DescTools: Tools for Descriptive Statistics

記述統計学のためのツール

• CRAN: http://cran.r-project.org/web/packages/DescTools/index.html
• Vignettes:
  • Combinatorics (PDF)
  • DescToolsCompanion (PDF)
  • Tables In R (PDF)
• URL: http://www.stats.ox.ac.uk/pub/RWin/

> library(DescTools)

Attaching package: 'DescTools'

The following object is masked from 'package:data.tree':

    Sort

> data("d.pizza")

バージョン: 0.99.17

%c%

文字列の結合演算子

> "foo" %c% "bar"

[1] "foobar"

%like%

AUC

Arguments

• x, y
• method... trapezoid, step or spline
• na.rm

> data.frame(x = c(1, 2, 2.5), y = c(1, 2, 4)) %$% {
+   AUC(x, y) %>% print()
+   plot(x, y, type = "l", col = "blue", ylim = c(0, 4))
+ }
> # [1] 3

ColToHex

> ColToHex(c("lightblue", "salmon"))

[1] "#ADD8E6" "#FA8072"

ColToHsv

> ColToHsv("peachpuff")

        [,1]
h 0.07857143
s 0.27450980
v 1.00000000

ColToRgb

> ColToRgb("peachpuff")

      [,1]
red    255
green  218
blue   185

Desc

データの要約

> Desc(d.pizza$wrongpizza)

------------------------------------------------------------------------- 
d.pizza$wrongpizza (logical - dichotomous)

  length      n    NAs unique
   1'209  1'205      4      2

        freq   perc  lci.95  uci.95'
FALSE  1'122  93.1%   91.5%   94.4%
TRUE      83   6.9%    5.6%    8.5%

' 95%-CI Wilson

> Desc(iris)

------------------------------------------------------------------------- 
Describe data.frame

'data.frame':    150 obs. of  5 variables:
 1 $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
 2 $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
 3 $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
 4 $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
 5 $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

------------------------------------------------------------------------- 
1 - Sepal.Length (numeric)

  length       n     NAs  unique      0s    mean  meanSE
     150     150       0      35       0   5.843   0.068

     .05     .10     .25  median     .75     .90     .95
   4.600   4.800   5.100   5.800   6.400   6.900   7.255

   range      sd   vcoef     mad     IQR    skew    kurt
   3.600   0.828   0.142   1.038   1.300   0.309  -0.606

lowest : 4.3, 4.4 (3), 4.5, 4.6 (4), 4.7 (2)
highest: 7.3, 7.4, 7.6, 7.7 (4), 7.9

------------------------------------------------------------------------- 
2 - Sepal.Width (numeric)

  length       n     NAs  unique      0s    mean  meanSE
     150     150       0      23       0   3.057   0.036

     .05     .10     .25  median     .75     .90     .95
   2.345   2.500   2.800   3.000   3.300   3.610   3.800

   range      sd   vcoef     mad     IQR    skew    kurt
   2.400   0.436   0.143   0.445   0.500   0.313   0.139

lowest : 2.0, 2.2 (3), 2.3 (4), 2.4 (3), 2.5 (8)
highest: 3.9 (2), 4.0, 4.1, 4.2, 4.4

------------------------------------------------------------------------- 
3 - Petal.Length (numeric)

  length       n     NAs  unique      0s    mean  meanSE
     150     150       0      43       0    3.76    0.14

     .05     .10     .25  median     .75     .90     .95
    1.30    1.40    1.60    4.35    5.10    5.80    6.10

   range      sd   vcoef     mad     IQR    skew    kurt
    5.90    1.77    0.47    1.85    3.50   -0.27   -1.42

lowest : 1.0, 1.1, 1.2 (2), 1.3 (7), 1.4 (13)
highest: 6.3, 6.4, 6.6, 6.7 (2), 6.9

------------------------------------------------------------------------- 
4 - Petal.Width (numeric)

  length       n     NAs  unique      0s    mean  meanSE
     150     150       0      22       0    1.20    0.06

     .05     .10     .25  median     .75     .90     .95
    0.20    0.20    0.30    1.30    1.80    2.20    2.30

   range      sd   vcoef     mad     IQR    skew    kurt
    2.40    0.76    0.64    1.04    1.50   -0.10   -1.36

lowest : 0.1 (5), 0.2 (29), 0.3 (7), 0.4 (7), 0.5
highest: 2.1 (6), 2.2 (3), 2.3 (8), 2.4 (3), 2.5 (3)

------------------------------------------------------------------------- 
5 - Species (factor)

  length      n    NAs unique levels  dupes
     150    150      0      3      3      y

        level  freq   perc  cumfreq  cumperc
1      setosa    50  33.3%       50    33.3%
2  versicolor    50  33.3%      100    66.7%
3   virginica    50  33.3%      150   100.0%

d.pizza

ピザのデータ

> data("d.pizza")
> dplyr::glimpse(d.pizza)

Observations: 1,209
Variables: 16
$ index          <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, ...
$ date           <date> 2014-03-01, 2014-03-01, 2014-03-01, 2014-03-01...
$ week           <dbl> 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9,...
$ weekday        <dbl> 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,...
$ area           <fctr> Camden, Westminster, Westminster, Brent, Brent...
$ count          <int> 5, 2, 3, 2, 5, 1, 4, NA, 3, 6, 3, 5, 4, 1, 6, 5...
$ rabate         <lgl> TRUE, FALSE, FALSE, FALSE, TRUE, FALSE, TRUE, N...
$ price          <dbl> 65.655, 26.980, 40.970, 25.980, 57.555, 13.990,...
$ operator       <fctr> Rhonda, Rhonda, Allanah, Allanah, Rhonda, Alla...
$ driver         <fctr> Taylor, Butcher, Butcher, Taylor, Carter, Tayl...
$ delivery_min   <dbl> 20.0, 19.6, 17.8, 37.3, 21.8, 48.7, 49.3, 25.6,...
$ temperature    <dbl> 53.00, 56.40, 36.50, NA, 50.00, 27.00, 33.90, 5...
$ wine_ordered   <int> 0, 0, 0, 0, 0, 0, 1, NA, 0, 1, 1, 0, 0, 1, 0, 0...
$ wine_delivered <int> 0, 0, 0, 0, 0, 0, 1, NA, 0, 1, 1, 0, 0, 1, 0, 0...
$ wrongpizza     <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE...
$ quality        <ord> medium, high, NA, NA, medium, low, low, high, h...

DrawCircle

> Canvas(xlim = c(-5,5))
> DrawCircle(radius = 4:1, 
+            col    = c("white", "steelblue2", "white", "red"), 
+            lwd = 3, 
+            nv = 300)

Freq

> data(d.pizza)
> Freq(d.pizza$price) %>% kable()

HighLow

最小値と最大値を同時に算出する

> data(d.pizza)
> d.pizza %$% HighLow(temperature, na.rm = TRUE) %>% cat()

Error in HighLow(temperature, na.rm = TRUE): unused argument (na.rm = TRUE)

Outlier

外れ値を表示

> Outlier(d.pizza$temperature, na.rm = TRUE)

 [1] 20.00 20.45 22.20 20.35 22.10 21.30 21.00 21.60 21.70 21.80 22.20
[12] 22.50 20.40 21.90 19.40 20.20 19.30 20.20 22.40

ParseSASDatalines

Untable

> Untable(HairEyeColor) %>% head()

   Hair   Eye  Sex
1 Black Brown Male
2 Black Brown Male
3 Black Brown Male
4 Black Brown Male
5 Black Brown Male
6 Black Brown Male

> Untable(HairEyeColor) %>% str()

'data.frame':    592 obs. of  3 variables:
 $ Hair: Factor w/ 4 levels "Black","Brown",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ Eye : Factor w/ 4 levels "Brown","Blue",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ Sex : Factor w/ 2 levels "Male","Female": 1 1 1 1 1 1 1 1 1 1 ...
 - attr(*, "out.attrs")=List of 2
  ..$ dim     : Named int  4 4 2
  .. ..- attr(*, "names")= chr  "Hair" "Eye" "Sex"
  ..$ dimnames:List of 3
  .. ..$ Hair: chr  "Hair=Black" "Hair=Brown" "Hair=Red" "Hair=Blond"
  .. ..$ Eye : chr  "Eye=Brown" "Eye=Blue" "Eye=Hazel" "Eye=Green"
  .. ..$ Sex : chr  "Sex=Male" "Sex=Female"