clustering-of-csv-files/irisclusters.py

# https://sky.pro/media/kak-ispolzovat-python-dlya-raboty-s-klasterizacziej-dannyh/

import pandas as pd
from sklearn.datasets import load_iris
from sklearn.cluster import KMeans
import seaborn as sns
from matplotlib import pyplot as plt
 
iris = load_iris()
data = pd.DataFrame(iris.data, columns=iris.feature_names)
print(data.head())
 
kmeans = KMeans(n_clusters=3)
kmeans.fit(data)

# центр тяжести двух кластеров:
print(kmeans.cluster_centers_)

data['cluster'] = kmeans.labels_
print(data.head())

sns.scatterplot(x=iris.feature_names[1], y=iris.feature_names[3], hue = 'cluster',  data=data, palette='viridis')
# sns.scatterplot(x='sepal length (cm)', y='petal length (cm)', hue = 'cluster',  data=data, palette='viridis')
plt.scatter(kmeans.cluster_centers_[0][0], kmeans.cluster_centers_[0][1], label='центр тяжести кластерa 0')
plt.scatter(kmeans.cluster_centers_[1][0], kmeans.cluster_centers_[1][1], label='центр тяжести кластерa 1', color = 'red')
plt.scatter(kmeans.cluster_centers_[2][0], kmeans.cluster_centers_[2][1], label='центр тяжести кластерa 2', color = 'violet')
plt.grid()
plt.legend()
plt.show()