cannot remove empty/NA rows in r

General
1

Hi everyone. I used

bike_rides <- janitor::remove_empty(bike_rides,which = c("cols"))
bike_rides <- janitor::remove_empty(bike_rides,which = c("rows"))

and
bike_rides <- drop_na(bike_rides) to remove empty spaces but there are still null cells. should I use another additional function to remove them also? because remove_empty and drop_na haven't removed them
I created an additional df with the top 10 popular stations (pop_start_casual) and when I run head it shows one empty chr cell with no name of the station, however,
when I visualize, there are 10 stations and not 9 like in df.

structure(list(ride_id = c("87BD0A8EA5A32570", "24341A8FAEE386F7", 
"4283B31CE989D479", "C8E4240E1B632BBA", "9D5BFF5B0C04D47F", "AB31418818EA94C8", 
"946A1DB8348B4B9B", "24AFB4228EF3818B", "A92CAF8151A36DBF", "39772A41D9C87C83"
), rideable_type = c("docked_bike", "electric_bike", "docked_bike", 
"electric_bike", "docked_bike", "docked_bike", "docked_bike", 
"docked_bike", "docked_bike", "docked_bike"), started_at = structure(c(1598108198, 
1602799093, 1588528522, 1600633940, 1595518952, 1594405460, 1590768057, 
1592049184, 1606201093, 1592505360), tzone = "UTC", class = c("POSIXct", 
"POSIXt")), ended_at = structure(c(1598109882, 1602800578, 1588530184, 
1600634322, 1595519133, 1594405655, 1590772439, 1592050870, 1606201372, 
1592506655), tzone = "UTC", class = c("POSIXct", "POSIXt")), 
    start_station_name = c("Halsted St & Clybourn Ave", "Dearborn St & Erie St", 
    "Greenwood Ave & 47th St", "Clark St & Grace St", "Orleans St & Merchandise Mart Plaza", 
    "Damen Ave & Pierce Ave", "Columbus Dr & Randolph St", "Clark St & Schreiber Ave", 
    "Greenview Ave & Diversey Pkwy", "Kingsbury St & Erie St"
    ), start_station_id = c(331L, 110L, 252L, 165L, 100L, 69L, 
    195L, 453L, 319L, 74L), end_station_name = c("Clark St & Leland Ave", 
    "LaSalle St & Illinois St", "Lake Park Ave & 56th St", "Clark St & Wellington Ave", 
    "Sedgwick St & Huron St", "Damen Ave & Thomas St (Augusta Blvd)", 
    "Columbus Dr & Randolph St", "Chicago Ave & Sheridan Rd", 
    "Lincoln Ave & Roscoe St", "Broadway & Cornelia Ave"), end_station_id = c(326L, 
    181L, 345L, 156L, 111L, 183L, 195L, 603L, 230L, 303L), start_lat = c(41.909668, 
    41.894204, 41.8098, 41.9508371666667, 41.888243, 41.909396, 
    41.8847, 41.999252, 41.932589, 41.893808), start_lng = c(-87.648128, 
    -87.6292258333333, -87.5994, -87.6591698333333, -87.63639, 
    -87.677691, -87.6195, -87.671377, -87.665936, -87.641697), 
    end_lat = c(41.967096, 41.8906896666667, 41.7932, 41.9365458333333, 
    41.894666, 41.901315, 41.8847, 42.050491, 41.94334, 41.945529
    ), end_lng = c(-87.667429, -87.631892, -87.5878, -87.6476191666667, 
    -87.638437, -87.677409, -87.6195, -87.677821, -87.67097, 
    -87.646439), member_casual = c("member", "casual", "casual", 
    "member", "member", "member", "casual", "casual", "member", 
    "member"), ride_length = c(28.07, 24.75, 27.7, 6.37, 3.02, 
    3.25, 73.03, 28.1, 4.65, 21.58), start_hr = c(14L, 21L, 17L, 
    20L, 15L, 18L, 16L, 11L, 6L, 18L), day_of_week = structure(c(7L, 
    5L, 1L, 1L, 5L, 6L, 6L, 7L, 3L, 5L), levels = c("Sunday", 
    "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"
    ), class = c("ordered", "factor")), month = structure(c(8L, 
    10L, 5L, 9L, 7L, 7L, 5L, 6L, 11L, 6L), levels = c("January", 
    "February", "March", "April", "May", "June", "July", "August", 
    "September", "October", "November", "December"), class = c("ordered", 
    "factor")), date = structure(c(18496, 18550, 18385, 18525, 
    18466, 18453, 18411, 18426, 18590, 18431), class = "Date"), 
    day = c("22", "15", "03", "20", "23", "10", "29", "13", "24", 
    "18"), year = c("2020", "2020", "2020", "2020", "2020", "2020", 
    "2020", "2020", "2020", "2020")), row.names = c(NA, -10L), class = c("data.table", 
"data.frame"), .internal.selfref = <pointer: 0x0000021b875589c0>)
2 
library(data.table)
# dput doesn't come over cleanly as data.table, so use
# data frame
d <- structure(list(ride_id = c("87BD0A8EA5A32570", "24341A8FAEE386F7", 
"4283B31CE989D479", "C8E4240E1B632BBA", "9D5BFF5B0C04D47F", "AB31418818EA94C8", 
"946A1DB8348B4B9B", "24AFB4228EF3818B", "A92CAF8151A36DBF", "39772A41D9C87C83"
), rideable_type = c("docked_bike", "electric_bike", "docked_bike", 
"electric_bike", "docked_bike", "docked_bike", "docked_bike", 
"docked_bike", "docked_bike", "docked_bike"), started_at = structure(c(1598108198, 
1602799093, 1588528522, 1600633940, 1595518952, 1594405460, 1590768057, 
1592049184, 1606201093, 1592505360), tzone = "UTC", class = c("POSIXct", 
"POSIXt")), ended_at = structure(c(1598109882, 1602800578, 1588530184, 
1600634322, 1595519133, 1594405655, 1590772439, 1592050870, 1606201372, 
1592506655), tzone = "UTC", class = c("POSIXct", "POSIXt")), 
start_station_name = c("Halsted St & Clybourn Ave", "Dearborn St & Erie St", 
"Greenwood Ave & 47th St", "Clark St & Grace St", "Orleans St & Merchandise Mart Plaza", 
"Damen Ave & Pierce Ave", "Columbus Dr & Randolph St", "Clark St & Schreiber Ave", 
"Greenview Ave & Diversey Pkwy", "Kingsbury St & Erie St"
), start_station_id = c(331L, 110L, 252L, 165L, 100L, 69L, 
195L, 453L, 319L, 74L), end_station_name = c("Clark St & Leland Ave",
"LaSalle St & Illinois St", "Lake Park Ave & 56th St", "Clark St & Wellington Ave", 
"Sedgwick St & Huron St", "Damen Ave & Thomas St (Augusta Blvd)", 
"Columbus Dr & Randolph St", "Chicago Ave & Sheridan Rd", 
"Lincoln Ave & Roscoe St", "Broadway & Cornelia Ave"), end_station_id = c(326L, 
181L, 345L, 156L, 111L, 183L, 195L, 603L, 230L, 303L), start_lat = c(41.909668, 
41.894204, 41.8098, 41.9508371666667, 41.888243, 41.909396, 
41.8847, 41.999252, 41.932589, 41.893808), start_lng = c(-87.648128, 
-87.6292258333333, -87.5994, -87.6591698333333, -87.63639, 
-87.677691, -87.6195, -87.671377, -87.665936, -87.641697), 
end_lat = c(41.967096, 41.8906896666667, 41.7932, 41.9365458333333, 
41.894666, 41.901315, 41.8847, 42.050491, 41.94334, 41.945529
), end_lng = c(-87.667429, -87.631892, -87.5878, -87.6476191666667, 
-87.638437, -87.677409, -87.6195, -87.677821, -87.67097, 
-87.646439), member_casual = c("member", "casual", "casual", 
"member", "member", "member", "casual", "casual", "member", 
"member"), ride_length = c(28.07, 24.75, 27.7, 6.37, 3.02, 
3.25, 73.03, 28.1, 4.65, 21.58), start_hr = c(14L, 21L, 17L, 
20L, 15L, 18L, 16L, 11L, 6L, 18L), day_of_week = structure(c(7L, 
5L, 1L, 1L, 5L, 6L, 6L, 7L, 3L, 5L), levels = c("Sunday", 
"Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"
), class = c("ordered", "factor")), month = structure(c(8L, 
10L, 5L, 9L, 7L, 7L, 5L, 6L, 11L, 6L), levels = c("January", 
"February", "March", "April", "May", "June", "July", "August", 
"September", "October", "November", "December"), class = c("ordered", 
"factor")), date = structure(c(18496, 18550, 18385, 18525, 
18466, 18453, 18411, 18426, 18590, 18431), class = "Date"), 
day = c("22", "15", "03", "20", "23", "10", "29", "13", "24", 
"18"), year = c("2020", "2020", "2020", "2020", "2020", "2020", 
"2020", "2020", "2020", "2020")), row.names = c(NA, -10L), class = c("data.frame"))

# convert to data.table 
DT <- data.frame(d)

# there are no NA values in sample
complete.cases(DT)
#>  [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE

# introduce some
DT[1,1] <- NA
DT[2,2] <- NA
DT[3,3] <- NA
DT[4,4] <- NA
DT[5,5] <- NA
DT[6,6] <- NA

# confirm
complete.cases(DT)
#>  [1] FALSE FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE

# retain only rows without NA
na.omit(DT)
#>             ride_id rideable_type          started_at            ended_at
#> 7  946A1DB8348B4B9B   docked_bike 2020-05-29 16:00:57 2020-05-29 17:13:59
#> 8  24AFB4228EF3818B   docked_bike 2020-06-13 11:53:04 2020-06-13 12:21:10
#> 9  A92CAF8151A36DBF   docked_bike 2020-11-24 06:58:13 2020-11-24 07:02:52
#> 10 39772A41D9C87C83   docked_bike 2020-06-18 18:36:00 2020-06-18 18:57:35
#>               start_station_name start_station_id          end_station_name
#> 7      Columbus Dr & Randolph St              195 Columbus Dr & Randolph St
#> 8       Clark St & Schreiber Ave              453 Chicago Ave & Sheridan Rd
#> 9  Greenview Ave & Diversey Pkwy              319   Lincoln Ave & Roscoe St
#> 10        Kingsbury St & Erie St               74   Broadway & Cornelia Ave
#>    end_station_id start_lat start_lng  end_lat   end_lng member_casual
#> 7             195  41.88470 -87.61950 41.88470 -87.61950        casual
#> 8             603  41.99925 -87.67138 42.05049 -87.67782        casual
#> 9             230  41.93259 -87.66594 41.94334 -87.67097        member
#> 10            303  41.89381 -87.64170 41.94553 -87.64644        member
#>    ride_length start_hr day_of_week    month       date day year
#> 7        73.03       16      Friday      May 2020-05-29  29 2020
#> 8        28.10       11    Saturday     June 2020-06-13  13 2020
#> 9         4.65        6     Tuesday November 2020-11-24  24 2020
#> 10       21.58       18    Thursday     June 2020-06-18  18 2020
3

Thank you for your reply.

Then what is this? look at my screenshot pls.
I am still learning, don't judge me too harshly, please. Maybe for you, it is obvious, but for me not.

image
image1855×721 165 KB

4

a blank string is not an NA_character_.

identical(NA_character_,"")

You can choose to convert all your empty strings to NA character, and then omit on that basis.

library(tidyverse)

df_ <- tibble(
  a = letters[1:6],
  b = LETTERS[1:6]
)

df_[3, 1] <- ""  # <- have a blank string

df_ <- mutate(
  df_,
  across(
    where(is.character),
    ~ if_else(.x == "", NA_character_, .x)
  )
)

na.omit(df_)
2 Likes
5

so when I use this function:

it does not remove emty rows?

6

Removes all rows and/or columns from a data.frame or matrix that are composed entirely of NA values.

if you have a blank string, this is not an NA, and the row is not entirely NA and will kept.

1 Like
7

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.