crash1<-read.csv("C:\\Users\\dell\\Downloads\\crashTest_1.csv")
crash<-crash1[-1]
attach(crash)
str(crash)
## 'data.frame': 80 obs. of 6 variables:
## $ ManHI : num -5.27 -4.82 9.57 2.84 0 0.4 5.94 5.78 0.86 7.36 ...
## $ ManBI : num -1.3 -5.38 -7.5 -2.85 2.68 6.34 3.14 -1.75 -4.32 7.42 ...
## $ IntI : num 2.86 9.72 -7.61 0.92 -4.15 0.83 -6.65 -6.85 8.1 0.27 ...
## $ HVACi : num -4.85 -0.97 1.33 5.51 0.85 5.03 6.62 0.73 -8.96 -8.62 ...
## $ Safety : num 4.04 -4.57 -5.1 -6.64 5.58 -8.1 -1.32 5.5 3.1 3.08 ...
## $ CarType: Factor w/ 2 levels "Hatchback","SUV": 2 1 1 1 2 2 1 1 1 2 ...
str(as.data.frame(CarType))
## 'data.frame': 80 obs. of 1 variable:
## $ CarType: Factor w/ 2 levels "Hatchback","SUV": 2 1 1 1 2 2 1 1 1 2 ...
colnames(crash)
## [1] "ManHI" "ManBI" "IntI" "HVACi" "Safety" "CarType"
a<-na.omit(crash)
model<-glm(CarType~ManHI+ManBI+IntI+HVACi+Safety,family = binomial,data=crash)
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
summary(model)
##
## Call:
## glm(formula = CarType ~ ManHI + ManBI + IntI + HVACi + Safety,
## family = binomial, data = crash)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.316e-04 -2.100e-08 -2.100e-08 2.100e-08 1.266e-04
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -22.76 12007.54 -0.002 0.998
## ManHI -13.48 3077.29 -0.004 0.997
## ManBI 36.02 7221.18 0.005 0.996
## IntI -44.90 8853.08 -0.005 0.996
## HVACi -58.50 11461.92 -0.005 0.996
## Safety -27.36 5396.42 -0.005 0.996
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 1.0585e+02 on 79 degrees of freedom
## Residual deviance: 5.3590e-08 on 74 degrees of freedom
## AIC: 12
##
## Number of Fisher Scoring iterations: 25
coef(model)
## (Intercept) ManHI ManBI IntI HVACi Safety
## -22.75669 -13.48426 36.02350 -44.89958 -58.50108 -27.35946
exp(coef(model))
## (Intercept) ManHI ManBI IntI HVACi
## 1.308864e-10 1.392712e-06 4.413764e+15 3.164889e-20 3.920173e-26
## Safety
## 1.312013e-12
library(car)
## Loading required package: carData
library(MASS)
library(caret)
## Loading required package: lattice
## Loading required package: ggplot2
pred<-predict(model)
pred
## 1 2 3 4 5 6
## 46.25999 -406.21421 -18.56468 -345.70071 57.72788 90.32317
## 7 8 9 10 11 12
## -42.31979 -49.35749 -114.30599 553.18283 -431.90220 692.08543
## 13 14 15 16 17 18
## 101.08116 -19.92011 -182.14115 -980.43665 -514.10404 -31.76917
## 19 20 21 22 23 24
## 980.58256 188.48942 404.07895 -414.12997 -89.64923 -197.35827
## 25 26 27 28 29 30
## 270.36394 -865.52797 -719.11935 -442.57124 -491.75063 -485.67639
## 31 32 33 34 35 36
## -19.50981 -498.54696 -237.16151 640.08712 -298.64036 -502.61463
## 37 38 39 40 41 42
## 383.88979 867.65124 211.68519 18.64143 83.68517 246.31623
## 43 44 45 46 47 48
## -289.99820 -503.19316 300.43968 312.88115 -126.96957 -332.61768
## 49 50 51 52 53 54
## -350.27679 1142.56739 19.79938 459.23179 -172.40615 -151.00050
## 55 56 57 58 59 60
## -103.46539 -326.32660 602.68435 321.41241 -184.22242 -206.57080
## 61 62 63 64 65 66
## -689.94434 -113.94725 -633.80474 -711.90139 591.76575 -353.89898
## 67 68 69 70 71 72
## 1032.34100 -1030.03287 926.13298 -718.46176 -280.73824 -267.05925
## 73 74 75 76 77 78
## -527.49340 89.93298 -108.78654 -212.21226 156.05974 20.03001
## 79 80
## -105.79642 -570.74074
pv<-as.data.frame(pred)
final<-cbind(crash,pv)
table(CarType)
## CarType
## Hatchback SUV
## 50 30
table(pv>0.5)
##
## FALSE TRUE
## 50 30
confusion<-table(pv>0.5,CarType)
confusion
## CarType
## Hatchback SUV
## FALSE 50 0
## TRUE 0 30
accuracy<-(sum(diag(confusion))/sum(confusion))
accuracy
## [1] 1