├── Customers.csv ├── README.md └── kmeanss.py /Customers.csv: -------------------------------------------------------------------------------- 1 | CustomerID,Genre,Age,Annual Income (k$),Spending Score (1-100) 2 | 0001,Male,19,15,39 3 | 0002,Male,21,15,81 4 | 0003,Female,20,16,6 5 | 0004,Female,23,16,77 6 | 0005,Female,31,17,40 7 | 0006,Female,22,17,76 8 | 0007,Female,35,18,6 9 | 0008,Female,23,18,94 10 | 0009,Male,64,19,3 11 | 0010,Female,30,19,72 12 | 0011,Male,67,19,14 13 | 0012,Female,35,19,99 14 | 0013,Female,58,20,15 15 | 0014,Female,24,20,77 16 | 0015,Male,37,20,13 17 | 0016,Male,22,20,79 18 | 0017,Female,35,21,35 19 | 0018,Male,20,21,66 20 | 0019,Male,52,23,29 21 | 0020,Female,35,23,98 22 | 0021,Male,35,24,35 23 | 0022,Male,25,24,73 24 | 0023,Female,46,25,5 25 | 0024,Male,31,25,73 26 | 0025,Female,54,28,14 27 | 0026,Male,29,28,82 28 | 0027,Female,45,28,32 29 | 0028,Male,35,28,61 30 | 0029,Female,40,29,31 31 | 0030,Female,23,29,87 32 | 0031,Male,60,30,4 33 | 0032,Female,21,30,73 34 | 0033,Male,53,33,4 35 | 0034,Male,18,33,92 36 | 0035,Female,49,33,14 37 | 0036,Female,21,33,81 38 | 0037,Female,42,34,17 39 | 0038,Female,30,34,73 40 | 0039,Female,36,37,26 41 | 0040,Female,20,37,75 42 | 0041,Female,65,38,35 43 | 0042,Male,24,38,92 44 | 0043,Male,48,39,36 45 | 0044,Female,31,39,61 46 | 0045,Female,49,39,28 47 | 0046,Female,24,39,65 48 | 0047,Female,50,40,55 49 | 0048,Female,27,40,47 50 | 0049,Female,29,40,42 51 | 0050,Female,31,40,42 52 | 0051,Female,49,42,52 53 | 0052,Male,33,42,60 54 | 0053,Female,31,43,54 55 | 0054,Male,59,43,60 56 | 0055,Female,50,43,45 57 | 0056,Male,47,43,41 58 | 0057,Female,51,44,50 59 | 0058,Male,69,44,46 60 | 0059,Female,27,46,51 61 | 0060,Male,53,46,46 62 | 0061,Male,70,46,56 63 | 0062,Male,19,46,55 64 | 0063,Female,67,47,52 65 | 0064,Female,54,47,59 66 | 0065,Male,63,48,51 67 | 0066,Male,18,48,59 68 | 0067,Female,43,48,50 69 | 0068,Female,68,48,48 70 | 0069,Male,19,48,59 71 | 0070,Female,32,48,47 72 | 0071,Male,70,49,55 73 | 0072,Female,47,49,42 74 | 0073,Female,60,50,49 75 | 0074,Female,60,50,56 76 | 0075,Male,59,54,47 77 | 0076,Male,26,54,54 78 | 0077,Female,45,54,53 79 | 0078,Male,40,54,48 80 | 0079,Female,23,54,52 81 | 0080,Female,49,54,42 82 | 0081,Male,57,54,51 83 | 0082,Male,38,54,55 84 | 0083,Male,67,54,41 85 | 0084,Female,46,54,44 86 | 0085,Female,21,54,57 87 | 0086,Male,48,54,46 88 | 0087,Female,55,57,58 89 | 0088,Female,22,57,55 90 | 0089,Female,34,58,60 91 | 0090,Female,50,58,46 92 | 0091,Female,68,59,55 93 | 0092,Male,18,59,41 94 | 0093,Male,48,60,49 95 | 0094,Female,40,60,40 96 | 0095,Female,32,60,42 97 | 0096,Male,24,60,52 98 | 0097,Female,47,60,47 99 | 0098,Female,27,60,50 100 | 0099,Male,48,61,42 101 | 0100,Male,20,61,49 102 | 0101,Female,23,62,41 103 | 0102,Female,49,62,48 104 | 0103,Male,67,62,59 105 | 0104,Male,26,62,55 106 | 0105,Male,49,62,56 107 | 0106,Female,21,62,42 108 | 0107,Female,66,63,50 109 | 0108,Male,54,63,46 110 | 0109,Male,68,63,43 111 | 0110,Male,66,63,48 112 | 0111,Male,65,63,52 113 | 0112,Female,19,63,54 114 | 0113,Female,38,64,42 115 | 0114,Male,19,64,46 116 | 0115,Female,18,65,48 117 | 0116,Female,19,65,50 118 | 0117,Female,63,65,43 119 | 0118,Female,49,65,59 120 | 0119,Female,51,67,43 121 | 0120,Female,50,67,57 122 | 0121,Male,27,67,56 123 | 0122,Female,38,67,40 124 | 0123,Female,40,69,58 125 | 0124,Male,39,69,91 126 | 0125,Female,23,70,29 127 | 0126,Female,31,70,77 128 | 0127,Male,43,71,35 129 | 0128,Male,40,71,95 130 | 0129,Male,59,71,11 131 | 0130,Male,38,71,75 132 | 0131,Male,47,71,9 133 | 0132,Male,39,71,75 134 | 0133,Female,25,72,34 135 | 0134,Female,31,72,71 136 | 0135,Male,20,73,5 137 | 0136,Female,29,73,88 138 | 0137,Female,44,73,7 139 | 0138,Male,32,73,73 140 | 0139,Male,19,74,10 141 | 0140,Female,35,74,72 142 | 0141,Female,57,75,5 143 | 0142,Male,32,75,93 144 | 0143,Female,28,76,40 145 | 0144,Female,32,76,87 146 | 0145,Male,25,77,12 147 | 0146,Male,28,77,97 148 | 0147,Male,48,77,36 149 | 0148,Female,32,77,74 150 | 0149,Female,34,78,22 151 | 0150,Male,34,78,90 152 | 0151,Male,43,78,17 153 | 0152,Male,39,78,88 154 | 0153,Female,44,78,20 155 | 0154,Female,38,78,76 156 | 0155,Female,47,78,16 157 | 0156,Female,27,78,89 158 | 0157,Male,37,78,1 159 | 0158,Female,30,78,78 160 | 0159,Male,34,78,1 161 | 0160,Female,30,78,73 162 | 0161,Female,56,79,35 163 | 0162,Female,29,79,83 164 | 0163,Male,19,81,5 165 | 0164,Female,31,81,93 166 | 0165,Male,50,85,26 167 | 0166,Female,36,85,75 168 | 0167,Male,42,86,20 169 | 0168,Female,33,86,95 170 | 0169,Female,36,87,27 171 | 0170,Male,32,87,63 172 | 0171,Male,40,87,13 173 | 0172,Male,28,87,75 174 | 0173,Male,36,87,10 175 | 0174,Male,36,87,92 176 | 0175,Female,52,88,13 177 | 0176,Female,30,88,86 178 | 0177,Male,58,88,15 179 | 0178,Male,27,88,69 180 | 0179,Male,59,93,14 181 | 0180,Male,35,93,90 182 | 0181,Female,37,97,32 183 | 0182,Female,32,97,86 184 | 0183,Male,46,98,15 185 | 0184,Female,29,98,88 186 | 0185,Female,41,99,39 187 | 0186,Male,30,99,97 188 | 0187,Female,54,101,24 189 | 0188,Male,28,101,68 190 | 0189,Female,41,103,17 191 | 0190,Female,36,103,85 192 | 0191,Female,34,103,23 193 | 0192,Female,32,103,69 194 | 0193,Male,33,113,8 195 | 0194,Female,38,113,91 196 | 0195,Female,47,120,16 197 | 0196,Female,35,120,79 198 | 0197,Female,45,126,28 199 | 0198,Male,32,126,74 200 | 0199,Male,32,137,18 201 | 0200,Male,30,137,83 -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # K-Means-clustering -------------------------------------------------------------------------------- /kmeanss.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | """ 3 | Created on Wed Apr 18 19:23:57 2018 4 | 5 | @K means algorithm 6 | 7 | """ 8 | 9 | import numpy as np 10 | import pandas as pd 11 | import matplotlib.pyplot as plt 12 | 13 | dataset=pd.read_csv('Customers.csv') 14 | 15 | X=dataset.iloc[:,[3,4]].values 16 | 17 | #Using the elbow method to find the optimal number of clusters 18 | 19 | from sklearn.cluster import KMeans 20 | 21 | wcss=[] 22 | for i in range(1,11): 23 | kmeans=KMeans(n_clusters=i, init='k-means++',random_state=0) 24 | kmeans.fit(X) 25 | wcss.append(kmeans.inertia_) 26 | 27 | plt.plot(range(1,11),wcss) 28 | plt.title('The Elbow Method') 29 | plt.xlabel('Number of Clusters') 30 | plt.ylabel('WCSS') 31 | plt.show() 32 | 33 | #Fitting K-MEans to the dataset 34 | kmeans=KMeans(n_clusters=5,init='k-means++',random_state=0) 35 | y_kmeans=kmeans.fit_predict(X) 36 | 37 | #Visualize the clusters 38 | 39 | plt.scatter(X[y_kmeans==0,0],X[y_kmeans==0,1],s=100,c='red',label='Cluster1') 40 | plt.scatter(X[y_kmeans==1,0],X[y_kmeans==1,1],s=100,c='blue',label='Cluster2') 41 | plt.scatter(X[y_kmeans==2,0],X[y_kmeans==2,1],s=100,c='green',label='Cluster3') 42 | plt.scatter(X[y_kmeans==3,0],X[y_kmeans==3,1],s=100,c='cyan',label='Cluster4') 43 | plt.scatter(X[y_kmeans==4,0],X[y_kmeans==4,1],s=100,c='magenta',label='Cluster5') 44 | 45 | plt.scatter(kmeans.cluster_centers_[:,0],kmeans.cluster_centers_[:,1],s=300,c='yellow',label='Centroids') 46 | 47 | plt.title('Clusters of customers') 48 | plt.xlabel('Annual Income(K$)') 49 | plt.ylabel('Spending Score(1-100)') 50 | plt.legend() 51 | plt.show() 52 | 53 | 54 | 55 | 56 | 57 | 58 | 59 | 60 | 61 | 62 | 63 | 64 | 65 | 66 | 67 | 68 | 69 | 70 | 71 | 72 | 73 | 74 | --------------------------------------------------------------------------------