Untitled

library("pipeR")

cars %>>%
  (~plot(dist~speed,data=.)) %>>%
  (lm(dist~speed,data=.)) %>>%
  abline(col="red")

mtcars$mpg %>>%
  sample(size=1000,replace=TRUE) %>>%
  density(kernel="gaussian") %>>%
  plot(col="red",main="density of mpg")

関数の最初の引数にパイプ

rnorm(100) %>>%
  summary()

rnorm(100) %>>%
  plot(col="red")

表現式中のドット(.)にパイプ

mtcars %>>%
  (lm(mpg~cyl+wt,data=.))

## 
## Call:
## lm(formula = mpg ~ cyl + wt, data = .)
## 
## Coefficients:
## (Intercept)          cyl           wt  
##      39.686       -1.508       -3.191

ラムダ式でパイプ

ラムダ式　x ~ f(x)

mtcars %>>%
  (df ~ lm(mpg ~.,data=df))

## 
## Call:
## lm(formula = mpg ~ ., data = df)
## 
## Coefficients:
## (Intercept)          cyl         disp           hp         drat  
##    12.30337     -0.11144      0.01334     -0.02148      0.78711  
##          wt         qsec           vs           am         gear  
##    -3.71530      0.82104      0.31776      2.52023      0.65541  
##        carb  
##    -0.19942

副作用ありパイプ

print(),plot()など、帰り値の無い関数を

パイプラインの途中に含めたい

x %>>% (~plot()) %>>% f()

cars %>>%
  (~plot(dist~speed,data=.)) %>>%
  (lm(dist~speed,data=.)) %>>%
    abline(col="red")

#代入ありパイプ

途中の結果を変数に保存しつつパイプしたい

x %>>% f() %>>% (~ var_name)

cars %>>%
  (~plot(dist~speed,data=.)) %>>%
  (lm(dist~speed,data=.)) %>>%
  (~ lm_model) %>>%
  abline(col="red")

lm_model

## 
## Call:
## lm(formula = dist ~ speed, data = .)
## 
## Coefficients:
## (Intercept)        speed  
##     -17.579        3.932

代入ありパイプ

何か変換をかけて代入したい

x %>>% f() %>>%

(~ g(.) -> var_name)

cars %>>%
  (~plot(dist~speed,data=.)) %>>%
  (lm(dist~speed,data=.)) %>>%
  (~ summary(.) -> lm_model_summary) %>>%
  abline(col="red")

lm_model_summary

## 
## Call:
## lm(formula = dist ~ speed, data = .)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -29.069  -9.525  -2.272   9.215  43.201 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept) -17.5791     6.7584  -2.601   0.0123 *  
## speed         3.9324     0.4155   9.464 1.49e-12 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 15.38 on 48 degrees of freedom
## Multiple R-squared:  0.6511, Adjusted R-squared:  0.6438 
## F-statistic: 89.57 on 1 and 48 DF,  p-value: 1.49e-12

オブジェクトから要素を抽出

リストからの要素抽出　list$element をパイプでやりたい

list %>>% (element)

cars %>>%
  (~plot(dist~speed,data=.)) %>>%
  (lm(dist~speed,data=.)) %>>%
  (coefficients) %>>%
  (abline(.[1],.[2],col="red"))

dplyr

library("pipeR")
library(dplyr)

## 
## Attaching package: 'dplyr'
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

mtcars %>>%
  filter(mpg <= mean(mpg)) %>>%
  select(mpg,wt,cyl) %>>%
  (~ plot(.)) %>>%
  (model = lm(mpg ~ wt + cyl,data=.)) %>>%
  (summ = summary(.)) %>>%
  (coefficients)

##              Estimate Std. Error   t value     Pr(>|t|)
## (Intercept) 31.928632  4.0100333  7.962186 9.127888e-07
## wt          -2.183321  0.6536109 -3.340398 4.472574e-03
## cyl         -1.012133  0.5699081 -1.775959 9.602413e-02

#install.packages("dplyr")
#install.packages("babynames")


library(babynames) # data package
library(dplyr)     # provides data manipulating functions.
library(magrittr)  # ceci n'est pas un pipe
library(ggplot2)   # for graphics

data(babynames)

## Warning in data(babynames): data set 'babynames' not found

summary(babynames)

##       year          sex                name                 n          
##  Min.   :1880   Length:1792091     Length:1792091     Min.   :    5.0  
##  1st Qu.:1948   Class :character   Class :character   1st Qu.:    7.0  
##  Median :1981   Mode  :character   Mode  :character   Median :   12.0  
##  Mean   :1972                                         Mean   :  186.1  
##  3rd Qu.:2000                                         3rd Qu.:   32.0  
##  Max.   :2013                                         Max.   :99674.0  
##       prop          
##  Min.   :2.260e-06  
##  1st Qu.:3.930e-06  
##  Median :7.430e-06  
##  Mean   :1.422e-04  
##  3rd Qu.:2.366e-05  
##  Max.   :8.155e-02

str(babynames)

## Classes 'tbl_df', 'tbl' and 'data.frame':    1792091 obs. of  5 variables:
##  $ year: num  1880 1880 1880 1880 1880 1880 1880 1880 1880 1880 ...
##  $ sex : chr  "F" "F" "F" "F" ...
##  $ name: chr  "Mary" "Anna" "Emma" "Elizabeth" ...
##  $ n   : int  7065 2604 2003 1939 1746 1578 1472 1414 1320 1288 ...
##  $ prop: num  0.0724 0.0267 0.0205 0.0199 0.0179 ...

babynames %>% 
  filter(name %>% substr(1, 3) %>% equals("Ste")) %>% 
  group_by(year, sex) %>% 
  summarize(total = sum(n)) %>%
  qplot(year, total, color = sex, data = ., geom = "line") %>%
  add(ggtitle('Names starting with "Ste"')) %>% 
  print