Assignment 5

Q1

dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")
sum(is.na(dirty_iris$Petal.Length))

## [1] 19

Q2

cc <- sum(complete.cases(dirty_iris))
percent_complete <- (cc / nrow(dirty_iris))

cc

## [1] 96

percent_complete

## [1] 0.64

Q3

numeric_columns <- sapply(dirty_iris, is.numeric)
nan_values <- sapply(dirty_iris[, numeric_columns], function(x) sum(is.nan(x)))

inf_values <- sapply(dirty_iris[, numeric_columns], function(x) sum(x == Inf))
neg_inf_values <- sapply(dirty_iris[, numeric_columns], function(x) sum(x == -Inf))

nan_values

## Sepal.Length  Sepal.Width Petal.Length  Petal.Width 
##            0            0            0            0

inf_values

## Sepal.Length  Sepal.Width Petal.Length  Petal.Width 
##           NA           NA           NA           NA

neg_inf_values

## Sepal.Length  Sepal.Width Petal.Length  Petal.Width 
##           NA           NA           NA           NA

Q4

str(dirty_iris)

## 'data.frame':    150 obs. of  5 variables:
##  $ Sepal.Length: num  6.4 6.3 6.2 5 5.7 5.3 6.4 5.9 5.8 4.8 ...
##  $ Sepal.Width : num  3.2 3.3 NA 3.4 2.6 NA 2.7 3 2.7 3.1 ...
##  $ Petal.Length: num  4.5 6 5.4 1.6 3.5 NA 5.3 5.1 4.1 1.6 ...
##  $ Petal.Width : num  1.5 2.5 2.3 0.4 1 0.2 NA 1.8 1 0.2 ...
##  $ Species     : chr  "versicolor" "virginica" "virginica" "setosa" ...

dirty_iris[is.nan(as.matrix(dirty_iris))] <- NA
dirty_iris[is.infinite(as.matrix(dirty_iris))] <- NA

Q5

# Logical vectors for each condition
v1 <- dirty_iris$Sepal.Width <= 0
v1

##   [1] FALSE FALSE    NA FALSE FALSE    NA FALSE FALSE FALSE FALSE FALSE FALSE
##  [13] FALSE FALSE FALSE  TRUE    NA FALSE FALSE    NA FALSE    NA FALSE FALSE
##  [25] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [37] FALSE FALSE FALSE FALSE    NA FALSE    NA FALSE FALSE FALSE    NA FALSE
##  [49] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [73] FALSE    NA FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [85] FALSE FALSE FALSE FALSE FALSE FALSE FALSE    NA FALSE FALSE FALSE FALSE
##  [97] FALSE    NA FALSE FALSE FALSE FALSE FALSE FALSE FALSE    NA FALSE FALSE
## [109] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE    NA FALSE FALSE FALSE
## [121] FALSE FALSE FALSE FALSE FALSE FALSE FALSE    NA FALSE  TRUE FALSE FALSE
## [133]    NA FALSE FALSE FALSE FALSE FALSE FALSE FALSE    NA    NA FALSE FALSE
## [145] FALSE FALSE FALSE FALSE FALSE FALSE

v2 <- dirty_iris$Sepal.Length > 30
v2

##   [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [13] FALSE FALSE    NA FALSE FALSE FALSE    NA FALSE FALSE FALSE FALSE FALSE
##  [25]    NA FALSE FALSE  TRUE FALSE    NA FALSE FALSE FALSE FALSE FALSE FALSE
##  [37] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [49] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE    NA FALSE FALSE
##  [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE    NA FALSE FALSE FALSE FALSE
##  [73] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [85] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [97] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [109] FALSE FALSE FALSE FALSE FALSE    NA FALSE FALSE FALSE FALSE    NA    NA
## [121] FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [133] FALSE FALSE FALSE FALSE FALSE    NA FALSE FALSE FALSE FALSE FALSE FALSE
## [145] FALSE FALSE FALSE FALSE FALSE FALSE

Q6

dirty_iris$Sepal.Width[is.na(dirty_iris$Sepal.Width)] <- 0
dirty_iris$Sepal.Width[dirty_iris$Sepal.Width < 0] <- abs(dirty_iris$Sepal.Width[dirty_iris$Sepal.Width < 0])

print(dirty_iris$Sepal.Width)

##   [1]  3.2  3.3  0.0  3.4  2.6  0.0  2.7  3.0  2.7  3.1  3.5  2.7  3.0  2.8  3.9
##  [16]  3.0  0.0  3.2  4.0  0.0  3.6  0.0  2.8  3.3  3.0  3.2  3.1 29.0  3.2  2.8
##  [31]  3.2  3.2  2.8  2.9  2.9  3.0  3.0  2.2  2.5  3.0  0.0  2.7  0.0  2.7  4.2
##  [46]  2.8  0.0  3.2  3.0  3.4  2.6  3.1  2.7  3.4  3.3  3.8  3.8  2.9  2.8  2.8
##  [61]  2.3  2.8  3.0  3.3  3.0  2.5  2.5  3.2  3.5  3.5  3.0  3.1  3.5  0.0  2.8
##  [76]  2.5  3.5  3.0  3.8  3.8  2.6  3.4  2.9  3.7  3.0  3.8  2.9  2.9  2.9  2.5
##  [91]  3.2  0.0  3.4  2.7  2.2  3.1  2.3  0.0  3.0  2.8  3.4  3.6  2.7  3.0  3.7
## [106]  0.0  3.0  3.0  2.8  3.4  3.4  3.4  3.4  3.3  3.1  2.6  0.0  3.1  3.0  2.8
## [121]  3.0  2.3  3.2  4.1 30.0  2.9  3.2  0.0  3.6  0.0  2.5  3.1  0.0  3.3  3.0
## [136]  3.0  3.2  3.0  3.1  2.2  0.0  0.0  3.0  2.9  2.5  3.1  3.0  3.5  3.1  2.6

Q7

# Mean
dirty_iris$Sepal.Width[is.na(dirty_iris$Sepal.Width)] <- mean(dirty_iris$Sepal.Width, na.rm = TRUE)

# Median
dirty_iris$Petal.Length[is.na(dirty_iris$Petal.Length)] <- median(dirty_iris$Petal.Length, na.rm = TRUE)

# Linear regression
# couldnt do it :(

# kNN imputation
library(VIM)

## Loading required package: colorspace

## Loading required package: grid

## VIM is ready to use.

## Suggestions and bug-reports can be submitted at: https://github.com/statistikat/VIM/issues

## 
## Attaching package: 'VIM'

## The following object is masked from 'package:datasets':
## 
##     sleep

dirty_iris_imputed <- kNN(dirty_iris, k = 5)
dirty_iris$Petal.Width <- dirty_iris_imputed$Petal.Width
sum(is.na(dirty_iris$Petal.Width))

## [1] 0

summary(dirty_iris$Petal.Width)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.100   0.300   1.300     Inf   1.875     Inf