samples
non_medoids = self._get_non_medoids(X, medoids)
# Calculate the cost when swapping medoid and samples
for sample in non_medoids:
# Swap sample with the medoid
new_medoids = medoids.copy()
new_medoids[medoids == medoid] = sample
# Assign samples to new medoids
new_clusters = self._create_clusters(X, new_medoids)
# Calculate the cost with the new set of medoids
new_cost = self._calculate_cost(
X, new_clusters, new_medoids)
# If the swap gives us a lower cost we save the medoids and cost
if new_cost < lowest_cost:
lowest_cost = new_cost
best_medoids = new_medoids
# If there was a swap that resultet in a lower cost we save the
# resulting medoids from the best swap and the new cost
if lowest_cost < cost:
cost = lowest_cost
medoids = best_medoids
# Else finished
else:
break
final_clusters = self._create_clusters(X, medoids)
# Return the samples cluster indices as labels
return self._get_cluster_labels(final_clusters, X)
[Machine Learning From Scratch]-unsupervised_learning-partitioning_around_medoids
?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請(qǐng)聯(lián)系作者
- 文/潘曉璐 我一進(jìn)店門(mén)赚爵,熙熙樓的掌柜王于貴愁眉苦臉地迎上來(lái)棉胀,“玉大人,你說(shuō)我怎么就攤上這事冀膝⊙渖荩” “怎么了?”我有些...
- 文/不壞的土叔 我叫張陵窝剖,是天一觀的道長(zhǎng)麻掸。 經(jīng)常有香客問(wèn)我,道長(zhǎng)赐纱,這世上最難降的妖魔是什么脊奋? 我笑而不...
- 正文 為了忘掉前任熬北,我火速辦了婚禮,結(jié)果婚禮上诚隙,老公的妹妹穿的比我還像新娘讶隐。我一直安慰自己,他們只是感情好最楷,可當(dāng)我...
- 文/花漫 我一把揭開(kāi)白布整份。 她就那樣靜靜地躺著,像睡著了一般籽孙。 火紅的嫁衣襯著肌膚如雪烈评。 梳的紋絲不亂的頭發(fā)上,一...
- 那天犯建,我揣著相機(jī)與錄音讲冠,去河邊找鬼。 笑死适瓦,一個(gè)胖子當(dāng)著我的面吹牛竿开,可吹牛的內(nèi)容都是我干的。 我是一名探鬼主播玻熙,決...
- 文/蒼蘭香墨 我猛地睜開(kāi)眼否彩,長(zhǎng)吁一口氣:“原來(lái)是場(chǎng)噩夢(mèng)啊……” “哼!你這毒婦竟也來(lái)了嗦随?” 一聲冷哼從身側(cè)響起列荔,我...
- 序言:老撾萬(wàn)榮一對(duì)情侶失蹤,失蹤者是張志新(化名)和其女友劉穎枚尼,沒(méi)想到半個(gè)月后贴浙,有當(dāng)?shù)厝嗽跇?shù)林里發(fā)現(xiàn)了一具尸體,經(jīng)...
- 正文 獨(dú)居荒郊野嶺守林人離奇死亡署恍,尸身上長(zhǎng)有42處帶血的膿包…… 初始之章·張勛 以下內(nèi)容為張勛視角 年9月15日...
- 正文 我和宋清朗相戀三年崎溃,在試婚紗的時(shí)候發(fā)現(xiàn)自己被綠了。 大學(xué)時(shí)的朋友給我發(fā)了我未婚夫和他白月光在一起吃飯的照片盯质。...
- 正文 年R本政府宣布朵逝,位于F島的核電站,受9級(jí)特大地震影響乡范,放射性物質(zhì)發(fā)生泄漏配名。R本人自食惡果不足惜啤咽,卻給世界環(huán)境...
- 文/蒙蒙 一、第九天 我趴在偏房一處隱蔽的房頂上張望渠脉。 院中可真熱鬧宇整,春花似錦、人聲如沸芋膘。這莊子的主人今日做“春日...
- 文/蒼蘭香墨 我抬頭看了看天上的太陽(yáng)为朋。三九已至臂拓,卻和暖如春,著一層夾襖步出監(jiān)牢的瞬間习寸,已是汗流浹背胶惰。 一陣腳步聲響...
- 正文 我出身青樓,卻偏偏與公主長(zhǎng)得像鸯匹,于是被迫代替她去往敵國(guó)和親坊饶。 傳聞我的和親對(duì)象是個(gè)殘疾皇子,可洞房花燭夜當(dāng)晚...