Functions for subsetting rows based on conditions or by position.
These are SciViews::R versions of tidyverse functions with standard
evaluation and formula-based non-standard evaluation (ending with underscore
_). They work with data.frame, data.table, and tibbles.
Functions:
filter_()- Keep rows that match conditionsfilter_out_()- Remove rows that match conditions (inverse offilter_())distinct_()- Keep only unique/distinct rows based on columnsslice_()- Select rows by position (index)slice_head_()- Select first n rows or proportionslice_tail_()- Select last n rows or proportion
filter_(.data = (.), ..., .by = NULL, .preserve = FALSE)
filter_out_(.data = (.), ..., .by = NULL, .preserve = FALSE)
distinct_(.data = (.), ..., .keep_all = FALSE, .method = "auto")
slice_(.data = (.), ..., .by = NULL, .preserve = NULL)
slice_head_(.data = (.), ..., n = 1L, prop, by = NULL, sort = TRUE)
slice_tail_(.data = (.), ..., n = 1L, prop, by = NULL, sort = TRUE)Arguments
- .data
A data frame (data.frame, data.table, or tibble)
- ...
For
filter_()andfilter_out_(): conditions as formulas (e.g.,~mpg > 20). Fordistinct_(): columns to use for uniqueness. Forslice_(): row positions.- .by
A list of names of the columns to use for grouping the data.
- .preserve
Logical. When
TRUE, preserve the grouping structure in the result. WhenFALSE(default), recalculate grouping based on the filtered data.- .keep_all
Logical. For
distinct_(), ifTRUE, keep all columns in the result. IfFALSE(default), keep only the distinct columns.- .method
The algorithm to use for grouping:
"radix","hash", or"auto"(by default)."auto"chose"radix"whensort = TRUEand"hash"otherwise.- n
Number of rows to keep
- prop
Proportion of rows to keep, between 0 and 1. Provide either
n, orpropbut not both simultaneously. If none is provided,n = 1is used. @param by A list of names of the columns to use for joining the two data frames.- by
A list of names of the columns to use for grouping the data.
- sort
If
TRUElargest group will be shown on top.
Value
A data frame with filtered/selected rows, maintaining the same class as the input (data.frame, data.table, or tibble).
Note
From {dplyr}, the slice_min(), slice_max() and slice_sample()
functions are not added yet.
See also
Examples
library(svTidy)
data(mtcars)
# Filter rows with condition
mtcars |> filter_(~mpg > 20)
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
#> Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
#> Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
#> Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
#> Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
#> Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
#> Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
#> Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
#> Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
#> Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
#> Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
#> Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
#> Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
#> Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2
# Remove rows matching condition (inverse of filter_())
mtcars |> filter_out_(~mpg > 20)
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
#> Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
#> Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
#> Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
#> Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
#> Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
#> Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
#> Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
#> Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
#> Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
#> Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
#> Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
#> AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
#> Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
#> Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
#> Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4
#> Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6
#> Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8
# Multiple conditions (AND logic)
mtcars |> filter_(~mpg > 20, ~cyl == 4)
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
#> Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
#> Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
#> Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
#> Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
#> Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
#> Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
#> Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
#> Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
#> Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
#> Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2
# Get distinct values for columns
mtcars |> distinct_(~cyl, ~gear)
#> cyl gear
#> Mazda RX4 6 4
#> Datsun 710 4 4
#> Hornet 4 Drive 6 3
#> Hornet Sportabout 8 3
#> Toyota Corona 4 3
#> Porsche 914-2 4 5
#> Ford Pantera L 8 5
#> Ferrari Dino 6 5
# Distinct with all columns kept
mtcars |> distinct_(~cyl, .keep_all = TRUE)
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> Mazda RX4 21.0 6 160 110 3.90 2.62 16.46 0 1 4 4
#> Datsun 710 22.8 4 108 93 3.85 2.32 18.61 1 1 4 1
#> Hornet Sportabout 18.7 8 360 175 3.15 3.44 17.02 0 0 3 2
# Slice specific rows
mtcars |> slice_(1, 5, 10)
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> Mazda RX4 21.0 6 160.0 110 3.90 2.62 16.46 0 1 4 4
#> Hornet Sportabout 18.7 8 360.0 175 3.15 3.44 17.02 0 0 3 2
#> Merc 280 19.2 6 167.6 123 3.92 3.44 18.30 1 0 4 4
# Select first 5 rows
mtcars |> slice_head_(n = 5)
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
#> Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
#> Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
#> Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
#> Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
# Select last 10% of rows
mtcars |> slice_tail_(prop = 0.1)
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> Ferrari Dino 19.7 6 145 175 3.62 2.77 15.5 0 1 5 6
#> Maserati Bora 15.0 8 301 335 3.54 3.57 14.6 0 1 5 8
#> Volvo 142E 21.4 4 121 109 4.11 2.78 18.6 1 1 4 2
# Grouped filtering
mtcars |>
group_by_(~cyl) |>
filter_(~mpg > mean(~mpg))
#> Warning: argument is not numeric or logical: returning NA
#> Warning: argument is not numeric or logical: returning NA
#> Warning: argument is not numeric or logical: returning NA
#> [1] mpg cyl disp hp drat wt qsec vs am gear carb
#> <0 rows> (or 0-length row.names)
#>
#> Grouped by: cyl [0 | NaN]