forked from bnsreenu/python_for_image_processing_APEER
-
Notifications
You must be signed in to change notification settings - Fork 0
/
tutorial71a-K_means_demo.py
99 lines (79 loc) · 3.17 KB
/
tutorial71a-K_means_demo.py
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
88
89
90
91
92
93
94
95
96
97
98
99
"""
@author: Sreenivas Bhattiprolu
"""
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets.samples_generator import make_blobs
# create simulated clusters using scikit learn's make_blobs
data, true_cluster = make_blobs(n_samples=500,
centers=3,
random_state=0,
cluster_std=0.60)
data_df = pd.DataFrame(data)
data_df.columns=['x','y']
data_df['true_cluster'] = true_cluster
data_df.head(n=3)
color_map= {0:'purple',1:'blue',2:'yellow'}
data_df['true_color'] = data_df.true_cluster.map(color_map)
data_df.head(n=3)
plt.scatter(x='x',y='y',c='true_color',data=data_df)
plt.xlabel("x")
plt.xlabel("y")
#plt.savefig('kmeans_data.png')
current_centers = data_df.sample(3,random_state=42)
plt.scatter(x='x',y='y',
c='yellow',
data=data_df)
plt.scatter(x='x',y='y',
data=current_centers,
c=['red','blue','green'],
s=100)
plt.xlabel("x")
plt.xlabel("y")
# distance
def dist(x, y):
return sum((xi - yi) ** 2 for xi, yi in zip(x, y))
def assign_cluster_labels(data, centers):
cluster_labels = []
for point in data:
# compute distances between three cluster centers to a data point
distances = [dist(point, center) for center in centers]
# find which cluster is closest to the data point and assign the cluster it
cluster_labels.append(distances.index(min(distances)))
return cluster_labels
current_labels = assign_cluster_labels(data_df[['x','y']].values,
current_centers[['x','y']].values)
current_labels[1:3]
#[2, 0, 0, 0, 0, 2, 0, 0, 0, 0]
plt.scatter(x='x',y='y',c=current_labels,data=data_df)
plt.scatter(x='x',y='y',data=current_centers,c=['red','blue','black'],marker='*', s=200)
plt.xlabel("x")
plt.xlabel("y")
#Second iteration
current_centers = data_df[['x','y']].groupby(current_labels).mean()
print(current_centers)
current_labels = assign_cluster_labels(data_df[['x','y']].values,
current_centers.values)
plt.scatter(x='x',y='y',c=current_labels,data=data_df)
plt.scatter(x='x',y='y',data=current_centers,c=['red','blue','black'],marker='*', s=200)
plt.xlabel("x")
plt.xlabel("y")
#3rd iteration
current_centers = data_df[['x','y']].groupby(current_labels).mean()
print(current_centers)
current_labels = assign_cluster_labels(data_df[['x','y']].values,
current_centers.values)
plt.scatter(x='x',y='y',c=current_labels,data=data_df)
plt.scatter(x='x',y='y',data=current_centers,c=['red','blue','black'],marker='*', s=200)
plt.xlabel("x")
plt.xlabel("y")
#4th iteration
current_centers = data_df[['x','y']].groupby(current_labels).mean()
print(current_centers)
current_labels = assign_cluster_labels(data_df[['x','y']].values,
current_centers.values)
plt.scatter(x='x',y='y',c=current_labels,data=data_df)
plt.scatter(x='x',y='y',data=current_centers,c=['purple','blue','yellow'],marker='*', s=200)
plt.xlabel("x")
plt.xlabel("y")