From c6c73122b08898d7907855fffcdb4f1385aba938 Mon Sep 17 00:00:00 2001
From: Conrad <grosserconrad@gmail.com>
Date: Sat, 26 May 2018 20:55:35 +0200
Subject: [PATCH] K-Means Step 1

- Added simple cluster assigning

Co-Authored-By: tchemn <tchemn@users.noreply.github.com>
---
 src/algorithms/kmeansMkI.py | 53 ++++++++++++++++++++++++++++++++-----
 1 file changed, 47 insertions(+), 6 deletions(-)

diff --git a/src/algorithms/kmeansMkI.py b/src/algorithms/kmeansMkI.py
index 9376c7f..a2c28f7 100644
--- a/src/algorithms/kmeansMkI.py
+++ b/src/algorithms/kmeansMkI.py
@@ -24,12 +24,53 @@ import multiprocessing
 
 # CODE
 # Main function of the algorithm
-def kmeansmk1(clusters, data):
-	print("Sorting data into " + str(clusters) + " clusters.")
+def kmeansmk1(data):
+	clusters = 2
+	data_size = len(data)
+
+	# Defining cluster points
+	for i in range(0, clusters):
+		globals()["cpoint_" + str(i)] = randint(0, data_size)
+		print("Cluster " + str(i) + ": " + str(data[globals()["cpoint_" + str(i)]]))
+
+	data_assigned = []
+	highPoint = findHighest(data)
+
+	for item in range(0, data_size):
+		min_cluster = highPoint
+		for cluster in range(0, clusters):
+			clusternumber = globals()["cpoint_" + str(cluster)]
+			if min_cluster > calcdiff(item, clusternumber, data):
+				min_cluster = calcdiff(item, clusternumber, data)
+				assinged_cluster = clusternumber
+		data_assigned.append(assinged_cluster)
+
+	# for item in range(0, data_size):
+	# 	print("Datapoint: " + str(data[item]) + " | Assigned cluster: " + str(data[data_assigned[item]]))
+
+def findHighest(data):
+	maximum = 0
+	for i in range(0, len(data)):
+		if int(data[i]) > maximum:
+			maximum = int(data[i])
+	return maximum
+
+def calcdiff(point1, point2, data):
+	if int(data[point2]) > int(data[point1]):
+		difference = int(data[point2]) - int(data[point1])
+	else:
+		difference = int(data[point1]) - int(data[point2])
+	# print("Datapoint: " + str(data[point1]) + " | Cluster: " + str(data[point2]) + " | Difference: " + str(difference))
+	return betrag(difference)
+
+def betrag(zahl):
+	if zahl < 0:
+		zahl = int((-2 * zahl) / 2)
+	return zahl
 
 # Startup function for collecting necesarry data
 def startup(data):
-	clusters = int(input("How many clusters are known? "))
+	# clusters = int(input("How many clusters are known? "))
 	# cores = input("How many cores should be used? ")
 	# path = input("Where is the data? ") or in this case data
 
@@ -37,17 +78,17 @@ def startup(data):
 	start_time = time.time()
 
 	# Firing up the engines!
-	kmeansmk1(clusters, data)
+	kmeansmk1(data)
 	# kmeansmk1(clusters, cores, path)
 
 	# Stopping benchmark
 	seconds = time.time() - start_time
-	print(str(seconds) + " seconds for execution")
+	# print(str(seconds) + " seconds for execution")
 
 # Simple generator for test data
 def testgenerator():
 	dataArray = []
-	for i in range(1,100):
+	for i in range(0,100):
 		if i <= 20:
 			plz = generatePLZ("09")
 		elif i > 20 and i < 50: