Asignment 4 pt 2

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

sum(is.na(dirty_iris$Petal.Length))

## [1] 19

sum(complete.cases(dirty_iris))

## [1] 96

mean(complete.cases(dirty_iris)) * 100

## [1] 64

sapply(dirty_iris, function(col) {
  c(
    NA_count   = sum(is.na(col)),
    NaN_count  = sum(is.nan(col)),
    Inf_count  = sum(is.infinite(col))
  )
})

##           Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## NA_count            10          17           19          12       0
## NaN_count            0           0            0           0       0
## Inf_count            0           0            0           1       0

num_cols <- sapply(dirty_iris, is.numeric)
dirty_iris[, num_cols] <- lapply(dirty_iris[, num_cols, drop = FALSE], function(x) {
  x[is.infinite(x) | is.nan(x)] <- NA
  x
})

viol_idx <- which(
  (!is.na(dirty_iris$Sepal.Width)  & dirty_iris$Sepal.Width  <= 0) |
  (!is.na(dirty_iris$Sepal.Length) & dirty_iris$Sepal.Length >  30)
)

length(viol_idx)                  

## [1] 4

dirty_iris[viol_idx, ]           

##     Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
## 16           5.0          -3          3.5         1.0 versicolor
## 28          73.0          29         63.0          NA  virginica
## 125         49.0          30         14.0         2.0     setosa
## 130          5.7           0          1.7         0.3     setosa

violations <- subset(dirty_iris, Sepal.Width <= 0)
violations

##     Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
## 16           5.0          -3          3.5         1.0 versicolor
## 130          5.7           0          1.7         0.3     setosa

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


dirty_iris$Sepal.Width[!is.na(dirty_iris$Sepal.Width) & dirty_iris$Sepal.Width == 0] <- NA

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

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

lm_model <- lm(Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width, 
               data = dirty_iris)

pred_vals <- predict(lm_model, 
                     newdata = dirty_iris[is.na(dirty_iris$Sepal.Length), ])

dirty_iris$Sepal.Length[is.na(dirty_iris$Sepal.Length)] <- pred_vals

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 <- kNN(dirty_iris, variable = "Petal.Width", k = 5)

## Sepal.Length  Sepal.Width Petal.Length Sepal.Length  Sepal.Width Petal.Length 
##          0.0          2.2          0.0         73.0         30.0         63.0