assignment4

Q.3 Reading data

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

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

## [1] 19

Q.4 Calculating percentages of complete observations

rows_complete <- sum(complete.cases(dirty_iris))
mean(complete.cases(dirty_iris)) * 100

## [1] 64

Q.5 Deciphering hidden values

any(is.infinite(dirty_iris$Petal.Width))

## [1] TRUE

any(is.infinite(dirty_iris$Petal.Length))

## [1] FALSE

any(is.infinite(dirty_iris$Species))

## [1] FALSE

any(is.nan(dirty_iris$Sepal.Width))

## [1] FALSE

any(is.nan(dirty_iris$Petal.Length))

## [1] FALSE

any(is.nan(dirty_iris$Petal.Width))

## [1] FALSE

Q.6 Replacing specific values

inf_rows <- which(is.infinite(dirty_iris$Petal.Width))
print(inf_rows)

## [1] 86

print(dirty_iris$Petal.Width[inf_rows])

## [1] Inf

dirty_iris$Petal.Width[is.infinite(dirty_iris$Petal.Width)] <- NA

print(any(is.infinite(dirty_iris$Petal.Width)))

## [1] FALSE

summary(dirty_iris$Petal.Width)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.100   0.300   1.300   1.207   1.800   2.500      13

Q.7 correcting logical observation errors

bad_width  <- dirty_iris$Sepal.Width <= 0
bad_length <- dirty_iris$Sepal.Length > 30

violating_rows <- bad_width | bad_length
print(which(violating_rows))

## [1]  16  28 125 130

violating_rows <- subset(dirty_iris, Sepal.Width <= 0 | Sepal.Length > 30)
print(violating_rows)

##     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

print(nrow(violating_rows))

## [1] 4

Q.8 Locating and correcting values

neg_rows <- which(dirty_iris$Sepal.Width < 0)
dirty_iris$Sepal.Width[neg_rows] <- abs(dirty_iris$Sepal.Width[neg_rows])

zero_rows <- which(dirty_iris$Sepal.Width == 0)
dirty_iris$Sepal.Width[zero_rows] <- NA

print(any(dirty_iris$Sepal.Width < 0, na.rm = TRUE))   

## [1] FALSE

print(dirty_iris$Sepal.Width[c(35, 127)]) 

## [1] 2.9 3.2

Q.9 Imputing values into dataset

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

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

model_sl <- lm(Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width, data = dirty_iris)
pred_sl <- predict(model_sl, newdata = dirty_iris)
dirty_iris$Sepal.Length[is.na(dirty_iris$Sepal.Length)] <- pred_sl[is.na(dirty_iris$Sepal.Length)]