urban/data_mining_algorithms
1
0
Fork 0
Code Issues Pull Requests Actions Packages Releases Activity

Added a numpy based visualizer

Browse Source 
if the algorithm doesnt work you might need to pip numpy and matplotlib
This commit is contained in:
tchemn
2018-06-01 00:37:48 +02:00
parent faa113f05e
commit e1d794c006
1 changed files with 19 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
src/algorithms/kmeansMkI.py
View File

@@ -23,6 +23,10 @@ from random import randint
# Importing libary for multi core processing # Importing libary for multi core processing
import multiprocessing import multiprocessing
# Importing libaries for easy plotting
import numpy as np
import matplotlib.pyplot as plt
# Importing own libaries Datamining Libary and Datamining Test # Importing own libaries Datamining Libary and Datamining Test
import dmlib import dmlib
import dmtest import dmtest
@@ -45,13 +49,27 @@ def kmeansmk1(data, clusters):
calcClusters(new_data, clusters) calcClusters(new_data, clusters)
for cluster in range(0, clusters): for cluster in range(0, clusters):
#keeps the algorith going until the central clusterpoint doesnt change anymore #keeps the algorithm going until the central clusterpoint doesnt change anymore
if globals()["cpointchanged_" + str(cluster)] == 1: if globals()["cpointchanged_" + str(cluster)] == 1:
done = 1 done = 1
# Printing final clusters # Printing final clusters
for i in range(0, clusters): for i in range(0, clusters):
print("Endcluster " + str(i + 1) + " is calculated to be at " + str(globals()["cpoint_" + str(i)]) + " after " + str(runs) + " runs") print("Endcluster " + str(i + 1) + " is calculated to be at " + str(globals()["cpoint_" + str(i)]) + " after " + str(runs) + " runs")
# plotting the random data and the found clusters
anew = []
inew = 0
while inew < 1000:
anew.append(inew)
inew = inew + 1
floatdata = [int(x) for x in data]
for i in range(0, clusters):
plt.axvline(x=int(globals()["cpoint_" + str(i)]), color='r')
plt.scatter(floatdata, anew, marker='x', s=7, color='k')
plt.show()
return 0 return 0
# Calculates middle values for each cluster, takes 2D array (item, assigned_cluster) # Calculates middle values for each cluster, takes 2D array (item, assigned_cluster)