claimants <- read.csv("E:\\DataScience Yogesh\\R _Codes\\Logistic Regression\\claimants.csv") # Choose the claimants Data set
View(claimants)
attach(claimants)
dim(claimants)
## [1] 1340 7
colnames(claimants)#
## [1] "CASENUM" "ATTORNEY" "CLMSEX" "CLMINSUR" "SEATBELT" "CLMAGE"
## [7] "LOSS"
summary(claimants)
## CASENUM ATTORNEY CLMSEX CLMINSUR
## Min. : 0 Min. :0.0000 Min. :0.0000 Min. :0.0000
## 1st Qu.: 4177 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:1.0000
## Median : 8756 Median :0.0000 Median :1.0000 Median :1.0000
## Mean :11202 Mean :0.4888 Mean :0.5587 Mean :0.9076
## 3rd Qu.:15702 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1.0000
## Max. :34153 Max. :1.0000 Max. :1.0000 Max. :1.0000
## NA's :12 NA's :41
## SEATBELT CLMAGE LOSS
## Min. :0.00000 Min. : 0.00 Min. : 0.000
## 1st Qu.:0.00000 1st Qu.: 9.00 1st Qu.: 0.400
## Median :0.00000 Median :30.00 Median : 1.069
## Mean :0.01703 Mean :28.41 Mean : 3.806
## 3rd Qu.:0.00000 3rd Qu.:43.00 3rd Qu.: 3.781
## Max. :1.00000 Max. :95.00 Max. :173.604
## NA's :48 NA's :189
claimants1 <- na.omit(claimants)
library(caret)
## Warning: package 'caret' was built under R version 3.4.4
## Loading required package: lattice
## Warning: package 'lattice' was built under R version 3.4.4
## Loading required package: ggplot2
## Warning: package 'ggplot2' was built under R version 3.4.4
inTrain <- createDataPartition(y = ATTORNEY, p=0.70,list = FALSE)
train <-claimants[inTrain,]
test <- claimants[-inTrain,]
str(claimants)
## 'data.frame': 1340 obs. of 7 variables:
## $ CASENUM : int 5 3 66 70 96 97 10 36 51 55 ...
## $ ATTORNEY: int 0 1 1 0 1 0 0 0 1 1 ...
## $ CLMSEX : int 0 1 0 0 0 1 0 1 1 0 ...
## $ CLMINSUR: int 1 0 1 1 1 1 1 1 1 1 ...
## $ SEATBELT: int 0 0 0 1 0 0 0 0 0 0 ...
## $ CLMAGE : int 50 18 5 31 30 35 9 34 60 NA ...
## $ LOSS : num 34.94 0.891 0.33 0.037 0.038 ...
str(factor(CLMSEX))
## Factor w/ 2 levels "0","1": 1 2 1 1 1 2 1 2 2 1 ...
#Logistic Regression
logit <- glm(ATTORNEY ~ factor(CLMSEX) + factor(CLMINSUR) + factor(SEATBELT) + CLMAGE + LOSS,family = binomial,data = train)
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
summary(logit)
##
## Call:
## glm(formula = ATTORNEY ~ factor(CLMSEX) + factor(CLMINSUR) +
## factor(SEATBELT) + CLMAGE + LOSS, family = binomial, data = train)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.61878 -1.03932 -0.01017 0.98581 2.51002
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.155101 0.282179 -0.550 0.583
## factor(CLMSEX)1 0.159545 0.159778 0.999 0.318
## factor(CLMINSUR)1 0.629587 0.263787 2.387 0.017 *
## factor(SEATBELT)1 -0.941330 0.618128 -1.523 0.128
## CLMAGE 0.005323 0.003939 1.351 0.177
## LOSS -0.307870 0.038008 -8.100 5.49e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 1043.14 on 753 degrees of freedom
## Residual deviance: 917.24 on 748 degrees of freedom
## (184 observations deleted due to missingness)
## AIC: 929.24
##
## Number of Fisher Scoring iterations: 6
logit1 <- glm(ATTORNEY ~ (CLMSEX) + (CLMINSUR) + (SEATBELT) + (CLMAGE) + LOSS,family=binomial,data = train)
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
summary(logit1)
##
## Call:
## glm(formula = ATTORNEY ~ (CLMSEX) + (CLMINSUR) + (SEATBELT) +
## (CLMAGE) + LOSS, family = binomial, data = train)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.61878 -1.03932 -0.01017 0.98581 2.51002
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.155101 0.282179 -0.550 0.583
## CLMSEX 0.159545 0.159778 0.999 0.318
## CLMINSUR 0.629587 0.263787 2.387 0.017 *
## SEATBELT -0.941330 0.618128 -1.523 0.128
## CLMAGE 0.005323 0.003939 1.351 0.177
## LOSS -0.307870 0.038008 -8.100 5.49e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 1043.14 on 753 degrees of freedom
## Residual deviance: 917.24 on 748 degrees of freedom
## (184 observations deleted due to missingness)
## AIC: 929.24
##
## Number of Fisher Scoring iterations: 6
# Odds Ratio
exp(coef(logit))
## (Intercept) factor(CLMSEX)1 factor(CLMINSUR)1 factor(SEATBELT)1
## 0.8563286 1.1729771 1.8768361 0.3901087
## CLMAGE LOSS
## 1.0053369 0.7350109
# Confusion matrix table
prob <- predict(logit,type=c("response"),test)
prob
## 5 7 10 11 13
## 6.507801e-01 3.619633e-01 NA 2.545023e-01 4.987849e-01
## 15 16 17 27 29
## 6.871756e-01 5.090069e-01 7.165389e-01 6.798307e-01 6.370791e-01
## 30 33 48 50 51
## NA 5.833997e-01 6.177028e-01 4.336436e-01 3.946849e-01
## 54 55 58 59 61
## NA 6.081545e-01 1.188663e-01 6.953896e-01 NA
## 62 66 68 72 74
## NA 6.745093e-01 6.478357e-01 5.786485e-01 6.431093e-01
## 77 78 80 84 85
## 5.979419e-01 NA 3.966548e-01 3.861645e-01 6.060248e-01
## 86 87 89 92 96
## 5.914215e-01 3.852730e-01 3.601025e-01 3.201177e-01 7.274604e-01
## 98 101 102 104 106
## 3.854811e-05 5.714660e-01 6.677884e-01 NA 3.368346e-01
## 111 118 134 140 141
## 6.267953e-01 4.367092e-01 NA 5.541643e-01 6.152975e-01
## 145 147 149 153 154
## 4.875233e-01 5.560822e-01 2.586435e-08 6.554037e-01 6.614355e-01
## 156 160 162 175 178
## 2.591143e-01 5.252200e-01 6.016303e-01 4.447529e-01 6.177513e-01
## 179 188 190 191 194
## 3.515624e-01 6.692197e-01 5.586259e-01 5.541610e-01 4.190238e-01
## 197 198 199 201 203
## 3.780416e-01 7.017255e-01 6.491333e-01 6.699355e-01 4.451600e-01
## 204 209 212 244 247
## 3.749675e-01 1.732209e-02 6.021631e-01 4.321739e-01 6.006772e-01
## 248 252 258 260 261
## 6.265292e-01 2.433802e-01 4.035167e-01 1.809102e-01 6.280153e-01
## 262 264 266 267 271
## 6.451620e-01 6.363907e-01 5.497028e-01 4.044097e-01 6.554531e-01
## 272 275 276 280 286
## 3.412175e-01 NA 6.036044e-01 6.633983e-01 1.648823e-01
## 289 291 293 295 298
## 5.716168e-01 6.891092e-01 5.134602e-01 NA 6.699598e-01
## 299 300 302 313 314
## NA 6.049920e-01 NA 4.374615e-01 4.497847e-01
## 315 316 318 319 320
## 5.521029e-01 6.620493e-01 6.578332e-01 NA 5.808386e-01
## 321 325 326 331 333
## 6.780500e-01 NA 7.062704e-01 4.398469e-01 NA
## 337 341 344 348 349
## 3.632934e-01 6.508701e-01 6.116182e-01 5.014312e-01 5.362234e-01
## 350 352 353 354 357
## 3.719357e-01 1.965539e-01 6.491909e-01 NA 4.975227e-01
## 362 364 372 378 384
## 4.708721e-01 2.220446e-16 4.194368e-01 3.395557e-01 6.106835e-01
## 388 393 394 397 398
## 6.771772e-01 6.256435e-01 6.545781e-01 5.999273e-01 NA
## 406 407 413 414 416
## 2.835937e-01 3.007541e-01 3.495360e-01 5.543049e-01 1.418175e-09
## 417 424 429 430 433
## 6.163304e-01 6.324284e-01 NA 6.663661e-01 2.349624e-01
## 434 438 439 442 444
## 1.248938e-07 4.050327e-01 3.706355e-01 NA 6.224140e-01
## 445 447 449 451 454
## 4.363338e-01 3.889917e-01 4.380293e-01 4.076436e-01 5.876634e-01
## 458 460 462 464 470
## 7.013659e-01 NA 6.478043e-01 5.534594e-01 5.836342e-01
## 471 478 485 487 492
## 3.336129e-01 6.378997e-01 NA 6.417592e-01 NA
## 498 507 510 512 514
## 6.333472e-01 4.502623e-01 NA 4.320546e-01 7.223017e-01
## 517 521 525 526 533
## 7.179583e-01 7.036394e-01 6.180049e-01 6.265661e-01 6.107727e-01
## 538 541 551 553 554
## 5.274661e-01 4.268062e-01 NA 2.898098e-01 4.606206e-01
## 558 559 560 565 566
## 6.130669e-01 3.185952e-01 NA 6.630773e-01 2.709331e-01
## 567 572 576 580 581
## 6.988060e-01 4.621374e-01 4.270525e-01 NA 2.341406e-01
## 583 588 595 599 603
## 6.579826e-01 4.607995e-01 7.028183e-01 6.254176e-01 6.585966e-01
## 605 612 617 618 622
## 3.975341e-01 NA 4.435689e-01 1.749435e-02 3.800932e-01
## 624 633 635 643 644
## 4.318316e-01 3.992394e-01 6.103400e-02 1.881906e-01 6.625405e-01
## 646 647 654 661 663
## 2.668418e-01 3.900183e-01 2.030652e-01 NA 6.530543e-01
## 664 665 666 667 669
## 6.748636e-01 4.458868e-01 3.442909e-01 NA 4.729095e-01
## 680 681 682 684 685
## 3.125853e-01 6.375882e-01 5.316692e-01 6.238151e-01 1.740888e-01
## 687 689 693 695 699
## 6.372059e-01 4.885298e-01 6.476953e-01 6.150239e-01 6.820187e-01
## 705 706 707 708 709
## 1.835988e-01 6.118083e-01 NA 6.448488e-01 5.683857e-01
## 710 714 715 717 724
## 6.140015e-01 NA 6.971504e-01 6.114752e-01 4.071959e-01
## 726 728 733 736 739
## 6.162787e-01 3.327526e-01 NA 6.154254e-01 2.676043e-01
## 740 743 745 749 750
## 3.211580e-01 6.348678e-01 3.272995e-01 4.382935e-01 6.600091e-01
## 754 755 756 758 769
## 6.236497e-01 NA 6.646028e-01 3.846948e-01 NA
## 775 785 786 787 791
## 6.530357e-01 NA 5.586493e-01 3.887430e-01 1.162335e-01
## 795 806 807 813 814
## 4.436651e-01 NA 4.674014e-01 6.614889e-01 4.930832e-11
## 825 829 831 836 837
## NA 1.808260e-01 2.592705e-01 6.684877e-01 NA
## 843 846 849 853 859
## 6.230489e-01 NA 3.293287e-01 5.613044e-01 5.827694e-01
## 862 866 867 868 874
## NA 6.199621e-01 6.684877e-01 6.228851e-01 4.350219e-01
## 884 890 893 896 900
## NA 6.523564e-01 6.197848e-01 5.013711e-01 3.279459e-01
## 902 905 908 910 916
## 6.358157e-01 6.388205e-01 1.159043e-01 NA 4.625811e-01
## 918 932 933 934 937
## 3.951265e-01 6.581103e-01 NA 6.110234e-01 6.661061e-01
## 941 944 948 952 955
## 6.806134e-01 NA 1.520110e-01 6.725564e-01 5.301902e-01
## 960 965 968 969 972
## 6.783456e-01 NA NA 5.258016e-01 1.259933e-01
## 973 974 976 977 979
## 3.970461e-01 5.002114e-01 3.461157e-01 2.648229e-01 2.732245e-01
## 984 987 989 990 993
## 2.494437e-01 1.862542e-01 6.457132e-01 3.829487e-01 5.910859e-01
## 1000 1002 1008 1009 1010
## 5.934617e-01 NA 5.859299e-01 5.495117e-01 NA
## 1017 1018 1020 1021 1027
## 2.052662e-01 4.837495e-01 4.218295e-01 3.777489e-01 6.682269e-01
## 1032 1034 1042 1045 1046
## 1.214988e-01 6.212765e-01 6.654698e-01 6.505998e-01 6.325367e-01
## 1052 1056 1060 1067 1071
## 5.522350e-01 NA NA 7.038392e-01 5.910496e-01
## 1074 1075 1076 1077 1080
## 4.840213e-01 5.329945e-01 5.780342e-01 6.520462e-01 6.816744e-01
## 1081 1082 1084 1089 1090
## 6.637846e-01 6.761235e-01 5.727173e-01 6.326208e-01 6.688697e-01
## 1092 1094 1097 1101 1102
## 1.450825e-01 2.454521e-01 4.471398e-01 4.238481e-01 6.139380e-01
## 1115 1120 1124 1126 1131
## 1.717765e-01 7.028770e-01 2.139036e-01 3.570940e-01 2.831644e-01
## 1133 1134 1137 1140 1144
## NA 3.641260e-01 6.981808e-01 2.632422e-01 3.848923e-01
## 1150 1151 1156 1158 1163
## NA 3.601072e-01 6.471016e-01 6.749477e-01 4.383924e-02
## 1172 1173 1175 1179 1181
## 3.591241e-01 5.778640e-01 4.929821e-01 5.524649e-01 NA
## 1182 1185 1189 1191 1196
## 2.201508e-01 3.883172e-01 4.172327e-02 4.103177e-01 5.190319e-01
## 1202 1203 1204 1209 1212
## NA 6.360707e-01 6.059823e-01 6.137547e-01 5.359596e-01
## 1216 1219 1220 1221 1222
## 1.226337e-01 6.433353e-01 6.623188e-01 6.680722e-01 5.462575e-01
## 1224 1229 1230 1233 1234
## NA 5.406630e-01 NA 2.464966e-01 4.812420e-01
## 1239 1253 1254 1255 1257
## 6.735772e-01 6.322009e-01 5.866488e-01 3.411993e-01 5.885952e-05
## 1260 1263 1266 1268 1269
## 3.448471e-01 6.154983e-01 NA NA 5.610856e-01
## 1273 1275 1277 1279 1280
## 6.832665e-01 6.322009e-01 NA 2.130570e-01 3.464069e-01
## 1281 1285 1289 1290 1301
## 6.278364e-01 5.909155e-01 5.736243e-01 2.948783e-01 5.893670e-01
## 1307 1309 1313 1329 1330
## 6.973598e-01 3.078786e-01 2.392111e-02 6.048839e-01 6.558765e-01
## 1333 1336
## 6.641707e-01 NA
prob1 <- predict(logit,test) #Don't use this
prob <-as.data.frame(prob)
prob
## prob
## 5 6.507801e-01
## 7 3.619633e-01
## 10 NA
## 11 2.545023e-01
## 13 4.987849e-01
## 15 6.871756e-01
## 16 5.090069e-01
## 17 7.165389e-01
## 27 6.798307e-01
## 29 6.370791e-01
## 30 NA
## 33 5.833997e-01
## 48 6.177028e-01
## 50 4.336436e-01
## 51 3.946849e-01
## 54 NA
## 55 6.081545e-01
## 58 1.188663e-01
## 59 6.953896e-01
## 61 NA
## 62 NA
## 66 6.745093e-01
## 68 6.478357e-01
## 72 5.786485e-01
## 74 6.431093e-01
## 77 5.979419e-01
## 78 NA
## 80 3.966548e-01
## 84 3.861645e-01
## 85 6.060248e-01
## 86 5.914215e-01
## 87 3.852730e-01
## 89 3.601025e-01
## 92 3.201177e-01
## 96 7.274604e-01
## 98 3.854811e-05
## 101 5.714660e-01
## 102 6.677884e-01
## 104 NA
## 106 3.368346e-01
## 111 6.267953e-01
## 118 4.367092e-01
## 134 NA
## 140 5.541643e-01
## 141 6.152975e-01
## 145 4.875233e-01
## 147 5.560822e-01
## 149 2.586435e-08
## 153 6.554037e-01
## 154 6.614355e-01
## 156 2.591143e-01
## 160 5.252200e-01
## 162 6.016303e-01
## 175 4.447529e-01
## 178 6.177513e-01
## 179 3.515624e-01
## 188 6.692197e-01
## 190 5.586259e-01
## 191 5.541610e-01
## 194 4.190238e-01
## 197 3.780416e-01
## 198 7.017255e-01
## 199 6.491333e-01
## 201 6.699355e-01
## 203 4.451600e-01
## 204 3.749675e-01
## 209 1.732209e-02
## 212 6.021631e-01
## 244 4.321739e-01
## 247 6.006772e-01
## 248 6.265292e-01
## 252 2.433802e-01
## 258 4.035167e-01
## 260 1.809102e-01
## 261 6.280153e-01
## 262 6.451620e-01
## 264 6.363907e-01
## 266 5.497028e-01
## 267 4.044097e-01
## 271 6.554531e-01
## 272 3.412175e-01
## 275 NA
## 276 6.036044e-01
## 280 6.633983e-01
## 286 1.648823e-01
## 289 5.716168e-01
## 291 6.891092e-01
## 293 5.134602e-01
## 295 NA
## 298 6.699598e-01
## 299 NA
## 300 6.049920e-01
## 302 NA
## 313 4.374615e-01
## 314 4.497847e-01
## 315 5.521029e-01
## 316 6.620493e-01
## 318 6.578332e-01
## 319 NA
## 320 5.808386e-01
## 321 6.780500e-01
## 325 NA
## 326 7.062704e-01
## 331 4.398469e-01
## 333 NA
## 337 3.632934e-01
## 341 6.508701e-01
## 344 6.116182e-01
## 348 5.014312e-01
## 349 5.362234e-01
## 350 3.719357e-01
## 352 1.965539e-01
## 353 6.491909e-01
## 354 NA
## 357 4.975227e-01
## 362 4.708721e-01
## 364 2.220446e-16
## 372 4.194368e-01
## 378 3.395557e-01
## 384 6.106835e-01
## 388 6.771772e-01
## 393 6.256435e-01
## 394 6.545781e-01
## 397 5.999273e-01
## 398 NA
## 406 2.835937e-01
## 407 3.007541e-01
## 413 3.495360e-01
## 414 5.543049e-01
## 416 1.418175e-09
## 417 6.163304e-01
## 424 6.324284e-01
## 429 NA
## 430 6.663661e-01
## 433 2.349624e-01
## 434 1.248938e-07
## 438 4.050327e-01
## 439 3.706355e-01
## 442 NA
## 444 6.224140e-01
## 445 4.363338e-01
## 447 3.889917e-01
## 449 4.380293e-01
## 451 4.076436e-01
## 454 5.876634e-01
## 458 7.013659e-01
## 460 NA
## 462 6.478043e-01
## 464 5.534594e-01
## 470 5.836342e-01
## 471 3.336129e-01
## 478 6.378997e-01
## 485 NA
## 487 6.417592e-01
## 492 NA
## 498 6.333472e-01
## 507 4.502623e-01
## 510 NA
## 512 4.320546e-01
## 514 7.223017e-01
## 517 7.179583e-01
## 521 7.036394e-01
## 525 6.180049e-01
## 526 6.265661e-01
## 533 6.107727e-01
## 538 5.274661e-01
## 541 4.268062e-01
## 551 NA
## 553 2.898098e-01
## 554 4.606206e-01
## 558 6.130669e-01
## 559 3.185952e-01
## 560 NA
## 565 6.630773e-01
## 566 2.709331e-01
## 567 6.988060e-01
## 572 4.621374e-01
## 576 4.270525e-01
## 580 NA
## 581 2.341406e-01
## 583 6.579826e-01
## 588 4.607995e-01
## 595 7.028183e-01
## 599 6.254176e-01
## 603 6.585966e-01
## 605 3.975341e-01
## 612 NA
## 617 4.435689e-01
## 618 1.749435e-02
## 622 3.800932e-01
## 624 4.318316e-01
## 633 3.992394e-01
## 635 6.103400e-02
## 643 1.881906e-01
## 644 6.625405e-01
## 646 2.668418e-01
## 647 3.900183e-01
## 654 2.030652e-01
## 661 NA
## 663 6.530543e-01
## 664 6.748636e-01
## 665 4.458868e-01
## 666 3.442909e-01
## 667 NA
## 669 4.729095e-01
## 680 3.125853e-01
## 681 6.375882e-01
## 682 5.316692e-01
## 684 6.238151e-01
## 685 1.740888e-01
## 687 6.372059e-01
## 689 4.885298e-01
## 693 6.476953e-01
## 695 6.150239e-01
## 699 6.820187e-01
## 705 1.835988e-01
## 706 6.118083e-01
## 707 NA
## 708 6.448488e-01
## 709 5.683857e-01
## 710 6.140015e-01
## 714 NA
## 715 6.971504e-01
## 717 6.114752e-01
## 724 4.071959e-01
## 726 6.162787e-01
## 728 3.327526e-01
## 733 NA
## 736 6.154254e-01
## 739 2.676043e-01
## 740 3.211580e-01
## 743 6.348678e-01
## 745 3.272995e-01
## 749 4.382935e-01
## 750 6.600091e-01
## 754 6.236497e-01
## 755 NA
## 756 6.646028e-01
## 758 3.846948e-01
## 769 NA
## 775 6.530357e-01
## 785 NA
## 786 5.586493e-01
## 787 3.887430e-01
## 791 1.162335e-01
## 795 4.436651e-01
## 806 NA
## 807 4.674014e-01
## 813 6.614889e-01
## 814 4.930832e-11
## 825 NA
## 829 1.808260e-01
## 831 2.592705e-01
## 836 6.684877e-01
## 837 NA
## 843 6.230489e-01
## 846 NA
## 849 3.293287e-01
## 853 5.613044e-01
## 859 5.827694e-01
## 862 NA
## 866 6.199621e-01
## 867 6.684877e-01
## 868 6.228851e-01
## 874 4.350219e-01
## 884 NA
## 890 6.523564e-01
## 893 6.197848e-01
## 896 5.013711e-01
## 900 3.279459e-01
## 902 6.358157e-01
## 905 6.388205e-01
## 908 1.159043e-01
## 910 NA
## 916 4.625811e-01
## 918 3.951265e-01
## 932 6.581103e-01
## 933 NA
## 934 6.110234e-01
## 937 6.661061e-01
## 941 6.806134e-01
## 944 NA
## 948 1.520110e-01
## 952 6.725564e-01
## 955 5.301902e-01
## 960 6.783456e-01
## 965 NA
## 968 NA
## 969 5.258016e-01
## 972 1.259933e-01
## 973 3.970461e-01
## 974 5.002114e-01
## 976 3.461157e-01
## 977 2.648229e-01
## 979 2.732245e-01
## 984 2.494437e-01
## 987 1.862542e-01
## 989 6.457132e-01
## 990 3.829487e-01
## 993 5.910859e-01
## 1000 5.934617e-01
## 1002 NA
## 1008 5.859299e-01
## 1009 5.495117e-01
## 1010 NA
## 1017 2.052662e-01
## 1018 4.837495e-01
## 1020 4.218295e-01
## 1021 3.777489e-01
## 1027 6.682269e-01
## 1032 1.214988e-01
## 1034 6.212765e-01
## 1042 6.654698e-01
## 1045 6.505998e-01
## 1046 6.325367e-01
## 1052 5.522350e-01
## 1056 NA
## 1060 NA
## 1067 7.038392e-01
## 1071 5.910496e-01
## 1074 4.840213e-01
## 1075 5.329945e-01
## 1076 5.780342e-01
## 1077 6.520462e-01
## 1080 6.816744e-01
## 1081 6.637846e-01
## 1082 6.761235e-01
## 1084 5.727173e-01
## 1089 6.326208e-01
## 1090 6.688697e-01
## 1092 1.450825e-01
## 1094 2.454521e-01
## 1097 4.471398e-01
## 1101 4.238481e-01
## 1102 6.139380e-01
## 1115 1.717765e-01
## 1120 7.028770e-01
## 1124 2.139036e-01
## 1126 3.570940e-01
## 1131 2.831644e-01
## 1133 NA
## 1134 3.641260e-01
## 1137 6.981808e-01
## 1140 2.632422e-01
## 1144 3.848923e-01
## 1150 NA
## 1151 3.601072e-01
## 1156 6.471016e-01
## 1158 6.749477e-01
## 1163 4.383924e-02
## 1172 3.591241e-01
## 1173 5.778640e-01
## 1175 4.929821e-01
## 1179 5.524649e-01
## 1181 NA
## 1182 2.201508e-01
## 1185 3.883172e-01
## 1189 4.172327e-02
## 1191 4.103177e-01
## 1196 5.190319e-01
## 1202 NA
## 1203 6.360707e-01
## 1204 6.059823e-01
## 1209 6.137547e-01
## 1212 5.359596e-01
## 1216 1.226337e-01
## 1219 6.433353e-01
## 1220 6.623188e-01
## 1221 6.680722e-01
## 1222 5.462575e-01
## 1224 NA
## 1229 5.406630e-01
## 1230 NA
## 1233 2.464966e-01
## 1234 4.812420e-01
## 1239 6.735772e-01
## 1253 6.322009e-01
## 1254 5.866488e-01
## 1255 3.411993e-01
## 1257 5.885952e-05
## 1260 3.448471e-01
## 1263 6.154983e-01
## 1266 NA
## 1268 NA
## 1269 5.610856e-01
## 1273 6.832665e-01
## 1275 6.322009e-01
## 1277 NA
## 1279 2.130570e-01
## 1280 3.464069e-01
## 1281 6.278364e-01
## 1285 5.909155e-01
## 1289 5.736243e-01
## 1290 2.948783e-01
## 1301 5.893670e-01
## 1307 6.973598e-01
## 1309 3.078786e-01
## 1313 2.392111e-02
## 1329 6.048839e-01
## 1330 6.558765e-01
## 1333 6.641707e-01
## 1336 NA
confusion <- table(prob > 0.5,test$ATTORNEY)
table(prob > 0.5)
##
## FALSE TRUE
## 149 193
table(ATTORNEY)
## ATTORNEY
## 0 1
## 685 655
confusion
##
## 0 1
## FALSE 123 26
## TRUE 58 135
table(prob > 0.5)
##
## FALSE TRUE
## 149 193
table(test$CLMAGE)
##
## 0 1 3 4 5 6 7 8 9 10 11 13 14 15 16 17 18 19 30 31 33 34 35 36 37
## 12 5 4 3 11 15 10 13 14 16 10 11 5 7 7 3 4 10 17 4 4 7 6 5 11
## 38 39 40 41 43 44 45 46 47 48 49 50 51 53 54 55 56 57 58 59 60 61 63 64 65
## 7 13 15 5 6 7 3 5 5 8 6 9 2 3 2 1 3 3 4 2 5 3 3 3 1
## 66 67 68 69 70 71 75 77 78 80
## 4 1 1 1 2 2 1 1 2 2
confusion
##
## 0 1
## FALSE 123 26
## TRUE 58 135
#Model Accuracy
Accuracy <-sum(diag(confusion)/sum(confusion))
sum(diag(confusion))
## [1] 258
sum(confusion)
## [1] 342
Accuracy
## [1] 0.754386