K-Nearest Neighbors (K-NN)

#Data called ‘Social_Network_Ads’

User ID	Gender	Age	EstimatedSalary	Purchased
15624510	Male	19	19000	0
15810944	Male	35	20000	0
15668575	Female	26	43000	0
15603246	Female	27	57000	0
15804002	Male	19	76000	0
15728773	Male	27	58000	0
15598044	Female	27	84000	0
15694829	Female	32	150000	1
15600575	Male	25	33000	0
15727311	Female	35	65000	0
15570769	Female	26	80000	0
15606274	Female	26	52000	0
15746139	Male	20	86000	0
15704987	Male	32	18000	0
15628972	Male	18	82000	0
15697686	Male	29	80000	0
15733883	Male	47	25000	1
15617482	Male	45	26000	1
15704583	Male	46	28000	1
15621083	Female	48	29000	1
15649487	Male	45	22000	1
15736760	Female	47	49000	1
15714658	Male	48	41000	1
15599081	Female	45	22000	1
15705113	Male	46	23000	1
15631159	Male	47	20000	1
15792818	Male	49	28000	1
15633531	Female	47	30000	1
15744529	Male	29	43000	0
15669656	Male	31	18000	0
15581198	Male	31	74000	0
15729054	Female	27	137000	1
15573452	Female	21	16000	0
15776733	Female	28	44000	0
15724858	Male	27	90000	0
15713144	Male	35	27000	0
15690188	Female	33	28000	0
15689425	Male	30	49000	0
15671766	Female	26	72000	0
15782806	Female	27	31000	0
15764419	Female	27	17000	0
15591915	Female	33	51000	0
15772798	Male	35	108000	0
15792008	Male	30	15000	0
15715541	Female	28	84000	0
15639277	Male	23	20000	0
15798850	Male	25	79000	0
15776348	Female	27	54000	0
15727696	Male	30	135000	1
15793813	Female	31	89000	0
15694395	Female	24	32000	0
15764195	Female	18	44000	0
15744919	Female	29	83000	0
15671655	Female	35	23000	0
15654901	Female	27	58000	0
15649136	Female	24	55000	0
15775562	Female	23	48000	0
15807481	Male	28	79000	0
15642885	Male	22	18000	0
15789109	Female	32	117000	0
15814004	Male	27	20000	0
15673619	Male	25	87000	0
15595135	Female	23	66000	0
15583681	Male	32	120000	1
15605000	Female	59	83000	0
15718071	Male	24	58000	0
15679760	Male	24	19000	0
15654574	Female	23	82000	0
15577178	Female	22	63000	0
15595324	Female	31	68000	0
15756932	Male	25	80000	0
15726358	Female	24	27000	0
15595228	Female	20	23000	0
15782530	Female	33	113000	0
15592877	Male	32	18000	0
15651983	Male	34	112000	1
15746737	Male	18	52000	0
15774179	Female	22	27000	0
15667265	Female	28	87000	0
15655123	Female	26	17000	0
15595917	Male	30	80000	0
15668385	Male	39	42000	0
15709476	Male	20	49000	0
15711218	Male	35	88000	0
15798659	Female	30	62000	0
15663939	Female	31	118000	1
15694946	Male	24	55000	0
15631912	Female	28	85000	0
15768816	Male	26	81000	0
15682268	Male	35	50000	0
15684801	Male	22	81000	0
15636428	Female	30	116000	0
15809823	Male	26	15000	0
15699284	Female	29	28000	0
15786993	Female	29	83000	0
15709441	Female	35	44000	0
15710257	Female	35	25000	0
15582492	Male	28	123000	1
15575694	Male	35	73000	0
15756820	Female	28	37000	0
15766289	Male	27	88000	0
15593014	Male	28	59000	0
15584545	Female	32	86000	0
15675949	Female	33	149000	1
15672091	Female	19	21000	0
15801658	Male	21	72000	0
15706185	Female	26	35000	0
15789863	Male	27	89000	0
15720943	Male	26	86000	0
15697997	Female	38	80000	0
15665416	Female	39	71000	0
15660200	Female	37	71000	0
15619653	Male	38	61000	0
15773447	Male	37	55000	0
15739160	Male	42	80000	0
15689237	Male	40	57000	0
15679297	Male	35	75000	0
15591433	Male	36	52000	0
15642725	Male	40	59000	0
15701962	Male	41	59000	0
15811613	Female	36	75000	0
15741049	Male	37	72000	0
15724423	Female	40	75000	0
15574305	Male	35	53000	0
15678168	Female	41	51000	0
15697020	Female	39	61000	0
15610801	Male	42	65000	0
15745232	Male	26	32000	0
15722758	Male	30	17000	0
15792102	Female	26	84000	0
15675185	Male	31	58000	0
15801247	Male	33	31000	0
15725660	Male	30	87000	0
15638963	Female	21	68000	0
15800061	Female	28	55000	0
15578006	Male	23	63000	0
15668504	Female	20	82000	0
15687491	Male	30	107000	1
15610403	Female	28	59000	0
15741094	Male	19	25000	0
15807909	Male	19	85000	0
15666141	Female	18	68000	0
15617134	Male	35	59000	0
15783029	Male	30	89000	0
15622833	Female	34	25000	0
15746422	Female	24	89000	0
15750839	Female	27	96000	1
15749130	Female	41	30000	0
15779862	Male	29	61000	0
15767871	Male	20	74000	0
15679651	Female	26	15000	0
15576219	Male	41	45000	0
15699247	Male	31	76000	0
15619087	Female	36	50000	0
15605327	Male	40	47000	0
15610140	Female	31	15000	0
15791174	Male	46	59000	0
15602373	Male	29	75000	0
15762605	Male	26	30000	0
15598840	Female	32	135000	1
15744279	Male	32	100000	1
15670619	Male	25	90000	0
15599533	Female	37	33000	0
15757837	Male	35	38000	0
15697574	Female	33	69000	0
15578738	Female	18	86000	0
15762228	Female	22	55000	0
15614827	Female	35	71000	0
15789815	Male	29	148000	1
15579781	Female	29	47000	0
15587013	Male	21	88000	0
15570932	Male	34	115000	0
15794661	Female	26	118000	0
15581654	Female	34	43000	0
15644296	Female	34	72000	0
15614420	Female	23	28000	0
15609653	Female	35	47000	0
15594577	Male	25	22000	0
15584114	Male	24	23000	0
15673367	Female	31	34000	0
15685576	Male	26	16000	0
15774727	Female	31	71000	0
15694288	Female	32	117000	1
15603319	Male	33	43000	0
15759066	Female	33	60000	0
15814816	Male	31	66000	0
15724402	Female	20	82000	0
15571059	Female	33	41000	0
15674206	Male	35	72000	0
15715160	Male	28	32000	0
15730448	Male	24	84000	0
15662067	Female	19	26000	0
15779581	Male	29	43000	0
15662901	Male	19	70000	0
15689751	Male	28	89000	0
15667742	Male	34	43000	0
15738448	Female	30	79000	0
15680243	Female	20	36000	0
15745083	Male	26	80000	0
15708228	Male	35	22000	0
15628523	Male	35	39000	0
15708196	Male	49	74000	0
15735549	Female	39	134000	1
15809347	Female	41	71000	0
15660866	Female	58	101000	1
15766609	Female	47	47000	0
15654230	Female	55	130000	1
15794566	Female	52	114000	0
15800890	Female	40	142000	1
15697424	Female	46	22000	0
15724536	Female	48	96000	1
15735878	Male	52	150000	1
15707596	Female	59	42000	0
15657163	Male	35	58000	0
15622478	Male	47	43000	0
15779529	Female	60	108000	1
15636023	Male	49	65000	0
15582066	Male	40	78000	0
15666675	Female	46	96000	0
15732987	Male	59	143000	1
15789432	Female	41	80000	0
15663161	Male	35	91000	1
15694879	Male	37	144000	1
15593715	Male	60	102000	1
15575002	Female	35	60000	0
15622171	Male	37	53000	0
15795224	Female	36	126000	1
15685346	Male	56	133000	1
15691808	Female	40	72000	0
15721007	Female	42	80000	1
15794253	Female	35	147000	1
15694453	Male	39	42000	0
15813113	Male	40	107000	1
15614187	Male	49	86000	1
15619407	Female	38	112000	0
15646227	Male	46	79000	1
15660541	Male	40	57000	0
15753874	Female	37	80000	0
15617877	Female	46	82000	0
15772073	Female	53	143000	1
15701537	Male	42	149000	1
15736228	Male	38	59000	0
15780572	Female	50	88000	1
15769596	Female	56	104000	1
15586996	Female	41	72000	0
15722061	Female	51	146000	1
15638003	Female	35	50000	0
15775590	Female	57	122000	1
15730688	Male	41	52000	0
15753102	Female	35	97000	1
15810075	Female	44	39000	0
15723373	Male	37	52000	0
15795298	Female	48	134000	1
15584320	Female	37	146000	1
15724161	Female	50	44000	0
15750056	Female	52	90000	1
15609637	Female	41	72000	0
15794493	Male	40	57000	0
15569641	Female	58	95000	1
15815236	Female	45	131000	1
15811177	Female	35	77000	0
15680587	Male	36	144000	1
15672821	Female	55	125000	1
15767681	Female	35	72000	0
15600379	Male	48	90000	1
15801336	Female	42	108000	1
15721592	Male	40	75000	0
15581282	Male	37	74000	0
15746203	Female	47	144000	1
15583137	Male	40	61000	0
15680752	Female	43	133000	0
15688172	Female	59	76000	1
15791373	Male	60	42000	1
15589449	Male	39	106000	1
15692819	Female	57	26000	1
15727467	Male	57	74000	1
15734312	Male	38	71000	0
15764604	Male	49	88000	1
15613014	Female	52	38000	1
15759684	Female	50	36000	1
15609669	Female	59	88000	1
15685536	Male	35	61000	0
15750447	Male	37	70000	1
15663249	Female	52	21000	1
15638646	Male	48	141000	0
15734161	Female	37	93000	1
15631070	Female	37	62000	0
15761950	Female	48	138000	1
15649668	Male	41	79000	0
15713912	Female	37	78000	1
15586757	Male	39	134000	1
15596522	Male	49	89000	1
15625395	Male	55	39000	1
15760570	Male	37	77000	0
15566689	Female	35	57000	0
15725794	Female	36	63000	0
15673539	Male	42	73000	1
15705298	Female	43	112000	1
15675791	Male	45	79000	0
15747043	Male	46	117000	1
15736397	Female	58	38000	1
15678201	Male	48	74000	1
15720745	Female	37	137000	1
15637593	Male	37	79000	1
15598070	Female	40	60000	0
15787550	Male	42	54000	0
15603942	Female	51	134000	0
15733973	Female	47	113000	1
15596761	Male	36	125000	1
15652400	Female	38	50000	0
15717893	Female	42	70000	0
15622585	Male	39	96000	1
15733964	Female	38	50000	0
15753861	Female	49	141000	1
15747097	Female	39	79000	0
15594762	Female	39	75000	1
15667417	Female	54	104000	1
15684861	Male	35	55000	0
15742204	Male	45	32000	1
15623502	Male	36	60000	0
15774872	Female	52	138000	1
15611191	Female	53	82000	1
15674331	Male	41	52000	0
15619465	Female	48	30000	1
15575247	Female	48	131000	1
15695679	Female	41	60000	0
15713463	Male	41	72000	0
15785170	Female	42	75000	0
15796351	Male	36	118000	1
15639576	Female	47	107000	1
15693264	Male	38	51000	0
15589715	Female	48	119000	1
15769902	Male	42	65000	0
15587177	Male	40	65000	0
15814553	Male	57	60000	1
15601550	Female	36	54000	0
15664907	Male	58	144000	1
15612465	Male	35	79000	0
15810800	Female	38	55000	0
15665760	Male	39	122000	1
15588080	Female	53	104000	1
15776844	Male	35	75000	0
15717560	Female	38	65000	0
15629739	Female	47	51000	1
15729908	Male	47	105000	1
15716781	Female	41	63000	0
15646936	Male	53	72000	1
15768151	Female	54	108000	1
15579212	Male	39	77000	0
15721835	Male	38	61000	0
15800515	Female	38	113000	1
15591279	Male	37	75000	0
15587419	Female	42	90000	1
15750335	Female	37	57000	0
15699619	Male	36	99000	1
15606472	Male	60	34000	1
15778368	Male	54	70000	1
15671387	Female	41	72000	0
15573926	Male	40	71000	1
15709183	Male	42	54000	0
15577514	Male	43	129000	1
15778830	Female	53	34000	1
15768072	Female	47	50000	1
15768293	Female	42	79000	0
15654456	Male	42	104000	1
15807525	Female	59	29000	1
15574372	Female	58	47000	1
15671249	Male	46	88000	1
15779744	Male	38	71000	0
15624755	Female	54	26000	1
15611430	Female	60	46000	1
15774744	Male	60	83000	1
15629885	Female	39	73000	0
15708791	Male	59	130000	1
15793890	Female	37	80000	0
15646091	Female	46	32000	1
15596984	Female	46	74000	0
15800215	Female	42	53000	0
15577806	Male	41	87000	1
15749381	Female	58	23000	1
15683758	Male	42	64000	0
15670615	Male	48	33000	1
15715622	Female	44	139000	1
15707634	Male	49	28000	1
15806901	Female	57	33000	1
15775335	Male	56	60000	1
15724150	Female	49	39000	1
15627220	Male	39	71000	0
15672330	Male	47	34000	1
15668521	Female	48	35000	1
15807837	Male	48	33000	1
15592570	Male	47	23000	1
15748589	Female	45	45000	1
15635893	Male	60	42000	1
15757632	Female	39	59000	0
15691863	Female	46	41000	1
15706071	Male	51	23000	1
15654296	Female	50	20000	1
15755018	Male	36	33000	0
15594041	Female	49	36000	1

# Importing the dataset

dataset = read.csv('Social_Network_Ads.csv')

dataset = dataset[3:5]

# Encoding the target feature as factor

dataset$Purchased = factor(dataset$Purchased, levels = c(0, 1))

# Splitting the dataset into the Training set and Test set

# install.packages('caTools')

library(caTools)

set.seed(123)

split = sample.split(dataset$Purchased, SplitRatio = 0.75)

training_set = subset(dataset, split == TRUE)

test_set = subset(dataset, split == FALSE)

# Feature Scaling

training_set[-3] = scale(training_set[-3])

test_set[-3] = scale(test_set[-3])

# Fitting K-NN to the Training set and Predicting the Test set results

library(class)

y_pred = knn(train = training_set[, -3],

             test = test_set[, -3],

             cl = training_set[, 3],

             k = 5,

             prob = TRUE)

# Making the Confusion Matrix

cm = table(test_set[, 3], y_pred)

solution

cm

y_pred

     0  1

  0 59  5

  1  6 30

# Visualising the Training set results

library(ElemStatLearn)

set = training_set

X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)

X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)

grid_set = expand.grid(X1, X2)

colnames(grid_set) = c('Age', 'EstimatedSalary')

y_grid = knn(train = training_set[, -3], test = grid_set, cl = training_set[, 3], k = 5)

plot(set[, -3],

     main = 'K-NN (Training set)',

     xlab = 'Age', ylab = 'Estimated Salary',

     xlim = range(X1), ylim = range(X2))

contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)

points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))

points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))

# Visualising the Test set results

library(ElemStatLearn)

set = test_set

X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)

X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)

grid_set = expand.grid(X1, X2)

colnames(grid_set) = c('Age', 'EstimatedSalary')

y_grid = knn(train = training_set[, -3], test = grid_set, cl = training_set[, 3], k = 5)

plot(set[, -3],

     main = 'K-NN (Test set)',

     xlab = 'Age', ylab = 'Estimated Salary',

     xlim = range(X1), ylim = range(X2))

contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)

points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))

points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))