tibble: Simple Data Frames

CRAN: http://cran.r-project.org/web/packages/tibble/index.html
GitHub: https://github.com/hadley/tibble
Vignettes: Data frames and table sources in "dplyr" style

> library(tibble)

バージョン: 1.3.1

関数名	概略
`add_column`	Add columns to a data frame
`add_row`	Add rows to a data frame
`as_tibble`	Coerce lists and matrices to data frames.
`enframe`	Converting atomic vectors to data frames, and vice versa
`frame_matrix`	Row-wise matrix creation
`glimpse`	Get a glimpse of your data.
`has_name`	Does an object have an element with this name?
`is.tibble`	Test if the object is a tibble.
`lst`	Build a list
`rownames`	Tools for working with row names
`set_tidy_names`	Repair object names.
`tibble-package`	tibble: Simple Data Frames
`tribble`	Row-wise tibble creation

add_row

行の追加

> (df <- data_frame(x = 1:3, y = 3:1))

# A tibble: 3 x 2
      x     y
  <int> <int>
1     1     3
2     2     2
3     3     1

> add_row(df, x = 4, y = 0)

# A tibble: 4 x 2
      x     y
  <dbl> <dbl>
1     1     3
2     2     2
3     3     1
4     4     0

all_equal

データフレーム構造の比較

ref) base::all.equal, dplyr::add_equal

> mtcars_df <- as_data_frame(mtcars)
> tibble:::all_equal(mtcars_df, mtcars_df)

Error in get(name, envir = asNamespace(pkg), inherits = FALSE): object 'all_equal' not found

> tibble:::all_equal(mtcars_df, mtcars)

Error in get(name, envir = asNamespace(pkg), inherits = FALSE): object 'all_equal' not found

as_data_frame

リスト、行列クラスのオブジェクトを強制的にデータフレームクラスのオブジェクトへと変換する

> l <- list(x = 1:500, y = runif(500), z = 500:1)
> (df <- as_data_frame(l))

# A tibble: 500 x 3
       x              y     z
   <int>          <dbl> <int>
 1     1 0.117581485538   500
 2     2 0.761716070119   499
 3     3 0.141795899253   498
 4     4 0.766908397898   497
 5     5 0.842138030799   496
 6     6 0.776749359677   495
 7     7 0.133827658836   494
 8     8 0.805936092744   493
 9     9 0.896782782627   492
10    10 0.926979867974   491
# ... with 490 more rows

> m <- matrix(rnorm(50), ncol = 5)
> (df <- as_data_frame(m))

# A tibble: 10 x 5
                V1              V2               V3               V4
             <dbl>           <dbl>            <dbl>            <dbl>
 1 -0.429531502079 -0.665818408586  0.1017221916258 -0.3067937000311
 2  0.131579552282  1.445858792643 -0.2889908762118  1.7048838403867
 3 -0.130438965975  0.791653292314  0.1395242777675  2.0223794317045
 4  0.731357619792  2.380875723873 -0.4393347992880 -0.0855216352114
 5 -0.115707706209  1.694230708376 -0.3905204582614  1.2936075877152
 6  0.651926695900 -1.836646051013 -0.8069781845554 -0.6028943723889
 7 -0.115131121322  0.321954472953  0.3841958461773 -1.2645116977316
 8  0.861137003272  1.075570148723  0.0678692859825  1.8855273485011
 9 -0.818637090271  0.380513700320  0.7705661905513  0.5194362498010
10 -0.826471792680 -0.722518627125 -0.4871169940771 -0.0751340136879
# ... with 1 more variables: V5 <dbl>

data_frame / lst

データフレームおよびリストの作成

> a <- 1:5
> data_frame(a, b = a * 2)

# A tibble: 5 x 2
      a     b
  <int> <dbl>
1     1     2
2     2     4
3     3     6
4     4     8
5     5    10

> data_frame(a, b = a * 2, c = 1)

# A tibble: 5 x 3
      a     b     c
  <int> <dbl> <dbl>
1     1     2     1
2     2     4     1
3     3     6     1
4     4     8     1
5     5    10     1

> data_frame(x = runif(10), y = x * 2)

# A tibble: 10 x 2
                x              y
            <dbl>          <dbl>
 1 0.224379061256 0.448758122511
 2 0.569050242659 1.138100485317
 3 0.610360722756 1.220721445512
 4 0.654660311993 1.309320623986
 5 0.261591032147 0.523182064295
 6 0.059085420100 0.118170840200
 7 0.556450227043 1.112900454085
 8 0.731231867801 1.462463735603
 9 0.401210993761 0.802421987522
10 0.998451555613 1.996903111227

> lst(n = 5, x = runif(n))

$n
[1] 5

$x
[1] 0.3745450654533 0.0728190739173 0.5882274415344 0.6285342019983
[5] 0.7971250561532

frame_data

行方向の指定によるデータフレーム生成

> frame_data(
+   ~colA, ~colB,
+   "a",   1,
+   "b",   2,
+   "c",   3
+ )

# A tibble: 3 x 2
   colA  colB
  <chr> <dbl>
1     a     1
2     b     2
3     c     3

> frame_data(
+   ~x,  ~y,
+   "a", 1:3,
+   "b", 4:6
+ )

# A tibble: 2 x 2
      x         y
  <chr>    <list>
1     a <int [3]>
2     b <int [3]>

glimpse

データ構造を概観する

> glimpse(mtcars)

Observations: 32
Variables: 11
$ mpg  <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19....
$ cyl  <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, ...
$ disp <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 1...
$ hp   <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, ...
$ drat <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.9...
$ wt   <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3...
$ qsec <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 2...
$ vs   <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, ...
$ am   <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, ...
$ gear <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, ...
$ carb <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, ...

repair_names

> list(3, 4, 5) %>% names()

NULL

> repair_names(list(3, 4, 5)) %>% names()

[1] "V1" "V2" "V3"

> mtcars %>% names()

 [1] "mpg"  "cyl"  "disp" "hp"   "drat" "wt"   "qsec" "vs"   "am"   "gear"
[11] "carb"

> repair_names(mtcars) %>% names() # 変更を加えない

 [1] "mpg"  "cyl"  "disp" "hp"   "drat" "wt"   "qsec" "vs"   "am"   "gear"
[11] "carb"

> tbl <- as_data_frame(structure(list(3, 4, 5), class = "data.frame"))

Error: Columns 1, 2, 3 must be named

> names(tbl)

NULL

> repair_names(tbl)

Error: `x` must be a vector

rownames / has_rownames / remove_rownames / rownames_to_column / column_to_rownames

行名に対する処理

> has_rownames(mtcars)

[1] TRUE

> has_rownames(iris)

[1] FALSE

> remove_rownames(mtcars) %>% has_rownames()

[1] FALSE

> mtcars_tbl <- as_data_frame(mtcars) %>% rownames_to_column()
> mtcars_tbl

# A tibble: 32 x 12
             rowname   mpg   cyl  disp    hp  drat    wt  qsec    vs    am
               <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
 1         Mazda RX4  21.0     6 160.0   110  3.90 2.620 16.46     0     1
 2     Mazda RX4 Wag  21.0     6 160.0   110  3.90 2.875 17.02     0     1
 3        Datsun 710  22.8     4 108.0    93  3.85 2.320 18.61     1     1
 4    Hornet 4 Drive  21.4     6 258.0   110  3.08 3.215 19.44     1     0
 5 Hornet Sportabout  18.7     8 360.0   175  3.15 3.440 17.02     0     0
 6           Valiant  18.1     6 225.0   105  2.76 3.460 20.22     1     0
 7        Duster 360  14.3     8 360.0   245  3.21 3.570 15.84     0     0
 8         Merc 240D  24.4     4 146.7    62  3.69 3.190 20.00     1     0
 9          Merc 230  22.8     4 140.8    95  3.92 3.150 22.90     1     0
10          Merc 280  19.2     6 167.6   123  3.92 3.440 18.30     1     0
# ... with 22 more rows, and 2 more variables: gear <dbl>, carb <dbl>

> column_to_rownames(mtcars_tbl)

Warning: Setting row names on a tibble is deprecated.

# A tibble: 32 x 11
     mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb
 * <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
 1  21.0     6 160.0   110  3.90 2.620 16.46     0     1     4     4
 2  21.0     6 160.0   110  3.90 2.875 17.02     0     1     4     4
 3  22.8     4 108.0    93  3.85 2.320 18.61     1     1     4     1
 4  21.4     6 258.0   110  3.08 3.215 19.44     1     0     3     1
 5  18.7     8 360.0   175  3.15 3.440 17.02     0     0     3     2
 6  18.1     6 225.0   105  2.76 3.460 20.22     1     0     3     1
 7  14.3     8 360.0   245  3.21 3.570 15.84     0     0     3     4
 8  24.4     4 146.7    62  3.69 3.190 20.00     1     0     4     2
 9  22.8     4 140.8    95  3.92 3.150 22.90     1     0     4     2
10  19.2     6 167.6   123  3.92 3.440 18.30     1     0     4     4
# ... with 22 more rows