# Loading package
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.1.3
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
# Summary of dataset in package
summary(mtcars)
## mpg cyl disp hp
## Min. :10.40 Min. :4.000 Min. : 71.1 Min. : 52.0
## 1st Qu.:15.43 1st Qu.:4.000 1st Qu.:120.8 1st Qu.: 96.5
## Median :19.20 Median :6.000 Median :196.3 Median :123.0
## Mean :20.09 Mean :6.188 Mean :230.7 Mean :146.7
## 3rd Qu.:22.80 3rd Qu.:8.000 3rd Qu.:326.0 3rd Qu.:180.0
## Max. :33.90 Max. :8.000 Max. :472.0 Max. :335.0
## drat wt qsec vs
## Min. :2.760 Min. :1.513 Min. :14.50 Min. :0.0000
## 1st Qu.:3.080 1st Qu.:2.581 1st Qu.:16.89 1st Qu.:0.0000
## Median :3.695 Median :3.325 Median :17.71 Median :0.0000
## Mean :3.597 Mean :3.217 Mean :17.85 Mean :0.4375
## 3rd Qu.:3.920 3rd Qu.:3.610 3rd Qu.:18.90 3rd Qu.:1.0000
## Max. :4.930 Max. :5.424 Max. :22.90 Max. :1.0000
## am gear carb
## Min. :0.0000 Min. :3.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:2.000
## Median :0.0000 Median :4.000 Median :2.000
## Mean :0.4062 Mean :3.688 Mean :2.812
## 3rd Qu.:1.0000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :1.0000 Max. :5.000 Max. :8.000
# Installing the package
library(caTools)
## Warning: package 'caTools' was built under R version 4.1.3
library(ROCR)
## Warning: package 'ROCR' was built under R version 4.1.3
split <- sample.split(mtcars, SplitRatio = 0.8)
split
## [1] FALSE TRUE TRUE TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE
train_reg <- subset(mtcars, split == "TRUE")
test_reg <- subset(mtcars, split == "FALSE")
# Training model
logistic_model <- glm(vs ~ wt + disp,
data = train_reg,
family = "binomial")
logistic_model
##
## Call: glm(formula = vs ~ wt + disp, family = "binomial", data = train_reg)
##
## Coefficients:
## (Intercept) wt disp
## 1.65647 1.79241 -0.03439
##
## Degrees of Freedom: 22 Total (i.e. Null); 20 Residual
## Null Deviance: 31.84
## Residual Deviance: 14.68 AIC: 20.68
# Summary
summary(logistic_model)
##
## Call:
## glm(formula = vs ~ wt + disp, family = "binomial", data = train_reg)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.7803 -0.2803 -0.1045 0.4853 1.8240
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.65647 3.06669 0.540 0.5891
## wt 1.79241 1.84604 0.971 0.3316
## disp -0.03439 0.01733 -1.985 0.0472 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 31.841 on 22 degrees of freedom
## Residual deviance: 14.680 on 20 degrees of freedom
## AIC: 20.68
##
## Number of Fisher Scoring iterations: 6
# Predict test data based on model
predict_reg <- predict(logistic_model,
test_reg, type = "response")
predict_reg
## Mazda RX4 Duster 360 Merc 240D Merc 450SE Fiat 128
## 0.700637013 0.013064634 0.911281452 0.369834329 0.947516921
## Honda Civic AMC Javelin Ford Pantera L Ferrari Dino
## 0.875224073 0.066553241 0.008730546 0.836857719
# Changing probabilities
predict_reg <- ifelse(predict_reg >0.5, 1, 0)
# Evaluating model accuracy
# using confusion matrix
table(test_reg$vs, predict_reg)
## predict_reg
## 0 1
## 0 4 2
## 1 0 3
missing_classerr <- mean(predict_reg != test_reg$vs)
print(paste('Accuracy =', 1 - missing_classerr))
## [1] "Accuracy = 0.777777777777778"
# ROC-AUC Curve
ROCPred <- prediction(predict_reg, test_reg$vs)
ROCPer <- performance(ROCPred, measure = "tpr",
x.measure = "fpr")
auc <- performance(ROCPred, measure = "auc")
auc <- auc@y.values[[1]]
auc
## [1] 0.8333333
# Plotting curve
plot(ROCPer)
plot(ROCPer, colorize = TRUE,
print.cutoffs.at = seq(0.1, by = 0.1),
main = "ROC CURVE")
abline(a = 0, b = 1)
auc <- round(auc, 4)
legend(.6, .4, auc, title = "AUC", cex = 1)
