Python: Clustering

c go java js lua py vbs rkt scm pro

The make_blobs method of the sklearn.datasets module provides a way to create groups of points

Here is the Python code.

import os
import matplotlib as mpl
import matplotlib.pyplot as plt
from PIL import Image

import numpy as np
import sklearn as sk
from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans

imagePos1 = 0
rlen1 = 1
clen1 = 1
dpi1 = 72
width1 = 640
height1 = 480
figSize1 = (width1 / dpi1, height1/dpi1)
fig1, ax1 = plt.subplots(rlen1,clen1,figsize=figSize1,dpi=dpi1)

fig1,ax1 = plt.subplots(1,1)

samples1 = 100
centers1 = 6
deviation1 = 1.20
random1 = 0
data1, _ = make_blobs(
	n_samples=samples1,
	centers=centers1,
	cluster_std=deviation1,
	random_state=random1,
	)

kmeans1 = KMeans(
	n_clusters=centers1,
	init="k-means++",
	max_iter=300,
	n_init=10,
	random_state=0,
	)
pred_y = kmeans1.fit_predict(data1)

plt.scatter(
	data1[:,0],
	data1[:,1],
	c="green",
	)

plt.scatter(
	kmeans1.cluster_centers_[:, 0],
	kmeans1.cluster_centers_[:, 1],
	s=200,
	c="red",
	)

plt.xlabel("X labels")
plt.ylabel("Y labels")
plt.title("Blobs scatter plot")

fig1.tight_layout()
imagePos1 += 1
type1 = "png"
saveFs1 = "./group21-1-0{0:d}.{1:s}".format(imagePos1,type1)
fig1.savefig(saveFs1,bbox_inches="tight")
savedImage1 = Image.open(saveFs1)
savedWidth1, savedHeight1= savedImage1.size
(_, _, _, _, _, _, savedSize1, _, savedTime1, _) = os.stat(saveFs1)
print("\t{0:s} : {1:d} x {2:d} , {3:,} bytes".format(saveFs1,savedWidth1,savedHeight1,savedSize1))

Here is the output of the Python code.

	./group21-1-01.png : 630 x 470 , 22,667 bytes

The underscore is used on the LHS (Left Hand Side) of the assignment statement to indicate that that return value is not needed in this situation.
There are 6 centers.
The random_state is 0 so that the same data is obtained each time the program is run.

6. Acronyms and/or initialisms for this page

1