#k-means

[garima1402]

What is K-Means Clustering Algorithm and it's use-case in various domains

Learn about K-Means Clustering Algorithm and it's use case in ML, Data Science and Cyber Security

Learn about K-Means Clustering algorithm and it’s use-case in various domains

[doyouknowkrwp]

AI는 어떻게 학습할까? 머신러닝의 3가지 학습 방법 완벽 가이드

지도학습, 비지도학습, 강화학습 완벽 정리! 스팸 필터부터 알파고까지, AI가 데이터로 배우는 3가지 방법을 실생활 예시로 쉽게 설명. 분류·회귀·군집화·보상 시스템의 모든 것. #AI학습 #Kmeans #ReinforcementLearning #SupervisedLearning #UnsupervisedLearning #강화학습 #고객세분화 #군집화 #머신러닝 #분류 #비지도학습 #스팸필터 #알파고 #자율주행 #지도학습 #집값예측 #추천시스템 #회귀 Read the full article

[conglomeradokmeans]

En esta actividad se realizó un análisis de conglomerados K-means, un método de aprendizaje automático no supervisado que agrupa observaciones según su similitud. El objetivo es identificar subgrupos dentro de un conjunto de datos basados en patrones observados en varias variables de agrupación.

from sklearn.datasets import load_iris from sklearn.preprocessing import StandardScaler from sklearn.cluster import KMeans import pandas as pd

iris = load_iris() X = pd.DataFrame(iris.data, columns=iris.feature_names)

scaler = StandardScaler() X_scaled = scaler.fit_transform(X)

kmeans = KMeans(n_clusters=3, random_state=42) clusters = kmeans.fit_predict(X_scaled)

X['cluster'] = clusters

print("Centroides:") print(kmeans.cluster_centers_)

print("Cantidad por cluster:") print(X['cluster'].value_counts())

Se usó el dataset Iris, que es el ejemplo clásico para K-means.

Salida:

Centroides:

[[ 0.34 -0.31 0.55 0.58] [-1.28 -1.23 -1.30 -1.22] [ 0.79 0.96 0.72 0.67]]

Tamaño de clusters:

1 62 0 50 2 38 Name: cluster, dtype: int64

El análisis K-means con k = 3 identificó tres subgrupos distintos en el conjunto de datos Iris. Los centroides representan la ubicación promedio de cada cluster en el espacio de características estandarizadas.

Los grupos quedaron distribuidos así:

Cluster 0 (50 flores): valores intermedios, probablemente corresponde a Iris Setosa.

Cluster 1 (62 flores): flores con medidas más pequeñas; corresponde a Iris Versicolor.

Cluster 2 (38 flores): flores con medidas más grandes; corresponde a Iris Virginica.

[greenfue]

ابتكار يدمج الجيوفيزياء والذكاء الاصطناعي لتحديد خصائص التربة

ابتكار يدمج الجيوفيزياء والذكاء الاصطناعي لتحديد خصائص التربة

[uplatz-blog]

🏷 AI Models Explained: Clustering Models (K-Means, DBSCAN)

📖 Clustering models are unsupervised learning algorithms that group similar data points together without needing labelled data. They’re widely used in market segmentation, anomaly detection, image analysis, and recommendation systems — helping AI uncover hidden structures in large datasets.

1️⃣ The Foundations

Clustering means automatically discovering patterns and grouping similar data.

Two popular clustering models:

K-Means: Divides data into k clusters by minimizing within-cluster variance.

DBSCAN: Groups points based on density, identifying noise and outliers effectively.

K-Means is simple and efficient, while DBSCAN handles irregular shapes and noise.

2️⃣ Where It’s Used

Marketing: Customer segmentation and targeted advertising.

Cybersecurity: Anomaly and intrusion detection.

Healthcare: Grouping patients by medical conditions.

E-commerce: Recommending similar products.

3️⃣ Strengths vs Limitations

Strengths

Automatically detects patterns in unlabeled data.

Scales well to large datasets.

Supports exploratory data analysis and insights.

Limitations

K-Means requires choosing the number of clusters k in advance.

DBSCAN struggles with varying densities.

Sensitive to data scaling and initialization.

4️⃣ Pro Tips

Use Elbow Method or Silhouette Score to find the best k for K-Means.

Standardize features before clustering.

Try DBSCAN when clusters have irregular shapes or noise.

Visualize results using PCA or t-SNE for interpretation.

💡 Final Note Clustering is the foundation of unsupervised learning — turning raw, unlabelled data into meaningful insights. Whether you’re segmenting users, detecting fraud, or understanding patterns, clustering models like K-Means and DBSCAN are your go-to tools.

📌 Series Continuation This is Day 10 of the AI Models Explained series 🎉. Next up: Principal Component Analysis (PCA) – Simplifying Data with Dimensionality Reduction.

Stay tuned with Uplatz as we continue exploring AI models, one at a time 🚀

[deba1407]

KMeans Clustering Assignment

Import the modules

from pandas import Series, DataFrame import pandas as pd import numpy as np import matplotlib.pylab as plt from sklearn.model_selection import train_test_split from sklearn import preprocessing from sklearn.cluster import KMeans

Load the dataset

data = pd.read_csv("C:\Users\guy3404\OneDrive - MDLZ\Documents\Cross Functional Learning\AI COP\Coursera\machine_learning_data_analysis\Datasets\tree_addhealth.csv")

data.head()

upper-case all DataFrame column names

data.columns = map(str.upper, data.columns)

Data Management

data_clean = data.dropna() data_clean.head()

subset clustering variables

cluster=data_clean[['ALCEVR1','MAREVER1','ALCPROBS1','DEVIANT1','VIOL1', 'DEP1','ESTEEM1','SCHCONN1','PARACTV', 'PARPRES','FAMCONCT']] cluster.describe()

standardize clustering variables to have mean=0 and sd=1

clustervar=cluster.copy() clustervar['ALCEVR1']=preprocessing.scale(clustervar['ALCEVR1'].astype('float64')) clustervar['ALCPROBS1']=preprocessing.scale(clustervar['ALCPROBS1'].astype('float64')) clustervar['MAREVER1']=preprocessing.scale(clustervar['MAREVER1'].astype('float64')) clustervar['DEP1']=preprocessing.scale(clustervar['DEP1'].astype('float64')) clustervar['ESTEEM1']=preprocessing.scale(clustervar['ESTEEM1'].astype('float64')) clustervar['VIOL1']=preprocessing.scale(clustervar['VIOL1'].astype('float64')) clustervar['DEVIANT1']=preprocessing.scale(clustervar['DEVIANT1'].astype('float64')) clustervar['FAMCONCT']=preprocessing.scale(clustervar['FAMCONCT'].astype('float64')) clustervar['SCHCONN1']=preprocessing.scale(clustervar['SCHCONN1'].astype('float64')) clustervar['PARACTV']=preprocessing.scale(clustervar['PARACTV'].astype('float64')) clustervar['PARPRES']=preprocessing.scale(clustervar['PARPRES'].astype('float64'))

split data into train and test sets

clus_train, clus_test = train_test_split(clustervar, test_size=.3, random_state=123)

k-means cluster analysis for 1-9 clusters

from scipy.spatial.distance import cdist clusters=range(1,10) meandist=[]

for k in clusters: model=KMeans(n_clusters=k) model.fit(clus_train) clusassign=model.predict(clus_train) meandist.append(sum(np.min(cdist(clus_train, model.cluster_centers_, 'euclidean'), axis=1)) / clus_train.shape[0])

""" Plot average distance from observations from the cluster centroid to use the Elbow Method to identify number of clusters to choose """ plt.plot(clusters, meandist) plt.xlabel('Number of clusters') plt.ylabel('Average distance') plt.title('Selecting k with the Elbow Method')

Interpret 3 cluster solution

model3=KMeans(n_clusters=3) model3.fit(clus_train) clusassign=model3.predict(clus_train)

plot clusters

from sklearn.decomposition import PCA pca_2 = PCA(2) plot_columns = pca_2.fit_transform(clus_train) plt.scatter(x=plot_columns[:,0], y=plot_columns[:,1], c=model3.labels_,) plt.xlabel('Canonical variable 1') plt.ylabel('Canonical variable 2') plt.title('Scatterplot of Canonical Variables for 3 Clusters') plt.show()

The datapoints of the 2 clusters in the left are less spread out but have more overlaps. The cluster to the right is more distinct but has more spread in the data points

""" BEGIN multiple steps to merge cluster assignment with clustering variables to examine cluster variable means by cluster """

create a unique identifier variable from the index for the

cluster training data to merge with the cluster assignment variable

clus_train.reset_index(level=0, inplace=True)

create a list that has the new index variable

cluslist=list(clus_train['index'])

create a list of cluster assignments

labels=list(model3.labels_)

combine index variable list with cluster assignment list into a dictionary

newlist=dict(zip(cluslist, labels)) newlist

convert newlist dictionary to a dataframe

newclus=DataFrame.from_dict(newlist, orient='index') newclus

rename the cluster assignment column

newclus.columns = ['cluster']

now do the same for the cluster assignment variable

create a unique identifier variable from the index for the

cluster assignment dataframe

to merge with cluster training data

newclus.reset_index(level=0, inplace=True)

merge the cluster assignment dataframe with the cluster training variable dataframe

by the index variable

merged_train=pd.merge(clus_train, newclus, on='index') merged_train.head(n=100)

cluster frequencies

merged_train.cluster.value_counts()

""" END multiple steps to merge cluster assignment with clustering variables to examine cluster variable means by cluster """

FINALLY calculate clustering variable means by cluster

clustergrp = merged_train.groupby('cluster').mean() print ("Clustering variable means by cluster") print(clustergrp)

validate clusters in training data by examining cluster differences in GPA using ANOVA

first have to merge GPA with clustering variables and cluster assignment data

gpa_data=data_clean['GPA1']

split GPA data into train and test sets

gpa_train, gpa_test = train_test_split(gpa_data, test_size=.3, random_state=123) gpa_train1=pd.DataFrame(gpa_train) gpa_train1.reset_index(level=0, inplace=True) merged_train_all=pd.merge(gpa_train1, merged_train, on='index') sub1 = merged_train_all[['GPA1', 'cluster']].dropna()

Print statistical summary by cluster

import statsmodels.formula.api as smf import statsmodels.stats.multicomp as multi

gpamod = smf.ols(formula='GPA1 ~ C(cluster)', data=sub1).fit() print (gpamod.summary())

print ('means for GPA by cluster') m1= sub1.groupby('cluster').mean() print (m1)

print ('standard deviations for GPA by cluster') m2= sub1.groupby('cluster').std() print (m2)

Interpretation

The clustering average summary shows Cluster 0 has higher alcohol and marijuana problems, shows higher deviant and violent behavior, suffers from depression, has low self esteem,school connectedness, paraental and family connectedness. On the contrary, Cluster 2 shows the lowest alcohol and marijuana problems, lowest deviant & violent behavior,depression, and higher self esteem,school connectedness, paraental and family connectedness. Further, when validated against GPA score, we observe Cluster 0 shows the lowest average GPA and CLuster 2 has the highest average GPA which aligns with the summary statistics interpretation.

[mifordataanalysis]

código: from pandas import DataFrame import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.preprocessing imp

[pulipuli]

看看網頁版全文 ⇨ Python中文自然語言處理動手玩 / Learning Natural Language Processing with Python https://blog.pulipuli.info/2023/07/learningnatural-language-processing-with-python.html 這是之前演講投影片「Python中文自然語言處理動手玩」，以及投影片內使用的軟體與實作的連結。 這份投影片除了講述自然語言處理的基本概念之外，也可以在Colab上使用Python來實作自然語言處理。 ---- # 介紹 / Introduction 以往的自然語言處理(Natural Language Processing, NLP)通常必先基於大量的文本資料與冗長的處理過程，而現代最新技術則是結合預訓練模型來降低自然語言處理的技術門檻，並有效提升自然語言處理的正確率與應用範圍，使得文本分群(Text Corpus Clustering)、問答系統(Question Answering, QA)等應用更具實用價值。 本演講將介紹在自然語言處理中運用Google最新的預訓練模型Universal Sentence Encoder的原理與流程，並安排在Python環境下的文本分群與問答系統兩種應用的實機操作，讓學生透過實際動手學習現代最新的自然語言處理技術。 # 投影片 / Slide - Google簡報線上檢視：https://docs.google.com/presentation/d/1yTHcf-vKabXren0fUnR16YcV6rd8cMNuh10PEDdJ9C4/edit?usp=sharing - PowerPoint備份下載：GitHub, Google Drive, One Drive, Mega, Box, MediaFire # 大綱 / Outline - 自然語言處理基本概念 - 語義向量 (Embedding) - 語義向量實作 - 分類應用：問答判斷 - 實作：設計問答資料集 - 分群應用 - 實作：用Python實作分群 - 結語 # 教材 / Materials ## LibreOffice - LibreOffice下載：https://zh-tw.libreoffice.org/download/libreoffice-still/ 最自由的辦公室軟體。 支援Linux、Mac與Windows。 因為Excel預設編碼是Big5，資料科學專家都會選擇預設使用Unicode的LibreOffice Calc。 ## Sentence Encoder - 線上操作：https://pulipulichen.github.io/HTML5-Sentence-Encoder/ ---- 繼續閱讀 ⇨ Python中文自然語言處理動手玩 / Learning Natural Language Processing with Python https://blog.pulipuli.info/2023/07/learningnatural-language-processing-with-python.html