FilesExpand file tree

 master

/

cluster37.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

87 lines (65 loc) · 2.63 KB

 master

/

cluster37.py

Copy path

Top

File metadata and controls

• Code
• Blame

87 lines (65 loc) · 2.63 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

import matplotlib.pyplot as plt

from matplotlib import style

style.use('ggplot')

import numpy as np

X = np.array([[1, 2],

[1.5, 1.8],

[5, 8 ],

[8, 8],

[1, 0.6],

[9,11]])

plt.scatter(X[:,0], X[:,1], s=150)

plt.show()

colors = 10*["g","r","c","b","k"]

class K_Means:

def __init__(self, k=2, tol=0.001, max_iter=300):

self.k = k

self.tol = tol

self.max_iter = max_iter

def fit(self,data):

self.centroids = {}

for i in range(self.k):

self.centroids[i] = data[i]

for i in range(self.max_iter):

self.classifications = {}

for i in range(self.k):

self.classifications[i] = []

for featureset in data:

distances = [np.linalg.norm(featureset-self.centroids[centroid]) for centroid in self.centroids]

classification = distances.index(min(distances))

self.classifications[classification].append(featureset)

prev_centroids = dict(self.centroids)

for classification in self.classifications:

self.centroids[classification] = np.average(self.classifications[classification],axis=0)

optimized = True

for c in self.centroids:

original_centroid = prev_centroids[c]

current_centroid = self.centroids[c]

if np.sum((current_centroid - original_centroid) / original_centroid * 100.0) > self.tol:

print(np.sum((current_centroid - original_centroid) / original_centroid * 100.0))

optimized = False

if optimized:

break

def predict(self, data):

distances = [np.linalg.norm(data - self.centroids[centroid]) for centroid in self.centroids]

classification = distances.index(min(distances))

return classification

clf = K_Means()

clf.fit(X)

for centroid in clf.centroids:

plt.scatter(clf.centroids[centroid][0], clf.centroids[centroid][1],

marker="o", color="k", s=150, linewidths=5)

for classification in clf.classifications:

color = colors[classification]

for featureset in clf.classifications[classification]:

plt.scatter(featureset[0], featureset[1], marker="x", color=color, s=150, linewidths=5)

unknowns = np.array([[1,3],

[8,9],

[0,3],

[5,4],

[6,4],])

for unknown in unknowns:

classification = clf.predict(unknown)

plt.scatter(unknown[0], unknown[1], marker="*", color=colors[classification], s=150, linewidths=5)

##

plt.show()