K-means clustering

No account yet ?

Tested in Anaconda and Python 3.7

import matplotlib.pyplot as plt
import seaborn as sns; sns.set()
import numpy as np
from sklearn.cluster import KMeans
 
from sklearn.datasets import make_blobs
 
X, y_true = make_blobs(n_samples = 500, centers = 4,
            cluster_std = 0.40, random_state = 0)
 
plt.scatter(X[:, 0], X[:, 1], s = 50);
plt.show()
 
kmeans = KMeans(n_clusters = 4)
 
kmeans.fit(X)
y_kmeans = kmeans.predict(X)
plt.scatter(X[:, 0], X[:, 1], c = y_kmeans, s = 50, cmap = 'viridis')
 
centers = kmeans.cluster_centers_
 
plt.scatter(centers[:, 0], centers[:, 1], c = 'black', s = 200, alpha = 0.5);
plt.show()
 

Source : https://tutoriels.edu.lat/pub/artificial-intelligence-with-python/artificial-intelligence-with-python-unsupervised-learning-clustering/ai-avec-python-apprentissage-non-supervise-clustering

Iris.txt

"Sepal Length" "Sepal Width" "Petal Length" "Petal Width" "Species"
5.1 3.5 1.4 0.2 setosa
4.9 3 1.4 0.2 setosa
4.7 3.2 1.3 0.2 setosa
4.6 3.1 1.5 0.2 setosa
5 3.6 1.4 0.2 setosa
5.4 3.9 1.7 0.4 setosa
4.6 3.4 1.4 0.3 setosa
5 3.4 1.5 0.2 setosa
4.4 2.9 1.4 0.2 setosa
4.9 3.1 1.5 0.1 setosa
5.4 3.7 1.5 0.2 setosa
4.8 3.4 1.6 0.2 setosa
4.8 3 1.4 0.1 setosa
4.3 3 1.1 0.1 setosa
5.8 4 1.2 0.2 setosa
5.7 4.4 1.5 0.4 setosa
5.4 3.9 1.3 0.4 setosa
5.1 3.5 1.4 0.3 setosa
5.7 3.8 1.7 0.3 setosa
5.1 3.8 1.5 0.3 setosa
5.4 3.4 1.7 0.2 setosa
5.1 3.7 1.5 0.4 setosa
4.6 3.6 1 0.2 setosa
5.1 3.3 1.7 0.5 setosa
4.8 3.4 1.9 0.2 setosa
5 3 1.6 0.2 setosa
5 3.4 1.6 0.4 setosa
5.2 3.5 1.5 0.2 setosa
5.2 3.4 1.4 0.2 setosa
4.7 3.2 1.6 0.2 setosa
4.8 3.1 1.6 0.2 setosa
5.4 3.4 1.5 0.4
...

Tested in Anaconda and Python 3.7

# -*- coding: utf-8 -*-
"""
Created on Wed Jun 22 12:21:06 2022
 
@author: https://github.com/fxjollois/cours-2021-2022/blob/main/insa-ms-esd--ml/kmeans-python.ipynb
"""
#Librairies utilisées
import pandas
import numpy
import matplotlib.pyplot as plt
import seaborn
seaborn.set_style("white")
 
from sklearn.cluster import KMeans
from sklearn.preprocessing import scale
 
#Données utilisées
iris = pandas.read_table("https://fxjollois.github.io/donnees/Iris.txt", sep = "\t")
iris.head()
print(iris)
 
iris2 = iris.drop("Species", axis = 1)
iris2.head()
print(iris2)
 
#Réalisation de la CAH
kmeans = KMeans(n_clusters = 3)
kmeans.fit(scale(iris2))
print(kmeans)
 
#Informations sur la partition
pandas.Series(kmeans.labels_).value_counts()
print(pandas.Series(kmeans.labels_).value_counts())
 
#Centre des classes
kmeans.cluster_centers_
print(kmeans.cluster_centers_)
 
iris2.assign(classe = kmeans.labels_).groupby("classe").mean()
print(iris2.assign(classe = kmeans.labels_).groupby("classe").mean())
 
#Choix du nombre de classes
inertia = []
for k in range(1, 11):
    kmeans = KMeans(n_clusters = k, init = "random", n_init = 20).fit(scale(iris2))
    inertia = inertia + [kmeans.inertia_]
inertia = pandas.DataFrame({"k": range(1, 11), "inertia": inertia})
seaborn.lineplot(data = inertia, x = "k", y = "inertia")
plt.scatter(2, inertia.query('k == 2')["inertia"], c = "red")
plt.scatter(3, inertia.query('k == 3')["inertia"], c = "red")
plt.show()
 

k-means - Mastère ESD - Introduction au Machine Learning - GitHub

Sepal Length Sepal Width Petal Length Petal Width Species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa
.. ... ... ... ... ...
145 6.7 3.0 5.2 2.3 virginica
146 6.3 2.5 5.0 1.9 virginica
147 6.5 3.0 5.2 2.0 virginica
148 6.2 3.4 5.4 2.3 virginica
149 5.9 3.0 5.1 1.8 virginica

[150 rows x 5 columns]
Sepal Length Sepal Width Petal Length Petal Width
0 5.1 3.5 1.4 0.2
1 4.9 3.0 1.4 0.2
2 4.7 3.2 1.3 0.2
3 4.6 3.1 1.5 0.2
4 5.0 3.6 1.4 0.2
.. ... ... ... ...
145 6.7 3.0 5.2 2.3
146 6.3 2.5 5.0 1.9
147 6.5 3.0 5.2 2.0
148 6.2 3.4 5.4 2.3
149 5.9 3.0 5.1 1.8

[150 rows x 4 columns]
KMeans(n_clusters=3)
2 53
1 50
0 47
dtype: int64
[[ 1.13597027 0.08842168 0.99615451 1.01752612]
[-1.01457897 0.85326268 -1.30498732 -1.25489349]
[-0.05021989 -0.88337647 0.34773781 0.2815273 ]]
Sepal Length Sepal Width Petal Length Petal Width
classe
0 6.780851 3.095745 5.510638 1.972340
1 5.006000 3.428000 1.462000 0.246000
2 5.801887 2.673585 4.369811 1.413208

Comparison of K-Means and MiniBatchKMeans clustering algorithms

Tested in Anaconda and Python 3.7

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()
from sklearn.cluster import MiniBatchKMeans, KMeans
 
data = pd.read_csv("housing.csv")
 
data = data.loc[:, ["median_income", "latitude", "longitude"]]
 
kmeans = MiniBatchKMeans(n_clusters=6, random_state=0, batch_size=6)
data["Cluster"] = kmeans.fit_predict(data)
data["Cluster"] = data["Cluster"].astype("int")
print(data.head())
 
plt.style.use('seaborn-whitegrid')
plt.rc("figure", autolayout=True)
plt.rc("axes", labelweight='bold', labelsize='large', titleweight='bold', titlesize=14, titlepad=10)
sns.relplot(x='longitude', y='latitude', hue='Cluster', data=data, height=6)
plt.title('MiniBatchKMeans')
plt.show()
 
kmeans = KMeans(n_clusters=6, random_state=0)
data["Cluster"] = kmeans.fit_predict(data)
data["Cluster"] = data["Cluster"].astype("int")
print(data.head())
 
plt.style.use('seaborn-whitegrid')
plt.rc("figure", autolayout=True)
plt.rc("axes", labelweight='bold', labelsize='large', titleweight='bold', titlesize=14, titlepad=10)
sns.relplot(x='longitude', y='latitude', hue='Cluster', data=data, height=6)
plt.title('K-Means')
plt.show()
 

Source : https://thecleverprogrammer.com/2021/09/10/mini-batch-k-means-clustering-in-machine-learning/
housing.csv : https://raw.githubusercontent.com/ageron/handson-ml/master/datasets/housing/housing.csv