Added numGen generator

- Removed unstable randomi version
- Added numGen generator
- Detected bug

src/algorithms/dmtest.py

@@ -31,4 +31,22 @@ 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")
+		file.write(content[w] + "\n")
+
+# Function for generating 'entries'x int_lenght'-long numbers in 'clusters' clusters
+def numGen(entries, cluster, int_lenght):
+	dataArray = []
+	clusterArray = []
+
+	for cluster_num in range(0, cluster):
+		clusterArray.append(randint(10,99))
+
+	for item in range(0, entries):
+		decider = randint(0, 2)
+		if decider == 2:
+			dataArray.append(generateNumber(int_lenght, randint(1,9)))
+		else:
+			cluster_decider = randint(0, cluster - 1)
+			dataArray.append(generateNumber(int_lenght - 1, clusterArray[cluster_decider]))
+	shuffle(dataArray)
+	return dataArray

src/algorithms/kmeansMkI.py

@@ -8,7 +8,7 @@
 #usage:				python pyscript.py
 #notes:
 #dependencies:		mathplotlib
-#known_issues:
+#known_issues:		When clusters are 'thin' or noice is to strong --> unaccurate
 #python_version:	3.x
 #==============================================================================
 
@@ -135,6 +135,8 @@ def startup(data):
 	print(str(seconds) + " seconds for execution")
 
 # Start the algorithm and generate test data
-data = dmtest.plzGen(10000)
+# data = dmtest.plzGen(10000)
+# data = dmtest.numGen(10000, 3, 5)
 
+data = dmtest.numGen(10000, 8, 7)
 startup(data)