Download as pdf or txt
Download as pdf or txt
You are on page 1of 30

SOURCE CODES:

setwd("F:/project")

> Telecom = read_excel("Cellphone-1.xlsx",sheet = "Data")

> str(Telecom)

Classes ‘tbl_df’, ‘tbl’ and 'data.frame': 3333 obs. of 11 variables:

$ Churn : num 0 0 0 0 0 0 0 0 0 0 ...

$ AccountWeeks : num 128 107 137 84 75 118 121 147 117 141 ...

$ ContractRenewal: num 1 1 1 0 0 0 1 0 1 0 ...

$ DataPlan : num 1 1 0 0 0 0 1 0 0 1 ...

$ DataUsage : num 2.7 3.7 0 0 0 0 2.03 0 0.19 3.02 ...

$ CustServCalls : num 1 1 0 2 3 0 3 0 1 0 ...

$ DayMins : num 265 162 243 299 167 ...

$ DayCalls : num 110 123 114 71 113 98 88 79 97 84 ...

$ MonthlyCharge : num 89 82 52 57 41 57 87.3 36 63.9 93.2 ...

$ OverageFee : num 9.87 9.78 6.06 3.1 7.42 ...

$ RoamMins : num 10 13.7 12.2 6.6 10.1 6.3 7.5 7.1 8.7 11.2 ...

> dim(Telecom)

[1] 3333 11

> sum(is.na(Telecom))

[1] 0

> min(Telecom$AccountWeeks); max(Telecom$AccountWeeks)

[1] 1

[1] 243

> summary(Telecom)

Churn AccountWeeks ContractRenewal DataPlan

Min. :0.0000 Min. : 1.0 Min. :0.0000 Min. :0.0000

1st Qu.:0.0000 1st Qu.: 74.0 1st Qu.:1.0000 1st Qu.:0.0000

Median :0.0000 Median :101.0 Median :1.0000 Median :0.0000

Mean :0.1449 Mean :101.1 Mean :0.9031 Mean :0.2766

3rd Qu.:0.0000 3rd Qu.:127.0 3rd Qu.:1.0000 3rd Qu.:1.0000


Max. :1.0000 Max. :243.0 Max. :1.0000 Max. :1.0000

DataUsage CustServCalls DayMins DayCalls MonthlyCharge

Min. :0.0000 Min. :0.000 Min. : 0.0 Min. : 0.0 Min. : 14.00

1st Qu.:0.0000 1st Qu.:1.000 1st Qu.:143.7 1st Qu.: 87.0 1st Qu.: 45.00

Median :0.0000 Median :1.000 Median :179.4 Median :101.0 Median : 53.50

Mean :0.8165 Mean :1.563 Mean :179.8 Mean :100.4 Mean : 56.31

3rd Qu.:1.7800 3rd Qu.:2.000 3rd Qu.:216.4 3rd Qu.:114.0 3rd Qu.: 66.20

Max. :5.4000 Max. :9.000 Max. :350.8 Max. :165.0 Max. :111.30

OverageFee RoamMins

Min. : 0.00 Min. : 0.00

1st Qu.: 8.33 1st Qu.: 8.50

Median :10.07 Median :10.30

Mean :10.05 Mean :10.24

3rd Qu.:11.77 3rd Qu.:12.10

Max. :18.19 Max. :20.00

> boxplot(Telecom)

> par(mfrow=c(3,3))

> hist(Telecom$AccountWeeks)

> hist(Telecom$DataUsage)

> hist(Telecom$CustServCalls)

> hist(Telecom$DayMins)

> hist(Telecom$DayCalls)

> hist(Telecom$DataUsage)

> hist(Telecom$MonthlyCharge)

> hist(Telecom$OverageFee)

> hist(Telecom$RoamMins)

> attach(Telecom)

The following objects are masked from Telecom (pos = 4):

AccountWeeks, Churn, ContractRenewal, CustServCalls, DataPlan,

DataUsage, DayCalls, DayMins, MonthlyCharge, OverageFee, RoamMins


> library(ggplot2)

> library(corrplot)

> corrplot(cor(Telecom))

> qplot(AccountWeeks,DataUsage,data=Telecom)

> qplot(AccountWeeks,DayMins,data=Telecom)

> qplot(AccountWeeks,MonthlyCharge,data=Telecom)

> qplot(AccountWeeks,OverageFee,data=Telecom)

> qplot(AccountWeeks,RoamMins,data=Telecom)

> hist(Churn,CustServCalls,Telecom)

Error in freq && !equidist : invalid 'x' type in 'x && y'

> numeric.var = sapply(Telecom, is.numeric)

> corr.matrix <- cor(Telecom[,numeric.var])

> corrplot(corr.matrix, main="\n\nCorrelation Plot for Numerical Variables", method="number")

> Telecom$Dataplan = NULL

> Telecom$DataUsage = NULL

> str(Telecom)

Classes ‘tbl_df’, ‘tbl’ and 'data.frame': 3333 obs. of 10 variables:

$ Churn : num 0 0 0 0 0 0 0 0 0 0 ...

$ AccountWeeks : num 128 107 137 84 75 118 121 147 117 141 ...

$ ContractRenewal: num 1 1 1 0 0 0 1 0 1 0 ...

$ DataPlan : num 1 1 0 0 0 0 1 0 0 1 ...

$ CustServCalls : num 1 1 0 2 3 0 3 0 1 0 ...

$ DayMins : num 265 162 243 299 167 ...

$ DayCalls : num 110 123 114 71 113 98 88 79 97 84 ...

$ MonthlyCharge : num 89 82 52 57 41 57 87.3 36 63.9 93.2 ...

$ OverageFee : num 9.87 9.78 6.06 3.1 7.42 ...

$ RoamMins : num 10 13.7 12.2 6.6 10.1 6.3 7.5 7.1 8.7 11.2 ...

> churnrate = table(Telecom$Churn) / nrow(Telecom)

> churnrate
0 1

0.8550855 0.1449145

> library(class)

> library(gmodels)

> library(datasets)

> summary(Telecom)

Churn AccountWeeks ContractRenewal DataPlan CustServCalls

Min. :0.0000 Min. : 1.0 Min. :0.0000 Min. :0.0000 Min. :0.000

1st Qu.:0.0000 1st Qu.: 74.0 1st Qu.:1.0000 1st Qu.:0.0000 1st Qu.:1.000

Median :0.0000 Median :101.0 Median :1.0000 Median :0.0000 Median :1.000

Mean :0.1449 Mean :101.1 Mean :0.9031 Mean :0.2766 Mean :1.563

3rd Qu.:0.0000 3rd Qu.:127.0 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:2.000

Max. :1.0000 Max. :243.0 Max. :1.0000 Max. :1.0000 Max. :9.000

DayMins DayCalls MonthlyCharge OverageFee RoamMins

Min. : 0.0 Min. : 0.0 Min. : 14.00 Min. : 0.00 Min. : 0.00

1st Qu.:143.7 1st Qu.: 87.0 1st Qu.: 45.00 1st Qu.: 8.33 1st Qu.: 8.50

Median :179.4 Median :101.0 Median : 53.50 Median :10.07 Median :10.30

Mean :179.8 Mean :100.4 Mean : 56.31 Mean :10.05 Mean :10.24

3rd Qu.:216.4 3rd Qu.:114.0 3rd Qu.: 66.20 3rd Qu.:11.77 3rd Qu.:12.10

Max. :350.8 Max. :165.0 Max. :111.30 Max. :18.19 Max. :20.00

> Telecom$Churn = as.factor(Telecom$Churn)

> mydata=createDataPartition(y=Telecom$Churn,p=0.7,list=FALSE)

> set.seed(123)

> trainData=Telecom[mydata,]

> testData=Telecom[-mydata,]

> dim(trainData)

[1] 2334 10

> dim(testData)

[1] 999 10

> print(sum(trainData$Churn=="1")/nrow(trainData))

[1] 0.1452442
> lmodel=glm(Churn~.,family = binomial(link = "logit"),data=trainData)

> print(summary(lmodel))

Call:

glm(formula = Churn ~ ., family = binomial(link = "logit"), data = trainData)

Deviance Residuals:

Min 1Q Median 3Q Max

-2.0553 -0.5045 -0.3431 -0.1992 3.0525

Coefficients:

Estimate Std. Error z value Pr(>|z|)

(Intercept) -6.2861356 0.6535782 -9.618 < 2e-16 ***

AccountWeeks 0.0003457 0.0016766 0.206 0.83665

ContractRenewal -1.9676217 0.1713300 -11.484 < 2e-16 ***

DataPlan -1.3577425 0.6468784 -2.099 0.03582 *

CustServCalls 0.5539090 0.0483978 11.445 < 2e-16 ***

DayMins 0.0107140 0.0039687 2.700 0.00694 **

DayCalls 0.0039345 0.0033077 1.190 0.23424

MonthlyCharge 0.0119062 0.0220000 0.541 0.58838

OverageFee 0.1372180 0.0460986 2.977 0.00291 **

RoamMins 0.0833328 0.0261358 3.188 0.00143 **

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

Null deviance: 1934.3 on 2333 degrees of freedom

Residual deviance: 1515.6 on 2324 degrees of freedom

AIC: 1535.6
Number of Fisher Scoring iterations: 6

> vif(lmodel)

AccountWeeks ContractRenewal DataPlan CustServCalls DayMins

1.003981 1.055954 13.715112 1.100637 10.060967

DayCalls MonthlyCharge OverageFee RoamMins

1.007451 26.125413 2.898266 1.178697

> lrtest(lmodel)

Likelihood ratio test

Model 1: Churn ~ AccountWeeks + ContractRenewal + DataPlan + CustServCalls +

DayMins + DayCalls + MonthlyCharge + OverageFee + RoamMins

Model 2: Churn ~ 1

#Df LogLik Df Chisq Pr(>Chisq)

1 10 -757.81

2 1 -967.14 -9 418.66 < 2.2e-16 ***

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

> anova(lmodel, test="Chisq")

Analysis of Deviance Table

Model: binomial, link: logit

Response: Churn

Terms added sequentially (first to last)

Df Deviance Resid. Df Resid. Dev Pr(>Chi)

NULL 2333 1934.3

AccountWeeks 1 0.115 2332 1934.2 0.734750


ContractRenewal 1 121.008 2331 1813.2 < 2.2e-16 ***

DataPlan 1 33.934 2330 1779.2 5.702e-09 ***

CustServCalls 1 111.989 2329 1667.2 < 2.2e-16 ***

DayMins 1 104.501 2328 1562.7 < 2.2e-16 ***

DayCalls 1 1.206 2327 1561.5 0.272175

MonthlyCharge 1 31.286 2326 1530.2 2.227e-08 ***

OverageFee 1 4.268 2325 1526.0 0.038842 *

RoamMins 1 10.354 2324 1515.6 0.001292 **

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

> pr2(lmodel)

Error in pr2(lmodel) : could not find function "pr2"

> ROCRpred=prediction(predTest,testData$Churn)

Error in is.data.frame(predictions) : object 'predTest' not found

> fitted.results = predict(lmodel,newdata=testing,type='response')

> fitted.results = ifelse(fitted.results > 0.5,1,0)

> misClasificError = mean(fitted.results != testing$Churn)

> print(paste('Logistic Regression Accuracy',1-misClasificError))

[1] "Logistic Regression Accuracy 0.85985985985986"

> print("Confusion Matrix for Logistic Regression"); table(testing$Churn, fitted.results > 0.5)

[1] "Confusion Matrix for Logistic Regression"

FALSE TRUE

0 827 28

1 112 32

> ROCRpred=prediction(lmodel,testData$Churn)

Error in prediction(lmodel, testData$Churn) :

Number of cross-validation runs must be equal for predictions and labels.

> lmodel2=glm(formula = Churn ~ AccountWeeks + ContractRenewal + CustServCalls + DayCalls + DayMins +


OverageFee + RoamMins, family = binomial, data = trainData)

> summary(lmodel2)
Call:

glm(formula = Churn ~ AccountWeeks + ContractRenewal + CustServCalls +

DayCalls + DayMins + OverageFee + RoamMins, family = binomial,

data = trainData)

Deviance Residuals:

Min 1Q Median 3Q Max

-1.9708 -0.5214 -0.3588 -0.2287 2.9352

Coefficients:

Estimate Std. Error z value Pr(>|z|)

(Intercept) -6.308e+00 6.421e-01 -9.825 < 2e-16 ***

AccountWeeks -1.046e-05 1.670e-03 -0.006 0.995000

ContractRenewal -1.920e+00 1.682e-01 -11.418 < 2e-16 ***

CustServCalls 5.448e-01 4.768e-02 11.425 < 2e-16 ***

DayCalls 3.590e-03 3.263e-03 1.100 0.271201

DayMins 1.244e-02 1.266e-03 9.829 < 2e-16 ***

OverageFee 1.451e-01 2.706e-02 5.363 8.2e-08 ***

RoamMins 8.795e-02 2.411e-02 3.648 0.000264 ***

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

Null deviance: 1934.3 on 2333 degrees of freedom

Residual deviance: 1554.7 on 2326 degrees of freedom

AIC: 1570.7

Number of Fisher Scoring iterations: 5


> lrtest(lmodel2)

Likelihood ratio test

Model 1: Churn ~ AccountWeeks + ContractRenewal + CustServCalls + DayCalls +

DayMins + OverageFee + RoamMins

Model 2: Churn ~ 1

#Df LogLik Df Chisq Pr(>Chisq)

1 8 -777.35

2 1 -967.14 -7 379.59 < 2.2e-16 ***

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

> exp(coefficients(lmodel2))

(Intercept) AccountWeeks ContractRenewal CustServCalls DayCalls

0.001821575 0.999989535 0.146577427 1.724210932 1.003596874

DayMins OverageFee RoamMins

1.012522052 1.156162339 1.091929137

> exp(coefficients(lmodel))

(Intercept) AccountWeeks ContractRenewal DataPlan CustServCalls

0.001861941 1.000345730 0.139788918 0.257240832 1.740041634

DayMins DayCalls MonthlyCharge OverageFee RoamMins

1.010771582 1.003942288 1.011977335 1.147078233 1.086903477

> library(pscl)

> vif(lmodel2)

AccountWeeks ContractRenewal CustServCalls DayCalls DayMins

1.001995 1.048199 1.090312 1.005826 1.042210

OverageFee RoamMins

1.027652 1.013871

> exp(cbind(OR=coef(lmodel), confint(lmodel)))

Waiting for profiling to be done...

OR 2.5 % 97.5 %

(Intercept) 0.001861941 0.0005079769 0.006595388


AccountWeeks 1.000345730 0.9970605030 1.003639008

ContractRenewal 0.139788918 0.0997948023 0.195471858

DataPlan 0.257240832 0.0705683186 0.894293449

CustServCalls 1.740041634 1.5838161710 1.915049172

DayMins 1.010771582 1.0029369394 1.018685566

DayCalls 1.003942288 0.9974623414 1.010487466

MonthlyCharge 1.011977335 0.9693289613 1.056782262

OverageFee 1.147078233 1.0480111034 1.255799098

RoamMins 1.086903477 1.0329465685 1.144463931

> pR2(lmodel2)

fitting null model for pseudo-r2

llh llhNull G2 McFadden r2ML r2CU

-777.3450017 -967.1400908 379.5901782 0.1962436 0.1500987 0.2664153

> confusionMatrix(trainData$Churn)

Error in is.factor(reference) :

argument "reference" is missing, with no default

> pred=predict(rf_model, newdata = training)

> predictglm=predict(lmodel2,type="response",newdata=training)

> predictglm

1 2 3 4 5 6 7

0.055244690 0.264484362 0.407305938 0.151309272 0.451610888 0.235784283 0.030726392

8 9 10 11 12 13 14

0.018147025 0.189685333 0.285866309 0.752697181 0.179901815 0.065177658 0.093862034

15 16 17 18 19 20 21

0.038882490 0.064498135 0.014993121 0.023610962 0.014389223 0.050086694 0.096266915

22 23 24 25 26 27 28

0.045420345 0.037623708 0.029241858 0.106680486 0.100776266 0.331898667 0.029496974

29 30 31 32 33 34 35

0.034770305 0.628862013 0.065855263 0.067852410 0.085904364 0.027090311 0.047714705

36 37 38 39 40 41 42

0.339919383 0.235915811 0.115243485 0.122749579 0.293088537 0.072206629 0.023103544


43 44 45 46 47 48 49

0.068755674 0.107258171 0.062356680 0.233918361 0.175688550 0.037159184 0.391755142

50 51 52 53 54 55 56

0.100665390 0.264915201 0.273501072 0.194784200 0.087740128 0.062530112 0.037378493

57 58 59 60 61 62 63

0.146971395 0.027046757 0.059015681 0.187948891 0.725707846 0.105595218 0.218262238

64 65 66 67 68 69 70

0.132380745 0.047674796 0.036137849 0.142325863 0.268645629 0.069811745 0.199005195

71 72 73 74 75 76 77

0.194956148 0.013916877 0.038506972 0.048765050 0.387496103 0.266489613 0.024343726

78 79 80 81 82 83 84

0.024871205 0.183219678 0.096123930 0.235649561 0.517287827 0.047058360 0.208073535

85 86 87 88 89 90 91

0.036194044 0.126098241 0.159986837 0.039723922 0.093496455 0.055224029 0.161811037

92 93 94 95 96 97 98

0.030465634 0.181316399 0.029836842 0.131283236 0.244423852 0.398195386 0.284073480

99 100 101 102 103 104 105

0.248531610 0.043941016 0.097410965 0.088841575 0.048787379 0.142159181 0.119183266

106 107 108 109 110 111 112

0.283530117 0.065401609 0.084791377 0.068645908 0.363509855 0.056871813 0.098102928

113 114 115 116 117 118 119

0.013242985 0.089082268 0.225866596 0.017493632 0.049219592 0.237068474 0.069551693

120 121 122 123 124 125 126

0.041921542 0.171720096 0.084526869 0.087977763 0.032940211 0.194580366 0.026153588

127 128 129 130 131 132 133

0.219521111 0.241060657 0.762075293 0.083909669 0.062600188 0.207278711 0.789047769

134 135 136 137 138 139 140

0.016631223 0.292780404 0.035143823 0.015275471 0.026653373 0.111883725 0.031016663

141 142 143 144 145 146 147

0.046155016 0.350597917 0.926931809 0.010573622 0.181747645 0.241962715 0.157692682

148 149 150 151 152 153 154


0.029392371 0.125658262 0.177618800 0.195229385 0.360053575 0.038908328 0.760832267

155 156 157 158 159 160 161

0.151540349 0.023785342 0.116293464 0.258268498 0.026703529 0.152719263 0.028099236

162 163 164 165 166 167 168

0.063538300 0.220623179 0.667106591 0.456912242 0.276637517 0.038336591 0.360824030

169 170 171 172 173 174 175

0.264649262 0.069435437 0.050729734 0.007846075 0.050510584 0.241910201 0.168620148

176 177 178 179 180 181 182

0.011803533 0.004501644 0.349314742 0.230604473 0.238407022 0.326986708 0.032011701

183 184 185 186 187 188 189

0.042373584 0.086136350 0.047603529 0.041957878 0.035501890 0.048040539 0.076507024

190 191 192 193 194 195 196

0.177169140 0.124984047 0.004982398 0.344389586 0.085891097 0.026834074 0.039612861

197 198 199 200 201 202 203

0.283699857 0.313397460 0.048954975 0.704088870 0.096035930 0.131108052 0.082956333

204 205 206 207 208 209 210

0.144662528 0.080838339 0.187333127 0.231163200 0.067178640 0.008113975 0.223663979

211 212 213 214 215 216 217

0.032393913 0.069800638 0.043567910 0.323541553 0.045544018 0.053760643 0.100422342

218 219 220 221 222 223 224

0.082025230 0.230814034 0.635182022 0.342601214 0.191417453 0.108833795 0.037941719

225 226 227 228 229 230 231

0.024760009 0.040554960 0.045093920 0.067987668 0.512189007 0.034698620 0.033083750

232 233 234 235 236 237 238

0.033992687 0.199479764 0.007344073 0.018553966 0.145279889 0.067899431 0.089805036

239 240 241 242 243 244 245

0.291716069 0.529706008 0.046149097 0.044368502 0.052001398 0.048817521 0.083746201

246 247 248 249 250 251 252

0.222010938 0.061457142 0.101930015 0.063779283 0.008963478 0.025205278 0.035988246

253 254 255 256 257 258 259

0.131659734 0.069192076 0.025670472 0.146963937 0.677764954 0.028008689 0.059112358


260 261 262 263 264 265 266

0.245769507 0.047702691 0.060391792 0.097754383 0.019859884 0.110079405 0.148790580

267 268 269 270 271 272 273

0.186701843 0.091566627 0.051067727 0.073327087 0.421820893 0.093967491 0.047720898

274 275 276 277 278 279 280

0.095241813 0.410089077 0.440256011 0.145673854 0.078252866 0.040211502 0.114668484

281 282 283 284 285 286 287

0.083595511 0.021607127 0.441161198 0.135887351 0.066100090 0.017839388 0.100228649

288 289 290 291 292 293 294

0.040797082 0.035699478 0.038523187 0.090705746 0.256346923 0.330205186 0.008689705

295 296 297 298 299 300 301

0.178790320 0.256751325 0.072053409 0.055850657 0.033022396 0.078903850 0.016887315

302 303 304 305 306 307 308

0.236878939 0.157705586 0.056657884 0.201511924 0.195214200 0.244325728 0.069549922

309 310 311 312 313 314 315

0.356959161 0.022384058 0.023406153 0.088546835 0.112903551 0.126570640 0.074486048

316 317 318 319 320 321 322

0.115206912 0.071966148 0.120784989 0.137523109 0.052839818 0.171174775 0.031812958

323 324 325 326 327 328 329

0.157120053 0.375048244 0.130018240 0.163758053 0.036175161 0.388910162 0.083999078

330 331 332 333 334 335 336

0.030718091 0.253350041 0.296944575 0.030085922 0.143304982 0.179147616 0.134483134

337 338 339 340 341 342 343

0.013436083 0.012622716 0.061707906 0.243976253 0.068859392 0.141560797 0.131064937

344 345 346 347 348 349 350

0.077109757 0.031233184 0.093523742 0.101698761 0.028275708 0.019808672 0.129548349

351 352 353 354 355 356 357

0.330306931 0.011827513 0.092578852 0.063689055 0.067160162 0.095760121 0.516835537

358 359 360 361 362 363 364

0.384648454 0.060844342 0.358178674 0.080512026 0.131313819 0.549272782 0.043170854

365 366 367 368 369 370 371


0.205028509 0.336616986 0.038359969 0.386802642 0.087850969 0.042053132 0.043804469

372 373 374 375 376 377 378

0.065288147 0.076177816 0.129870078 0.819740301 0.115140541 0.065458851 0.038779886

379 380 381 382 383 384 385

0.064897628 0.073824579 0.184708962 0.018368215 0.049767902 0.068669428 0.049738631

386 387 388 389 390 391 392

0.196966385 0.104084141 0.055240760 0.755780497 0.691388371 0.011179481 0.158721290

393 394 395 396 397 398 399

0.185452785 0.540372360 0.118610348 0.077125596 0.111474047 0.029832098 0.065655459

400 401 402 403 404 405 406

0.041668254 0.207477816 0.128785187 0.089776488 0.785909207 0.062827538 0.152759576

407 408 409 410 411 412 413

0.271167549 0.275608648 0.073192003 0.058423416 0.211570590 0.037851647 0.133983514

414 415 416 417 418 419 420

0.010586634 0.014919180 0.291019280 0.017113857 0.295582580 0.041698017 0.185006069

421 422 423 424 425 426 427

0.033757680 0.042376542 0.049343992 0.204814090 0.040603883 0.069740630 0.081959784

428 429 430 431 432 433 434

0.492757919 0.056541035 0.056353265 0.128402337 0.060638015 0.206503794 0.504395376

435 436 437 438 439 440 441

0.181328684 0.047927543 0.410189562 0.230635460 0.061372823 0.566582137 0.079306236

442 443 444 445 446 447 448

0.022075318 0.092072928 0.151580504 0.165950037 0.186677652 0.024058537 0.230974666

449 450 451 452 453 454 455

0.049346235 0.016802157 0.051112585 0.132075791 0.017606055 0.137138541 0.054926393

456 457 458 459 460 461 462

0.052471262 0.120419045 0.130678044 0.267725487 0.116735984 0.032830993 0.004515576

463 464 465 466 467 468 469

0.260903087 0.087296282 0.145539310 0.170663317 0.068673838 0.028636655 0.100114064

470 471 472 473 474 475 476

0.015378516 0.250767188 0.146583601 0.075410983 0.052502929 0.117346309 0.162583630


477 478 479 480 481 482 483

0.022354389 0.133321091 0.068050663 0.298611951 0.069482714 0.130991001 0.053613388

484 485 486 487 488 489 490

0.054510543 0.035400347 0.603773333 0.012477149 0.045527016 0.080858437 0.572201442

491 492 493 494 495 496 497

0.101549542 0.249642783 0.100272577 0.547769355 0.040363230 0.037064198 0.053612929

498 499 500 501 502 503 504

0.009279076 0.046005113 0.178914896 0.048003890 0.130240348 0.086240414 0.224315640

505 506 507 508 509 510 511

0.334086963 0.127250400 0.074363794 0.081502235 0.051187962 0.117681238 0.020427403

512 513 514 515 516 517 518

0.204631687 0.112390843 0.176760007 0.081415639 0.027802758 0.091079226 0.314291368

519 520 521 522 523 524 525

0.048397026 0.114590760 0.323024505 0.169127550 0.252156622 0.413063662 0.059215987

526 527 528 529 530 531 532

0.077879184 0.013445082 0.512858401 0.090383770 0.050593136 0.016639312 0.144084379

533 534 535 536 537 538 539

0.089148524 0.016870498 0.157170655 0.029481452 0.049012165 0.050315934 0.292595507

540 541 542 543 544 545 546

0.080060454 0.099802575 0.143259295 0.255198264 0.031420870 0.101434017 0.099734475

547 548 549 550 551 552 553

0.056768117 0.040785549 0.218881882 0.049759606 0.076689857 0.203116424 0.702288028

554 555 556 557 558 559 560

0.298404572 0.075386207 0.200189282 0.343310217 0.051259071 0.262333356 0.097556974

561 562 563 564 565 566 567

0.401595756 0.142149074 0.628581201 0.048858757 0.030990742 0.355123658 0.246828140

568 569 570 571 572 573 574

0.183786492 0.137537135 0.085895422 0.026680668 0.030197217 0.183002643 0.058935122

575 576 577 578 579 580 581

0.116399413 0.034162708 0.087450128 0.044101705 0.245074349 0.020762078 0.110456583

582 583 584 585 586 587 588


0.059331014 0.056080306 0.006392524 0.022499427 0.099287127 0.277851488 0.040444591

589 590 591 592 593 594 595

0.127400171 0.403337370 0.393022072 0.063365405 0.027588084 0.015896014 0.059417748

596 597 598 599 600 601 602

0.076074284 0.163792589 0.099529669 0.468768516 0.093713675 0.062607481 0.178328210

603 604 605 606 607 608 609

0.056512397 0.166022979 0.652362395 0.325124660 0.100371013 0.181098196 0.166234320

610 611 612 613 614 615 616

0.050742361 0.071275577 0.440271499 0.085478669 0.071258644 0.133803831 0.066207624

617 618 619 620 621 622 623

0.115753716 0.285901437 0.108238486 0.021329189 0.033548901 0.404235298 0.037380945

624 625 626 627 628 629 630

0.527983673 0.337173131 0.062047026 0.460939761 0.574681056 0.046739109 0.074948827

631 632 633 634 635 636 637

0.213511817 0.207478864 0.013521014 0.096568355 0.047390321 0.013631621 0.068123581

638 639 640 641 642 643 644

0.385794553 0.059397666 0.037574501 0.110157384 0.064561368 0.516626507 0.035791886

645 646 647 648 649 650 651

0.156104606 0.064150668 0.025691328 0.019826151 0.870969058 0.046615157 0.179577146

652 653 654 655 656 657 658

0.231422343 0.054331540 0.020354341 0.015703282 0.030272247 0.034600567 0.009766684

659 660 661 662 663 664 665

0.040313997 0.022634282 0.066388700 0.065001022 0.025910000 0.147385722 0.021322268

666 667 668 669 670 671 672

0.460894248 0.043328927 0.074302729 0.092664538 0.028826325 0.090902708 0.224537166

673 674 675 676 677 678 679

0.349346390 0.045447735 0.153818801 0.249957797 0.085044128 0.032154403 0.215266773

680 681 682 683 684 685 686

0.284275882 0.059741925 0.230554440 0.136153900 0.102890510 0.146407229 0.064655570

687 688 689 690 691 692 693

0.104293634 0.050120403 0.082614253 0.120370904 0.091548822 0.464095945 0.208053715


694 695 696 697 698 699 700

0.014291362 0.143606244 0.702829603 0.011861065 0.196868026 0.043365849 0.095935161

701 702 703 704 705 706 707

0.021692951 0.641114855 0.152973779 0.238219922 0.061890195 0.012133507 0.011772023

708 709 710 711 712 713 714

0.385152067 0.040717945 0.019106829 0.033455971 0.398671353 0.020445233 0.036199755

715 716 717 718 719 720 721

0.030913369 0.402744780 0.196981646 0.025867278 0.037543807 0.150791665 0.064641790

722 723 724 725 726 727 728

0.035839589 0.054449273 0.008998777 0.231321807 0.035123905 0.017298641 0.049854094

729 730 731 732 733 734 735

0.271969628 0.283013776 0.067389200 0.494069296 0.091757982 0.022677274 0.069215485

736 737 738 739 740 741 742

0.143734788 0.049047430 0.121503905 0.098539631 0.152438770 0.056412464 0.123884164

743 744 745 746 747 748 749

0.139577436 0.728612014 0.186436357 0.027617033 0.053720263 0.025214128 0.089330288

750 751 752 753 754 755 756

0.055761180 0.081723445 0.036745017 0.047795021 0.090475437 0.078496215 0.289658734

757 758 759 760 761 762 763

0.068827249 0.066517769 0.047085502 0.023542616 0.183547428 0.034109594 0.179474841

764 765 766 767 768 769 770

0.166219619 0.087586151 0.013935566 0.228296095 0.290569959 0.716692596 0.278684979

771 772 773 774 775 776 777

0.091997574 0.019383710 0.162521896 0.025176350 0.107899791 0.023027805 0.042284561

778 779 780 781 782 783 784

0.268195189 0.046032070 0.194509178 0.099388659 0.328725099 0.205683692 0.165204730

785 786 787 788 789 790 791

0.181004216 0.100503012 0.017511757 0.083239679 0.040955164 0.012872295 0.153244943

792 793 794 795 796 797 798

0.080980627 0.069216534 0.193664543 0.437437505 0.286724639 0.039086665 0.095001313

799 800 801 802 803 804 805


0.064515478 0.031718156 0.508399832 0.024433819 0.108218421 0.022968617 0.102919432

806 807 808 809 810 811 812

0.695424263 0.165732849 0.074769216 0.060808014 0.236330408 0.062178118 0.087987223

813 814 815 816 817 818 819

0.017952592 0.031221275 0.074410547 0.153715332 0.316919269 0.039609447 0.061261657

820 821 822 823 824 825 826

0.015913538 0.081837718 0.350905712 0.015391834 0.417963266 0.076271538 0.084308482

827 828 829 830 831 832 833

0.078915767 0.040287659 0.142686134 0.049011829 0.091794810 0.122478773 0.024131257

834 835 836 837 838 839 840

0.022891047 0.256923866 0.101175222 0.092967749 0.060649210 0.070700636 0.481395291

841 842 843 844 845 846 847

0.078613784 0.023966153 0.141670887 0.031765072 0.030604023 0.336171145 0.737413748

848 849 850 851 852 853 854

0.060198744 0.067186194 0.397953746 0.067549034 0.103228962 0.143979105 0.141553701

855 856 857 858 859 860 861

0.610640456 0.058139319 0.021628348 0.183543729 0.277010566 0.117473260 0.059010232

862 863 864 865 866 867 868

0.098846184 0.050449927 0.091981248 0.076930585 0.297327270 0.113753119 0.197683652

869 870 871 872 873 874 875

0.072535585 0.017313348 0.129242538 0.046353321 0.046390800 0.036297903 0.107598888

876 877 878 879 880 881 882

0.109949583 0.099996575 0.005240661 0.044428191 0.244511979 0.097073966 0.670557540

883 884 885 886 887 888 889

0.161875695 0.555341745 0.788206184 0.078673037 0.084469293 0.090972156 0.025138654

890 891 892 893 894 895 896

0.202254588 0.017900915 0.118212852 0.137135507 0.718907295 0.110697673 0.046952688

897 898 899 900 901 902 903

0.103581246 0.104755291 0.047255782 0.030190023 0.177159171 0.087825884 0.176964353

904 905 906 907 908 909 910

0.049527152 0.517720016 0.294024629 0.163768734 0.033300223 0.042670774 0.253442833


911 912 913 914 915 916 917

0.146721622 0.111974181 0.023014225 0.640304240 0.397892165 0.024624501 0.066609066

918 919 920 921 922 923 924

0.080090031 0.085770391 0.088218455 0.101774922 0.026308832 0.027552576 0.166926027

925 926 927 928 929 930 931

0.183724774 0.317935248 0.175258574 0.173883497 0.098281480 0.091488167 0.049010400

932 933 934 935 936 937 938

0.391877467 0.053223817 0.139469657 0.123599283 0.102991691 0.209328468 0.067801031

939 940 941 942 943 944 945

0.085537026 0.026272967 0.137510452 0.218556388 0.196464580 0.034824059 0.347503893

946 947 948 949 950 951 952

0.233009247 0.614716439 0.133299729 0.050411393 0.039712532 0.076358791 0.163084807

953 954 955 956 957 958 959

0.053503264 0.034872990 0.222578124 0.019071954 0.610168779 0.135699380 0.086189952

960 961 962 963 964 965 966

0.105195210 0.040097157 0.123135249 0.041250915 0.077570777 0.220445317 0.089465788

967 968 969 970 971 972 973

0.054125361 0.452053801 0.409814622 0.054349257 0.015942602 0.074959195 0.409008359

974 975 976 977 978 979 980

0.292535984 0.020753053 0.076227445 0.285119706 0.082700712 0.011914811 0.017006853

981 982 983 984 985 986 987

0.686214642 0.015953760 0.113926752 0.027630818 0.003481304 0.033025758 0.048363274

988 989 990 991 992 993 994

0.061074090 0.340140317 0.057761806 0.039837531 0.037809861 0.036982725 0.475055911

995 996 997 998 999 1000

0.020358315 0.562393239 0.103616311 0.031433559 0.111200190 0.022832089

[ reached getOption("max.print") -- omitted 1334 entries ]

> testing$Churn=as.character(testing$Churn)

> testing$Churn[testing$Churn=="No"] <- "0"

> testing$Churn[testing$Churn=="Yes"] <- "1"

> fitted.results=predict(lmodel,newdata=testing,type='response')
> fitted.results=ifelse(fitted.results > 0.5,1,0)

> misClasificError=mean(fitted.results != testing$Churn)

> print(paste('Logistic Regression Accuracy',1-misClasificError))

[1] "Logistic Regression Accuracy 0.85985985985986"

> print("Confusion Matrix for Logistic Regression"); table(testing$Churn, fitted.results > 0.5)

[1] "Confusion Matrix for Logistic Regression"

FALSE TRUE

0 827 28

1 112 32

> sum(Telecom$Churn=="1")/nrow(Telecom)

[1] 0.1449145

> str(Telecom)

Classes ‘tbl_df’, ‘tbl’ and 'data.frame': 3333 obs. of 10 variables:

$ Churn : Factor w/ 2 levels "0","1": 1 1 1 1 1 1 1 1 1 1 ...

$ AccountWeeks : num 128 107 137 84 75 118 121 147 117 141 ...

$ ContractRenewal: num 1 1 1 0 0 0 1 0 1 0 ...

$ DataPlan : num 1 1 0 0 0 0 1 0 0 1 ...

$ CustServCalls : num 1 1 0 2 3 0 3 0 1 0 ...

$ DayMins : num 265 162 243 299 167 ...

$ DayCalls : num 110 123 114 71 113 98 88 79 97 84 ...

$ MonthlyCharge : num 89 82 52 57 41 57 87.3 36 63.9 93.2 ...

$ OverageFee : num 9.87 9.78 6.06 3.1 7.42 ...

$ RoamMins : num 10 13.7 12.2 6.6 10.1 6.3 7.5 7.1 8.7 11.2 ...

> Trainknn=trainData

> Testknn=testData

> TrainBayes=trainData

> TestBayes=testData

> lmodel=glm(Churn~.,family = binomial(link = "logit"),data=trainData)

> print(summary(lmodel))
Call:

glm(formula = Churn ~ ., family = binomial(link = "logit"), data = trainData)

Deviance Residuals:

Min 1Q Median 3Q Max

-2.0553 -0.5045 -0.3431 -0.1992 3.0525

Coefficients:

Estimate Std. Error z value Pr(>|z|)

(Intercept) -6.2861356 0.6535782 -9.618 < 2e-16 ***

AccountWeeks 0.0003457 0.0016766 0.206 0.83665

ContractRenewal -1.9676217 0.1713300 -11.484 < 2e-16 ***

DataPlan -1.3577425 0.6468784 -2.099 0.03582 *

CustServCalls 0.5539090 0.0483978 11.445 < 2e-16 ***

DayMins 0.0107140 0.0039687 2.700 0.00694 **

DayCalls 0.0039345 0.0033077 1.190 0.23424

MonthlyCharge 0.0119062 0.0220000 0.541 0.58838

OverageFee 0.1372180 0.0460986 2.977 0.00291 **

RoamMins 0.0833328 0.0261358 3.188 0.00143 **

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

Null deviance: 1934.3 on 2333 degrees of freedom

Residual deviance: 1515.6 on 2324 degrees of freedom

AIC: 1535.6

Number of Fisher Scoring iterations: 6

> view(lmodel2)
> print(summary(lmodel2))

Call:

glm(formula = Churn ~ AccountWeeks + ContractRenewal + CustServCalls +

DayCalls + DayMins + OverageFee + RoamMins, family = binomial,

data = trainData)

Deviance Residuals:

Min 1Q Median 3Q Max

-1.9708 -0.5214 -0.3588 -0.2287 2.9352

Coefficients:

Estimate Std. Error z value Pr(>|z|)

(Intercept) -6.308e+00 6.421e-01 -9.825 < 2e-16 ***

AccountWeeks -1.046e-05 1.670e-03 -0.006 0.995000

ContractRenewal -1.920e+00 1.682e-01 -11.418 < 2e-16 ***

CustServCalls 5.448e-01 4.768e-02 11.425 < 2e-16 ***

DayCalls 3.590e-03 3.263e-03 1.100 0.271201

DayMins 1.244e-02 1.266e-03 9.829 < 2e-16 ***

OverageFee 1.451e-01 2.706e-02 5.363 8.2e-08 ***

RoamMins 8.795e-02 2.411e-02 3.648 0.000264 ***

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

Null deviance: 1934.3 on 2333 degrees of freedom

Residual deviance: 1554.7 on 2326 degrees of freedom

AIC: 1570.7

Number of Fisher Scoring iterations: 5


> dim(Trainknn)

[1] 2334 10

> dim(Testknn)

[1] 999 10

> head(Trainknn)

# A tibble: 6 x 10

Churn AccountWeeks ContractRenewal DataPlan CustServCalls DayMins DayCalls

<fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>

10 128 1 1 1 265. 110

20 107 1 1 1 162. 123

30 137 1 0 0 243. 114

40 84 0 0 2 299. 71

50 75 0 0 3 167. 113

60 118 0 0 0 223. 98

# ... with 3 more variables: MonthlyCharge <dbl>, OverageFee <dbl>, RoamMins <dbl>

> pred = knn(Trainknn[-1], Testknn[-1], Trainknn[,1], k = 3)

Error in knn(Trainknn[-1], Testknn[-1], Trainknn[, 1], k = 3) :

'train' and 'class' have different lengths

> Telecom_test_pred=knn(train = Trainknn,

+ test = Testknn,

+ cl= Telecom_train_labels,

+ k = 3,

+ prob=TRUE)

Error in knn(train = Trainknn, test = Testknn, cl = Telecom_train_labels, :

'train' and 'class' have different lengths

> pred=knn(Trainknn[-1],Testknn[-1],Trainknn[1],k=19)

Error in knn(Trainknn[-1], Testknn[-1], Trainknn[1], k = 19) :

'train' and 'class' have different lengths

> table.knn = table(Testknn[,1], pred)

Error: Must use a vector in `[`, not an object of class matrix.


Call `rlang::last_error()` to see a backtrace.

> sum(diag(table.knn)/sum(table.knn))

Error in diag(table.knn) : object 'table.knn' not found

> dim(TrainBayes)

[1] 2334 10

> dim(TestBayes)

[1] 999 10

> train.NB=train.NB[-c(8,10)]

Error: Negative column indexes in `[` must match number of columns:

* `.data` has 9 columns

* Position 2 equals -10

Call `rlang::last_error()` to see a backtrace.

> train.NB=train.NB[-c(8,9)]

> test.NB=test.NB[-c(8,9)]

> train.NB$Churn=as.factor(train.NB$Churn)

> test.NB$Churn=as.factor(test.NB$Churn)

> NB=naiveBayes(x=TrainBayes[-1], y=TrainBayes$Churn)

> NB

Naive Bayes Classifier for Discrete Predictors

Call:

naiveBayes.default(x = TrainBayes[-1], y = TrainBayes$Churn)

A-priori probabilities:

TrainBayes$Churn

0 1

0.8547558 0.1452442

Conditional probabilities:

AccountWeeks
TrainBayes$Churn [,1] [,2]

0 101.1975 39.29269

1 101.9794 39.24309

ContractRenewal

TrainBayes$Churn [,1] [,2]

0 0.9328321 0.2503753

1 0.7109145 0.4540078

DataPlan

TrainBayes$Churn [,1] [,2]

0 0.2972431 0.4571591

1 0.1563422 0.3637163

CustServCalls

TrainBayes$Churn [,1] [,2]

0 1.445614 1.142954

1 2.259587 1.809865

DayMins

TrainBayes$Churn [,1] [,2]

0 175.3046 49.97021

1 206.3634 69.97969

DayCalls

TrainBayes$Churn [,1] [,2]

0 100.5719 19.50113

1 101.4926 22.51053

MonthlyCharge

TrainBayes$Churn [,1] [,2]


0 55.81414 16.38930

1 58.84041 16.13284

OverageFee

TrainBayes$Churn [,1] [,2]

0 9.928416 2.503162

1 10.614248 2.594425

RoamMins

TrainBayes$Churn [,1] [,2]

0 10.18050 2.76674

1 10.76047 2.84053

> predNB=predict(NB,TestBayes,type = "class")

> predNB1=predict(NB,TrainBayes,type = "class")

> y_pred.NB=predict(NB,newdata=TestBayes[-1])

> tab.NB=table(test.NB[,1],y_pred.NB)

Error: Must use a vector in `[`, not an object of class matrix.

Call `rlang::last_error()` to see a backtrace.

> tab.NB

[1] 0.8358358

> mean(predNB==TestBayes$Churn)

[1] 0.8438438

> tab.NB=table(test.NB[,1],y_pred.NB)

Error: Must use a vector in `[`, not an object of class matrix.

Call `rlang::last_error()` to see a backtrace.

> CM=confusionMatrix(predNB, TestBayes[["Churn"]])

> CM

Confusion Matrix and Statistics

Reference
Prediction 0 1

0 785 86

1 70 58

Accuracy : 0.8438

95% CI : (0.8198, 0.8658)

No Information Rate : 0.8559

P-Value [Acc > NIR] : 0.8694

Kappa : 0.3365

Mcnemar's Test P-Value : 0.2298

Sensitivity : 0.9181

Specificity : 0.4028

Pos Pred Value : 0.9013

Neg Pred Value : 0.4531

Prevalence : 0.8559

Detection Rate : 0.7858

Detection Prevalence : 0.8719

Balanced Accuracy : 0.6605

'Positive' Class : 0

> CM2=confusionMatrix(predNB1,TrainBayes[["Churn"]])

> CM2

Confusion Matrix and Statistics

Reference

Prediction 0 1

0 1837 192
1 158 147

Accuracy : 0.85

95% CI : (0.8349, 0.8643)

No Information Rate : 0.8548

P-Value [Acc > NIR] : 0.75154

Kappa : 0.3698

Mcnemar's Test P-Value : 0.07774

Sensitivity : 0.9208

Specificity : 0.4336

Pos Pred Value : 0.9054

Neg Pred Value : 0.4820

Prevalence : 0.8548

Detection Rate : 0.7871

Detection Prevalence : 0.8693

Balanced Accuracy : 0.6772

'Positive' Class : 0

> normalize=function(x){return((x-min(x))/(max(x)-min(x)))}

> Telecom$norm.Churn=normalize(Churn)

> Telecom$norm.Accountweeks=normalize(AccountWeeks)

> Telecom$norm.daycalls=normalize(DayCalls)

> Telecom$norm.daymins=normalize(DayMins)

> Telecom$norm.overagefee=normalize(OverageFee)

> Telecom$norm.contractrenewal=normalize(ContractRenewal)

> Telecom$norm.dataplan=normalize(DataPlan)

> Telecom$norm.datausage=normalize(DataUsage)
> Telecom$norm.Cust=normalize(CustServCalls)

> Telecom$norm.monthlycharge=normalize(MonthlyCharge)

> Telecom$norm.roammins=normalize(RoamMins)

> view(Telecom)

> Telecom

# A tibble: 3,333 x 21

Churn AccountWeeks ContractRenewal DataPlan CustServCalls DayMins DayCalls

<fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>

10 128 1 1 1 265. 110

20 107 1 1 1 162. 123

30 137 1 0 0 243. 114

40 84 0 0 2 299. 71

50 75 0 0 3 167. 113

60 118 0 0 0 223. 98

70 121 1 1 3 218. 88

80 147 0 0 0 157 79

90 117 1 0 1 184. 97

10 0 141 0 1 0 259. 84

# ... with 3,323 more rows, and 14 more variables: MonthlyCharge <dbl>,

# OverageFee <dbl>, RoamMins <dbl>, norm.Churn <dbl>, norm.Accountweeks <dbl>,

# norm.daycalls <dbl>, norm.daymins <dbl>, norm.overagefee <dbl>,

# norm.contractrenewal <dbl>, norm.dataplan <dbl>, norm.datausage <dbl>,

# norm.Cust <dbl>, norm.monthlycharge <dbl>, norm.roammins <dbl>

> pred = knn(Trainknn[-1], Testknn[-1], Trainknn[,1], k = 3)

Error in knn(Trainknn[-1], Testknn[-1], Trainknn[, 1], k = 3) :

'train' and 'class' have different lengths

> y_pred.3=knn(Trainknn=train.NB[,-1],test=test.NB[-1], cl=train.NB[,1],k=3)

Error in knn(Trainknn = train.NB[, -1], test = test.NB[-1], cl = train.NB[, :

unused argument (Trainknn = train.NB[, -1])

> set.seed(1234)

> pd=sample(2,nrow(Telecom),replace=TRUE, prob=c(0.7,0.3))


> train1=Telecom[pd==1,]

> test1=Telecom[pd==2,]

> train.NB=train1[,c(1,13:22)]

Error: Positive column indexes in `[` must match number of columns:

* `.data` has 21 columns

* Position 11 equals 22

Call `rlang::last_error()` to see a backtrace.

> test.NB=test1[,c(1,13:22)]

Error: Positive column indexes in `[` must match number of columns:

* `.data` has 21 columns

* Position 11 equals 22

Call `rlang::last_error()` to see a backtrace.

> str(train.NB)

Classes ‘tbl_df’, ‘tbl’ and 'data.frame': 2362 obs. of 7 variables:

$ Churn : Factor w/ 2 levels "0","1": 1 1 1 1 1 1 1 1 1 2 ...

$ norm.Accountweeks : num 0.525 0.438 0.562 0.343 0.483 ...

$ norm.daycalls : num 0.667 0.745 0.691 0.43 0.594 ...

$ norm.daymins : num 0.756 0.461 0.694 0.853 0.637 ...

$ norm.overagefee : num 0.543 0.538 0.333 0.17 0.606 ...

$ norm.contractrenewal: num 1 1 1 0 0 1 0 1 0 1 ...

$ norm.dataplan : num 1 1 0 0 0 1 0 0 1 0 ...

> table(train.NB$Churn)

0 1

2034 328

> table(test.NB$Churn)

0 1

816 155

> y_pred.3=knn(Trainknn=train.NB[,-1],Testknn=test.NB[-1], cl=train.NB[,1],k=3)

You might also like