<Course> Machine Learning Chapter 6: Algorithm 2 (k-means)

Machine learning

table of contents Chapter 1: Linear Regression Model [Chapter 2: Nonlinear Regression Model] (https://qiita.com/matsukura04583/items/baa3f2269537036abc57) [Chapter 3: Logistic Regression Model] (https://qiita.com/matsukura04583/items/0fb73183e4a7a6f06aa5) [Chapter 4: Principal Component Analysis] (https://qiita.com/matsukura04583/items/b3b5d2d22189afc9c81c) [Chapter 5: Algorithm 1 (k-nearest neighbor method (kNN))] (https://qiita.com/matsukura04583/items/543719b44159322221ed) [Chapter 6: Algorithm 2 (k-means)] (https://qiita.com/matsukura04583/items/050c98c7bb1c9e91be71) [Chapter 7: Support Vector Machine] (https://qiita.com/matsukura04583/items/6b718642bcbf97ae2ca8)

Chapter 6: Algorithm 2 (k-means)

What is k-means?

• Unsupervised learning
• Clustering method
• Clustering ・ ・ ・ Grouping things with similar characteristics
• Classify the given data into k clusters

k-means algorithm

• Set the initial value for each cluster center
• For each data point, calculate the distance to each cluster center and assign the closest cluster
• Calculate the mean vector (center) of each cluster
• Repeat a few steps until it converges
• Procedure
• Set the initial value for each cluster center
• For each data point, calculate the distance to each cluster center and assign the closest cluster
• Calculate the mean vector (center) of each cluster
• Repeat cluster reassignment and center update
• The clustering result can change if the initial value of the center is changed. Changing the value of + k also changes the clustering result

(Practice) Classify into 3 clusters using k-means

#https://datahexa.com/kmeans-clustering-with-wine-dataset/reference
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import cluster, preprocessing, datasets

from sklearn.cluster import KMeans

wine = datasets.load_wine()
X = wine.data
X.shape

result

y=wine.target
y.shape

result

(178,)

wine.target_names

result

array(['class_0', 'class_1', 'class_2'], dtype='<U7')

model = KMeans(n_clusters=3)
labels = model.fit_predict(X)
df = pd.DataFrame({'labels': labels})
type(df)

result

pandas.core.frame.DataFrame

def species_label(theta):
    if theta == 0:
        return wine.target_names[0]
    if theta == 1:
        return wine.target_names[1]
    if theta == 2:
        return wine.target_names[2]
df['species'] = [species_label(theta) for theta in wine.target]
pd.crosstab(df['labels'], df['species'])

Related Sites Chapter 1: Linear Regression Model [Chapter 2: Nonlinear Regression Model] (https://qiita.com/matsukura04583/items/baa3f2269537036abc57) [Chapter 3: Logistic Regression Model] (https://qiita.com/matsukura04583/items/0fb73183e4a7a6f06aa5) [Chapter 4: Principal Component Analysis] (https://qiita.com/matsukura04583/items/b3b5d2d22189afc9c81c) [Chapter 5: Algorithm 1 (k-nearest neighbor method (kNN))] (https://qiita.com/matsukura04583/items/543719b44159322221ed) [Chapter 6: Algorithm 2 (k-means)] (https://qiita.com/matsukura04583/items/050c98c7bb1c9e91be71) [Chapter 7: Support Vector Machine] (https://qiita.com/matsukura04583/items/6b718642bcbf97ae2ca8)