{{counter}}
R
!!!R.package Rで便利なパッケージ
{{outline}}
!!パッケージのインストール
*たとえば、gplots を使いたい場合
{{pre
> install.packages("gplots", dependencies = T)
> library(gplots)
}}

!!stringr
!str_detect()
*該当する文字列があるかどうか調べる
 str_detect(データ, "正規表現")
*subset() と合わせて使うと便利
**データフレーム中の特定の列に「ある種の文字列」があるかどうかを調べて、その文字列を含む行だけを選び出す。
***「ある種の文字列」の例：小文字の連続で書かれている「単語」が複数あるもの
{{pre
fragJBnozeroMW <- subset(fragJBnozero, str_detect(fragJBnozero[,3], "[:lower:]+ +[^a-z]*[:lower:]+"), select=c("total","MW"))

> fragJBnozeroMW
     total                                MW
251    256                    a [NN] of [NP]
278    253                       do n't [VP]
285    252                  the [NN] of [NP]
291    219                       do not [VP]
306    235                      want to [VP]
325    240                             a lot
330    213                       for example
341    210                     a lot of [NP]
}}
----
参考サイト
https://heavywatal.github.io/rstats/stringr.html


!!psych
心理学系のパッケージ
基本的な記述統計量は <<summary(x)>>で出るが、
もう少し詳しく見るには、このパッケージをインストールして <<describe(x)>>を使う。
{{pre
> describe(x)
   vars   n mean   sd median trimmed  mad  min  max range  skew kurtosis   se
X1    1 100 0.06 1.06   0.04    0.07 0.87 -2.9 2.51  5.41 -0.04    -0.32 0.11
}}
*標準偏差、歪度、尖度、標準誤差なども出る。
!!tm
https://www.rdocumentation.org/packages/tm/versions/0.7-3

*Boost_tokenizer(x)
*MC_tokenizer(x)
*removePunctuation(tmp)
*removeNumbers(x)
----
{{pre
tmp.v <- Vectorsource(tmp)
tmp.c <- Corpus(tmp.v)
tmpc.td <- TermDocumentMatrix(tmp.c)
findFreqTerms(tmpc.td)
 findMostFreqTerms(tmpc.td)
$`1`
     the     said      and computer      its terminal 
      15        7        6        6        5        5 
}}
----

!!koRpus
https://reaktanz.de/R/pckg/koRpus/koRpus_vignette.html
*MTLD
 > library(koRpus)
 
 > ns002 <- tokenize(choose.files(), lang="en")
で、たとえば、NS002のテキストだけのファイルを読み込んで、

 > MTLD(ns002)
 Language: "en"
 
 Total number of tokens: 463
 Total number of types:  218
 
 Measure of Textual Lexical Diversity
                 MTLD: 87.62
    Number of factors: 5.28
          Factor size: 0.72
     SD tokens/factor: 36.8 (all factors)
                       30.05 (complete factors only)
 
 Note: Analysis was conducted case insensitive.

!!rpart

 >model1 = rpart(LMH ~ DD + SL + MDD, data = C3L2)
 
 > rpart.plot(model)

!!gplots
{{pre
install.packages("gplots", dependencies = T)
library(gplots)

> head(meanMHD)
  Group      MHD
1    C2 1.500000
2    C2 1.000000
3    C2 2.000000
4    C2 1.250000
5    C2 1.333333
6    C2 1.333333

attach(meanMHD)
plotmeans(MHD ~ Group)
detach(oneWayMHD)
}}
{{ref_image meanComparisonMHD.png}}

!!orddom
*psychパッケージがインストールしてあること
 orddom(x, y)
*これだけで各種効果量を出してくれて、お好きなのをどうぞ、って感じ。
{{pre
> orddom(dmu02shd$MDD, dmu03shd$MDD)
              ordinal                metric                
var1_X        "group 1 (x)"          "group 1 (x)"         
var2_Y        "group 2 (y)"          "group 2 (y)"         
type_title    "indep"                "indep"               
n in X        "592"                  "592"                 
n in Y        "547"                  "547"                 
N #Y>X        "176563"               "176563"              
N #Y=X        "13390"                "13390"               
N #Y<X        "133871"               "133871"              
PS X>Y        "0.413406665349078"    "0.432442005161643"   
PS Y>X        "0.545243712634023"    "0.567557994838357"   
A X>Y         "0.434081476357528"    "0.434081476357528"   
A Y>X         "0.565918523642472"    "0.565918523642472"   
delta         "0.131837047284944"    "0.128573222406733"   
1-alpha       "95"                   "95"                  
CI low        "0.0647643614128363"   "0.0665435144203836"  
CI high       "0.197723891470872"    "0.190602930393082"   
s delta       "0.0339578629779545"   "0.533045085206667"   
var delta     "0.00115313645802954"  "0.284137062862983"   
se delta      NA                     "0.0316134060048762"  
z/t score     "3.88237173141703"     "4.0670474540738"     
H1 tails p/CI "2"                    "2"                   
p             "0.000109396219747593" "5.52499619534335e-05"
Cohen's d     "0.177125083672158"    "0.241205155014015"   
d CI low      "0.0839111293425067"   "0.124543945177201"   
d CI high     "0.275869162430133"    "0.357866364850828"   
var d.i       "0.291361840460969"    "0.251891629550177"   
var dj.       "0.362041171144457"    "0.319040086833437"   
var dij       "0.941272277686609"    "0.569924729477023"   
df            "1137"                 "1094.88514066995"    
NNT           "7.58512133420789"     "5.70864949792907"    
}}

ノンパラメトリックの場合、Cliff's deltaをみると、以下の基準に基づき判断すればよい：
https://www.rdocumentation.org/packages/effsize/versions/0.7.4/topics/cliff.delta
 The magnitude is assessed using the thresholds provided in (Romano 2006), i.e. 
 |d|<0.147 "negligible", 
 |d|<0.33 "small", 
 |d|<0.474 "medium", 
 otherwise "large" 

!!effsize
{{pre
install.packages("effsize")
library(effsize)
> cliff.delta(dmu02shd$MDD, dmu03shd$MDD)

Cliff's Delta

delta estimate: -0.131837 (negligible)
95 percent confidence interval:
      lower       upper 
-0.19765420 -0.06483658 
}}
*「(negligible)」と、評価もコメントしてつけてくれる。

!!lawstat
Brunner-Munzel Testが入っている。
{{pre
> brunner.munzel.test(dmu02shd$MDD, dmu03shd$MDD)

        Brunner-Munzel Test

data:  dmu02shd$MDD and dmu03shd$MDD
Brunner-Munzel Test Statistic = 3.8809, df = 1098.7, p-value = 0.0001103
95 percent confidence interval:
 0.5325908 0.5992463
sample estimates:
P(X<Y)+.5*P(X=Y) 
       0.5659185 
}}

!!brunnermunzel
 install.packages("brunnermunzel")
 library(brunnermunzel)

{{pre
> brunnermunzel.test(dmu02shd$MDD, dmu03shd$MDD)

        Brunner-Munzel Test

data:  dmu02shd$MDD and dmu03shd$MDD
Brunner-Munzel Test Statistic = 3.8809, df = 1098.7, p-value = 0.0001103
95 percent confidence interval:
 0.5325908 0.5992463
sample estimates:
P(X<Y)+.5*P(X=Y) 
       0.5659185 
}}