Data Cleaning

Subset Data

Basic subset of rows based on criteria

new <- subset(old, old$variable > 4 | old$variable > 4)

Subset only a few columns

attr <- attr[4:12]

Subset rows and only keeping certain columns

new <- subset(old, old$variable > 4 | old$variable > 4, select=c(var1, var2))

Subset with list

c_perf <- subset(perf, perf$task_id %in% c(A, B, C, D, E)

###Merge or Join Data merge two data frames by ID total <- merge(data frameA,data frameB,by="ID")

join two dataframes using the dplyr package (analog to SQL joins) analysis <- left_join(pc_perf,attr,by = "task_id")

Rename Variables

# Many options for this. Two are below
#Rename the second column of the cars df as Stopping Distance (ft)
colnames(cars)[2] <-"Stopping Distance (ft)"

###Rename the variable that is currently "dist" of the cars df as Stopping Distance (ft)
cars %>% 
  rename("Stopping Distance (ft)" = dist) %>% 
  colnames()

Missing data Count NAs in all columns of a df

df %>%
  select(everything()) %>%  
  summarise_all(funs(sum(is.na(.))))

Convert Factor to date 

vou19_20$Date <- mdy_hms((vou19_20$StartDate))

###Create Percentile Rank Variable

df$percentile <- ecdf(df$score)(df$score)