In [6]:

    

import pandas as pd
import numpy as np
%matplotlib inline
import matplotlib.pyplot as plt
from IPython.display import display, HTML
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm
from operator import attrgetter
from matplotlib.patches import Ellipse
from math import atan2,degrees
import numpy.random as rnd


    

In [7]:

    

points = pd.read_csv('Clustering.csv',sep=',')


    

In [8]:

    

plt.plot(points.X, points.Y, 'ro')
plt.axis([min(points.X)-1, max(points.X)+1, min(points.Y)-1, max(points.Y)+1])
for i, txt in enumerate(points.index):
    plt.annotate(txt+1, (points.X[i],points.Y[i]))
plt.show()


    

In [9]:

    

class Dist:
    def __init__(self,p1indx,p2indx,dist):
        self.p1 = p1indx
        self.p2 = p2indx
        self.dist=dist
distances={}
distancelst = []
for i in range(len(points.index)):
    for j in range(len(points.index)):
        if i==j:
            continue
        if (i,j) not in distances.keys():
            dist = np.linalg.norm(np.array([points.X[i],points.Y[i]])-np.array([points.X[j],points.Y[j]]))
            distances[(i,j)]=dist
            distances[(j,i)]=dist
            distancelst.append(Dist(i,j,dist))


    

In [12]:

    

distancelst.sort(key=lambda x: x.dist, reverse=False)


    

In [13]:

    

for i in distancelst:
    print i.dist,i.p1+1,i.p2+1


    

    




0.424264068712 9 18
0.583095189485 6 11
0.707106781187 3 12
0.707106781187 3 13
0.707106781187 12 19
0.761577310586 12 14
0.824621125124 2 14
0.824621125124 14 19
0.860232526704 10 11
1.0 3 19
1.0 6 10
1.0 12 13
1.11803398875 7 15
1.11803398875 18 20
1.1401754251 9 11
1.21655250606 9 10
1.3152946438 9 20
1.39283882772 1 11
1.41421356237 1 6
1.41421356237 2 19
1.41421356237 3 4
1.41421356237 4 8
1.41421356237 6 19
1.44222051019 3 14
1.56204993518 11 18
1.58113883008 2 12
1.58113883008 4 13
1.58113883008 7 17
1.58113883008 8 17
1.58113883008 10 18
1.58113883008 13 19
1.69705627485 6 9
1.72626765016 13 14
1.80277563773 15 16
1.80277563773 15 17
1.96977156036 6 14
1.98494332413 11 19
2.0 1 19
2.0 2 6
2.11896201004 11 20
2.12132034356 4 12
2.12132034356 6 12
2.12132034356 6 18
2.20907220344 1 9
2.2360679775 1 3
2.2360679775 1 4
2.2360679775 1 7
2.2360679775 1 10
2.2360679775 2 3
2.2360679775 2 10
2.2360679775 3 6
2.2360679775 4 19
2.2360679775 10 19
2.5 1 20
2.5 5 20
2.5 10 20
2.5179356624 2 11
2.54558441227 10 14
2.5495097568 1 12
2.5495097568 1 18
2.5495097568 2 13
2.5495097568 4 17
2.5495097568 16 17
2.5495097568 11 14
2.69072480941 11 12
2.69258240357 6 20
2.74590604355 3 11
2.80713376952 1 14
2.82842712475 3 8
2.82842712475 7 8
2.82842712475 7 16
2.84253408071 4 14
2.91547594742 1 13
2.91547594742 1 17
2.91547594742 6 13
2.91547594742 8 13
2.91547594742 10 12
3.0 1 8
3.0 4 6
3.04138126515 7 20
3.11126983722 9 19
3.16227766017 1 2
3.16227766017 3 10
3.16227766017 4 7
3.33766385366 4 11
3.35410196625 1 15
3.35410196625 8 15
3.39705755029 7 11
3.41760149813 2 9
3.44093010682 11 13
3.53553390593 5 18
3.53553390593 8 12
3.53553390593 18 19
3.60555127546 2 4
3.60555127546 5 7
3.60555127546 6 7
3.60555127546 8 19
3.60555127546 9 14
3.64005494464 5 15
3.67151195014 7 9
3.80525951809 5 9
3.80788655293 2 18
3.80788655293 3 17
3.80788655293 7 18
3.80788655293 10 13
3.80788655293 15 20
3.81837661841 9 12
3.88329756779 3 9
4.0 3 7
4.0 4 10
4.0 8 16
4.02243707222 14 18
4.03112887415 4 15
4.03112887415 19 20
4.12310562562 6 8
4.12310562562 7 19
4.12310562562 13 17
4.24264068712 7 10
4.24264068712 12 18
4.25205832509 8 14
4.29418211072 11 17
4.30116263352 3 18
4.30116263352 6 17
4.30116263352 17 19
4.32897216438 8 11
4.36806593357 4 9
4.472135955 1 5
4.472135955 12 17
4.4821869662 11 15
4.5 17 20
4.52769256907 7 12
4.52769256907 7 13
4.55411901469 5 11
4.58039299624 9 13
4.60977222865 2 20
4.60977222865 3 20
4.64004310325 9 15
4.66154480832 14 20
4.71699056603 4 20
4.71699056603 6 15
4.71699056603 12 20
4.71699056603 15 18
4.74341649025 4 18
4.87647413609 9 17
4.94772675074 7 14
5.0 1 16
5.0 2 8
5.0 5 10
5.0 5 16
5.0 13 18
5.02493781056 3 15
5.07740090991 14 17
5.09901951359 4 16
5.09901951359 5 6
5.09901951359 8 10
5.09901951359 17 18
5.14781507049 5 17
5.14781507049 10 17
5.2038447325 8 9
5.22015325446 8 20
5.22015325446 15 19
5.31507290637 10 15
5.31507290637 13 20
5.38516480713 2 7
5.5 13 15
5.52268050859 8 18
5.59016994375 12 15
5.59016994375 16 20
5.7008771255 2 17
6.0440052945 14 15
6.22414652784 11 16
6.32455532034 3 16
6.32455532034 5 19
6.40312423743 4 5
6.40312423743 5 8
6.40312423743 6 16
6.44049687524 9 16
6.5 2 15
6.5192024052 16 18
6.67083203206 13 16
6.7082039325 3 5
6.7082039325 16 19
6.96419413859 5 12
6.96419413859 12 16
7.03420215803 5 14
7.07106781187 2 5
7.07106781187 10 16
7.38241153012 5 13
7.51531769122 14 16
8.0622577483 2 16

In [14]:

    

def EclispeInfo(p1indx,p2indx,increment=0.2,anglecoef=1):
    delta_x = points.X[p1indx]-points.X[p2indx]
    delta_y = points.Y[p1indx]-points.Y[p2indx]
    theta_radians = atan2(delta_y, delta_x)
    e = Ellipse(((points.X[p1indx]+points.X[p2indx])/2,(points.Y[p1indx]+points.Y[p2indx])/2),
            abs(delta_y)+increment,abs(delta_x)+increment,-2*anglecoef*degrees(theta_radians))
    e.set_clip_box(ax.bbox)
    e.set_alpha(0.4)
    e.set_facecolor(rnd.rand(3))
    return e


    

In [15]:

    

fig = plt.figure(0)
ax = fig.add_subplot(111, aspect='equal')

ax.plot(points.X, points.Y, 'ro')
ax.axis([min(points.X)-1, max(points.X)+1, min(points.Y)-1, max(points.Y)+1])
for i, txt in enumerate(points.index):
    ax.annotate(txt+1, (points.X[i],points.Y[i]))
ax.add_artist(EclispeInfo(17,8))
ax.add_artist(EclispeInfo(5,10))
ax.add_artist(EclispeInfo(2,11))
ax.add_artist(EclispeInfo(6,14))
ax.add_artist(EclispeInfo(17,19,1))
ax.add_artist(EclispeInfo(5,9,1))
ax.add_artist(EclispeInfo(2,12,1))
ax.add_artist(EclispeInfo(6,16,1))
ax.add_artist(EclispeInfo(8,9,3.5,0.5))
ax.add_artist(EclispeInfo(8,9,3.9))
ax.add_artist(EclispeInfo(12,18,0.8,2.6))
#And So On I stopped due unclearity of the plot after a while.
plt.show()


    

In [40]:

    

distances[(15,8)]


    

    
Out[40]:





6.4404968752418474

In [ ]: