Work - Classifier Assessment

Create dataframe

library("tidyverse")

## -- Attaching packages ------------------------------------- tidyverse 1.2.1 --

## v ggplot2 3.1.0     v purrr   0.2.5
## v tibble  1.4.2     v dplyr   0.7.8
## v tidyr   0.8.2     v stringr 1.3.1
## v readr   1.1.1     v forcats 0.3.0

## -- Conflicts ---------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library("caret")

## Loading required package: lattice

## 
## Attaching package: 'caret'

## The following object is masked from 'package:purrr':
## 
##     lift

Tweet <- c("a", "b", "c", "d", "e", "f", "g", "h", "i", "j")
Person.1 <- c(1, 2, 0, 1, 2, 1, 1, 1, 0, 0)
Person.2 <- c(2, 2, 0, 2, 1, 1, 2, 1, 1, 0)
Person.3 <- c(1, 2, 0, 1, 2, 2, 1, 1, 1, 0)


d <- tibble(Tweet, Person.1, Person.2, Person.3)


d$Person.1 <- as.numeric(d$Person.1)
d$Person.2 <- as.numeric(d$Person.2)
d$Person.3 <- as.numeric(d$Person.3)

d$Human.Extremist <- ifelse(d$Person.1 > 1 & d$Person.2 > 1 & d$Person.3 > 1 ,"YES", "NO")
d$ML.Extremist <- c("YES", "NO", "NO", "YES", "NO", "YES", "YES", "NO", "NO", "YES")
d

class.table <- table(d$Human.Extremist, d$ML.Extremist)
confusionMatrix(class.table)

## Confusion Matrix and Statistics
## 
##      
##       NO YES
##   NO   4   5
##   YES  1   0
##                                           
##                Accuracy : 0.4             
##                  95% CI : (0.1216, 0.7376)
##     No Information Rate : 0.5             
##     P-Value [Acc > NIR] : 0.8281          
##                                           
##                   Kappa : -0.2            
##  Mcnemar's Test P-Value : 0.2207          
##                                           
##             Sensitivity : 0.8000          
##             Specificity : 0.0000          
##          Pos Pred Value : 0.4444          
##          Neg Pred Value : 0.0000          
##              Prevalence : 0.5000          
##          Detection Rate : 0.4000          
##    Detection Prevalence : 0.9000          
##       Balanced Accuracy : 0.4000          
##                                           
##        'Positive' Class : NO              
##