Assignment 5

Insert Data and packages

pacman::p_load(dplyr)
pacman::p_load(VIM)
dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")

Q 1,2

sum(is.na(dirty_iris))

[1] 58

Q 3

summary(dirty_iris)

  Sepal.Length     Sepal.Width      Petal.Length    Petal.Width    Species         
 Min.   : 0.000   Min.   :-3.000   Min.   : 0.00   Min.   :0.1   Length:150        
 1st Qu.: 5.100   1st Qu.: 2.800   1st Qu.: 1.60   1st Qu.:0.3   Class :character  
 Median : 5.750   Median : 3.000   Median : 4.50   Median :1.3   Mode  :character  
 Mean   : 6.559   Mean   : 3.391   Mean   : 4.45   Mean   :Inf                     
 3rd Qu.: 6.400   3rd Qu.: 3.300   3rd Qu.: 5.10   3rd Qu.:1.8                     
 Max.   :73.000   Max.   :30.000   Max.   :63.00   Max.   :Inf                     
 NA's   :10       NA's   :17       NA's   :19      NA's   :12                      

Q 4

filter(dirty_iris, Petal.Width == Inf) %>%
  replace(4, NA)

dirty_iris[which(dirty_iris$Petal.Width == Inf), "Petal.Width"] <- NA

Q 5

impossible_iris <-
  dirty_iris %>%
  subset(Sepal.Width < 0 | Sepal.Length > 30)

Q 6

#dirty_iris %>%
#  filter(Sepal.Width < 0) %>%
#  replace(2, NA)

dirty_iris[which(dirty_iris$Sepal.Width < 0), "Sepal.Width"] <- NA

summary(dirty_iris)

  Sepal.Length     Sepal.Width      Petal.Length    Petal.Width      Species         
 Min.   : 0.000   Min.   : 0.000   Min.   : 0.00   Min.   :0.100   Length:150        
 1st Qu.: 5.100   1st Qu.: 2.800   1st Qu.: 1.60   1st Qu.:0.300   Class :character  
 Median : 5.750   Median : 3.000   Median : 4.50   Median :1.300   Mode  :character  
 Mean   : 6.559   Mean   : 3.439   Mean   : 4.45   Mean   :1.207                     
 3rd Qu.: 6.400   3rd Qu.: 3.300   3rd Qu.: 5.10   3rd Qu.:1.800                     
 Max.   :73.000   Max.   :30.000   Max.   :63.00   Max.   :2.500                     
 NA's   :10       NA's   :18       NA's   :19      NA's   :13                        

Q 7 -> Linear Regression Model

model <- lm(Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width,
            data = dirty_iris) #3: basic linear model
summary(dirty_iris) #3: always check

  Sepal.Length     Sepal.Width      Petal.Length    Petal.Width      Species         
 Min.   : 0.000   Min.   : 0.000   Min.   : 0.00   Min.   :0.100   Length:150        
 1st Qu.: 5.100   1st Qu.: 2.800   1st Qu.: 1.60   1st Qu.:0.300   Class :character  
 Median : 5.750   Median : 3.000   Median : 4.50   Median :1.300   Mode  :character  
 Mean   : 6.559   Mean   : 3.439   Mean   : 4.45   Mean   :1.207                     
 3rd Qu.: 6.400   3rd Qu.: 3.300   3rd Qu.: 5.10   3rd Qu.:1.800                     
 Max.   :73.000   Max.   :30.000   Max.   :63.00   Max.   :2.500                     
 NA's   :10       NA's   :18       NA's   :19      NA's   :13                        

I <- is.na(dirty_iris$Sepal.Length) #3: save missing values

dirty_iris$Sepal.Length[I] <- predict(model,
                         newdata = dirty_iris[I,]) #3: uses the model to predict values for Sepal.Length
summary(dirty_iris)

  Sepal.Length     Sepal.Width      Petal.Length    Petal.Width      Species         
 Min.   : 0.000   Min.   : 0.000   Min.   : 0.00   Min.   :0.100   Length:150        
 1st Qu.: 5.100   1st Qu.: 2.800   1st Qu.: 1.60   1st Qu.:0.300   Class :character  
 Median : 5.800   Median : 3.000   Median : 4.50   Median :1.300   Mode  :character  
 Mean   : 6.554   Mean   : 3.439   Mean   : 4.45   Mean   :1.207                     
 3rd Qu.: 6.400   3rd Qu.: 3.300   3rd Qu.: 5.10   3rd Qu.:1.800                     
 Max.   :73.000   Max.   :30.000   Max.   :63.00   Max.   :2.500                     
 NA's   :1        NA's   :18       NA's   :19      NA's   :13                        

Q7 -> Mean & Median

mean(dirty_iris$Sepal.Width, na.rm = TRUE)

[1] 3.393333

dirty_iris[is.na(dirty_iris$Sepal.Width)] <- mean(dirty_iris[!is.na(dirty_iris$Sepal.Width)])

Error in `[.data.frame`(dirty_iris, !is.na(dirty_iris$Sepal.Width)) : 
  undefined columns selected

Q 7 -> kNN

dirty_iris2 <- kNN(dirty_iris) #3: function auto fills in w column mean
dirty_iris <- subset(dirty_iris2, select = Sepal.Length:Species) #3: generates extra rows
summary(dirty_iris) 

  Sepal.Length     Sepal.Width      Petal.Length     Petal.Width      Species         
 Min.   : 0.000   Min.   : 0.000   Min.   : 0.000   Min.   :0.100   Length:150        
 1st Qu.: 5.100   1st Qu.: 2.800   1st Qu.: 1.600   1st Qu.:0.300   Class :character  
 Median : 5.800   Median : 3.000   Median : 4.400   Median :1.300   Mode  :character  
 Mean   : 6.543   Mean   : 3.393   Mean   : 4.307   Mean   :1.210                     
 3rd Qu.: 6.400   3rd Qu.: 3.300   3rd Qu.: 5.100   3rd Qu.:1.875                     
 Max.   :73.000   Max.   :30.000   Max.   :63.000   Max.   :2.500