assignment_4_34

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

## [1] 19

##returns 19

sum(complete.cases(dirty_iris))

## [1] 96

##96

nrow(dirty_iris)

## [1] 150

##150,,math…

sum(complete.cases(dirty_iris)) / nrow(dirty_iris) * 100

## [1] 64

##64 ##question6

dirty_iris[] <- lapply(dirty_iris, function(x) {
  if (is.numeric(x)) x[is.nan(x)] <- NA
  x
})

dirty_iris[] <- lapply(dirty_iris, function(x) {
  if (is.numeric(x)) {
    x[is.nan(x)] <- NA
    x[is.infinite(x)] <- NA 
  }
  x
})

##returns 4

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

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

##mean,median,regression,kNN

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)

if (!requireNamespace("VIM", quietly = TRUE)) install.packages("VIM")
library(VIM)

## Warning: package 'VIM' was built under R version 4.5.2

## Loading required package: colorspace

## Warning: package 'colorspace' was built under R version 4.5.2

## 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

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

train <- complete.cases(dirty_iris[, c("Sepal.Length","Sepal.Width","Petal.Length","Petal.Width")])
model <- lm(Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width, data = dirty_iris[train, ])

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