Code Cleanup II

- Removed test functions from randomi
- Enabled timer at kmeans
- Adjusted functions of the dmlib libary

src/algorithms/dmtest.py

@@ -1,28 +1,32 @@
 # For random generation of numbers import randint
 from random import randint, shuffle
 
-# Simple generator for test data (100 plzs, 20-30-50 biased), returns 1D array of plzs 
-def testgenerator():
+# Simple generator for test plzs (40-40-20 biased), returns 1D array of plzs
+def plzGen(entries):
 	dataArray = []
-	for i in range(0,100):
-		if i <= 40:
-			plz = generatePLZ("05")
-		elif i > 40 and i < 80:
-			plz = generatePLZ("50")
+	plz_lenght = 5
+	for i in range(0, int(entries)):
+		if i < round(entries * 0.4):
+			plz = generateNumber(plz_lenght, 2)
+		elif i >= round(entries * 0.4) and i < round(entries * 0.8):
+			plz = generateNumber(plz_lenght, 9)
 		else:
-			plz = generatePLZ("")
+			plz = generateNumber(plz_lenght, randint(0,9))
 		dataArray.append(plz)
 	shuffle(dataArray)
 	return dataArray
 
-# Generates a PLZ from a certain start point
-def generatePLZ(start):
-	if len(start) == 0:
-		plz = ""
-		for j in range(1,6):
-			plz = plz + str(randint(0,9))
-	else:
-		plz = start
-		for j in range(1,4):
-			plz = plz + str(randint(0,9))
-	return plz
+# Function for generating the content of one single row randomly
+def generateNumber(numberLenght, startingNumber):
+	number = str(startingNumber)
+	for length in range(0, numberLenght - 1):
+		number = number + str(randint(0,9))
+	return number
+
+# Function for writing data into a file (content = string, nameChunkStart and namePartStart are for better naming)
+# /testdata/ folder has to be created at this point
+def writeFile(content, nameChunkStart, namePartStart):
+	filenumber = int(nameChunkStart) + int(namePartStart)
+	file = open("testdata/file" + str(filenumber) + ".txt", "w")
+	for w in range(0, len(content)):
+		file.write(content[w] + "\n")

src/algorithms/kmeansMkI.py

@@ -84,8 +84,7 @@ def assignCluster(data, highPoint, clusters):
 # Startup function for collecting necesarry data
 def startup(data):
 	# Using two clusters for testing
-	# clusters = int(input("How many clusters are known? "))
-	clusters = 2
+	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
 
@@ -100,9 +99,14 @@ def startup(data):
 
 	# Stopping benchmark
 	seconds = time.time() - start_time
-	# print(str(seconds) + " seconds for execution")
+	print(str(seconds) + " seconds for execution")
+
+	# Printing final clusters
+	for i in range(0, clusters):
+		print("Cluster " + str(i + 1) + " found at " + str(globals()["cpoint_" + str(i)]))
+
 
 # Start the algorithm and generate test data
-data = dmtest.testgenerator()
+data = dmtest.plzGen(1000)
 
-startup(data)
+startup(data)

src/data_generators/randomi2.1.py

@@ -21,18 +21,6 @@ from datetime import date
 # Importing for multi core processing
 import multiprocessing
 
-def generate09():
-	plz = "09"
-	for i in range(0,3):
-		plz = plz + str(randint(0,9))
-	return plz
-
-def generatePLZ():
-	plz = ""
-	for i in range(0,5):
-		plz = plz + str(randint(0,9))
-	return plz
-
 # randomI function which creates each file
 def randomI(units, rows, rowLength, partstart, cluster):
 	for setcounter in range(0, units):
@@ -58,7 +46,7 @@ def generateRow(rowLength):
 		row = row + str(randint(0, 9))
 	return row
 
-# Function for writing data into a file
+# Function for writing data into a file (content = string, setcount and partstart are for better naming)
 def writeFile(content, setcounter, partstart):
 	filenumber = int(setcounter) + int(partstart)
 	file = open("testdata/file" + str(filenumber) + ".txt", "w")