From d4095e5cbe3fdee52b8890c9d2aa15fc6df153e0 Mon Sep 17 00:00:00 2001
From: Marin Mlinarevic <marin.mlinarevic@outlook.com>
Date: Thu, 10 Dec 2020 13:33:24 +0100
Subject: [PATCH 1/2] Import specific methods and add random samples for
 testing

---
 week09/improvement/clustering.py |  4 ++--
 week09/improvement/samples.csv   | 12 ++++++++++++
 2 files changed, 14 insertions(+), 2 deletions(-)
 create mode 100644 week09/improvement/samples.csv

diff --git a/week09/improvement/clustering.py b/week09/improvement/clustering.py
index d6359ea..def02c4 100644
--- a/week09/improvement/clustering.py
+++ b/week09/improvement/clustering.py
@@ -1,7 +1,7 @@
 """This code implements the k-means clustering algorithm for 2 dimensions."""
 
-from math import *
-from random import *
+from math import sqrt
+from random import randrange
 
 k=3
 
diff --git a/week09/improvement/samples.csv b/week09/improvement/samples.csv
new file mode 100644
index 0000000..2e4b0d5
--- /dev/null
+++ b/week09/improvement/samples.csv
@@ -0,0 +1,12 @@
+342,4454
+34,5
+34,34
+45,56
+453,67
+34,6
+7,45
+45,7
+45,6
+65654,456
+54,564
+456,56
\ No newline at end of file

From 9dffb2c04e6710033767e253382c1b996f6eafcf Mon Sep 17 00:00:00 2001
From: Marin Mlinarevic <marin.mlinarevic@outlook.com>
Date: Thu, 10 Dec 2020 13:43:32 +0100
Subject: [PATCH 2/2] Changed variable k to num_clusters and adapted code to
 use the variable

---
 week09/improvement/clustering.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/week09/improvement/clustering.py b/week09/improvement/clustering.py
index def02c4..16ccf00 100644
--- a/week09/improvement/clustering.py
+++ b/week09/improvement/clustering.py
@@ -3,13 +3,13 @@
 from math import sqrt
 from random import randrange
 
-k=3
+num_clusters=3
 
 lines = open('samples.csv', 'r').readlines()
 ps=[]
 for line in lines: ps.append(tuple(map(float, line.strip().split(','))))
 
-m=[ps[randrange(len(ps))], ps[randrange(len(ps))], ps[randrange(len(ps))]]
+m=[ps[randrange(len(ps))] for i in range(num_clusters)]
 
 alloc=[None]*len(ps)
 n=0
@@ -21,12 +21,12 @@
     d[1]=sqrt((p[0]-m[1][0])**2 + (p[1]-m[1][1])**2)
     d[2]=sqrt((p[0]-m[2][0])**2 + (p[1]-m[2][1])**2)
     alloc[i]=d.index(min(d))
-  for i in range(3):
+  for i in range(num_clusters):
     alloc_ps=[p for j, p in enumerate(ps) if alloc[j] == i]
     new_mean=(sum([a[0] for a in alloc_ps]) / len(alloc_ps), sum([a[1] for a in alloc_ps]) / len(alloc_ps))
     m[i]=new_mean
   n=n+1
 
-for i in range(3):
+for i in range(num_clusters):
   alloc_ps=[p for j, p in enumerate(ps) if alloc[j] == i]
   print("Cluster " + str(i) + " is centred at " + str(m[i]) + " and has " + str(len(alloc_ps)) + " points.")
\ No newline at end of file