###options為設定，digits為小數點3位，width線寬
options(digits=3)
options(width=72) # narrow output
ds = read.csv("http://www.amherst.edu/~nhorton/r2/datasets/help.csv")
###使用dplyr語法
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
newds = select(ds, cesd, female, i1, i2, id, treat, f1a, f1b, f1c, f1d, f1e,
f1f, f1g, f1h, f1i, f1j, f1k, f1l, f1m, f1n, f1o, f1p, f1q, f1r, f1s, f1t)
###names了解newds資料------------------------------------------------------------------------
names(newds)
## [1] "cesd" "female" "i1" "i2" "id" "treat" "f1a"
## [8] "f1b" "f1c" "f1d" "f1e" "f1f" "f1g" "f1h"
## [15] "f1i" "f1j" "f1k" "f1l" "f1m" "f1n" "f1o"
## [22] "f1p" "f1q" "f1r" "f1s" "f1t"
str(newds[,1:10]) # 建構10個變項structure of the first 10 variables
## 'data.frame': 453 obs. of 10 variables:
## $ cesd : int 49 30 39 15 39 6 52 32 50 46 ...
## $ female: int 0 0 0 1 0 1 1 0 1 0 ...
## $ i1 : int 13 56 0 5 10 4 13 12 71 20 ...
## $ i2 : int 26 62 0 5 13 4 20 24 129 27 ...
## $ id : int 1 2 3 4 5 6 7 8 9 10 ...
## $ treat : int 1 1 0 0 0 1 0 1 0 1 ...
## $ f1a : int 3 3 3 0 3 1 3 1 3 2 ...
## $ f1b : int 2 2 2 0 0 0 1 1 2 3 ...
## $ f1c : int 3 0 3 1 3 1 3 2 3 3 ...
## $ f1d : int 0 3 0 3 3 3 1 3 1 0 ...
summary(newds[,1:10]) # 總結10個變項summary of the first 10 variables
## cesd female i1 i2
## Min. : 1.0 Min. :0.000 Min. : 0.0 Min. : 0.0
## 1st Qu.:25.0 1st Qu.:0.000 1st Qu.: 3.0 1st Qu.: 3.0
## Median :34.0 Median :0.000 Median : 13.0 Median : 15.0
## Mean :32.8 Mean :0.236 Mean : 17.9 Mean : 22.6
## 3rd Qu.:41.0 3rd Qu.:0.000 3rd Qu.: 26.0 3rd Qu.: 32.0
## Max. :60.0 Max. :1.000 Max. :142.0 Max. :184.0
## id treat f1a f1b
## Min. : 1 Min. :0.000 Min. :0.00 Min. :0.00
## 1st Qu.:119 1st Qu.:0.000 1st Qu.:1.00 1st Qu.:0.00
## Median :233 Median :0.000 Median :2.00 Median :1.00
## Mean :233 Mean :0.497 Mean :1.63 Mean :1.39
## 3rd Qu.:348 3rd Qu.:1.000 3rd Qu.:3.00 3rd Qu.:2.00
## Max. :470 Max. :1.000 Max. :3.00 Max. :3.00
## f1c f1d
## Min. :0.00 Min. :0.00
## 1st Qu.:1.00 1st Qu.:0.00
## Median :2.00 Median :1.00
## Mean :1.92 Mean :1.56
## 3rd Qu.:3.00 3rd Qu.:3.00
## Max. :3.00 Max. :3.00
###head看前三行------------------------------------------------------------------------
head(newds, n=3)
## cesd female i1 i2 id treat f1a f1b f1c f1d f1e f1f f1g f1h f1i f1j
## 1 49 0 13 26 1 1 3 2 3 0 2 3 3 0 2 3
## 2 30 0 56 62 2 1 3 2 0 3 3 2 0 0 3 0
## 3 39 0 0 0 3 0 3 2 3 0 2 2 1 3 2 3
## f1k f1l f1m f1n f1o f1p f1q f1r f1s f1t
## 1 3 0 1 2 2 2 2 3 3 2
## 2 3 0 0 3 0 0 0 2 0 0
## 3 1 0 1 3 2 0 0 3 2 0
###comment命名物件或變數
comment(newds) = "HELP baseline dataset"
comment(newds)
## [1] "HELP baseline dataset"
###存檔
save(ds, file="savedfile")
###write載入資料------------------------------------------------------------------------
write.csv(ds, file="ds.csv")
###使用foreign包裝，寫入newds資料------------------------------------------------------------------------
library(foreign)
write.foreign(newds, "file.dat", "file.sas", package="SAS")
###[1:10]列出newds的1到10個資料------------------------------------------------------------------------
with(newds, cesd[1:10])
## [1] 49 30 39 15 39 6 52 32 50 46
with(newds, head(cesd, 10))
## [1] 49 30 39 15 39 6 52 32 50 46
###[cesd > 56]篩選大於56的資料------------------------------------------------------------------------
with(newds, cesd[cesd > 56])
## [1] 57 58 57 60 58 58 57
###運用dplyr語法篩選大於56的資料、id------------------------------------------------------------------------
library(dplyr)
filter(newds, cesd > 56) %>% select(id, cesd)
## id cesd
## 1 71 57
## 2 127 58
## 3 200 57
## 4 228 60
## 5 273 58
## 6 351 58
## 7 13 57
###[1:4]列出newds的1到4個資料------------------------------------------------------------------------
with(newds, sort(cesd)[1:4])
## [1] 1 3 3 4
##which.min找出最小值
with(newds, which.min(cesd))
## [1] 199
###載入mosaic------------------------------------------------------------------------
library(mosaic)
## Loading required package: lattice
## Loading required package: ggformula
## Loading required package: ggplot2
## Loading required package: ggstance
##
## Attaching package: 'ggstance'
## The following objects are masked from 'package:ggplot2':
##
## geom_errorbarh, GeomErrorbarh
##
## New to ggformula? Try the tutorials:
## learnr::run_tutorial("introduction", package = "ggformula")
## learnr::run_tutorial("refining", package = "ggformula")
## Loading required package: mosaicData
## Loading required package: Matrix
## Registered S3 method overwritten by 'mosaic':
## method from
## fortify.SpatialPolygonsDataFrame ggplot2
##
## The 'mosaic' package masks several functions from core packages in order to add
## additional features. The original behavior of these functions should not be affected by this.
##
## Note: If you use the Matrix package, be sure to load it BEFORE loading mosaic.
##
## Have you tried the ggformula package for your plots?
##
## Attaching package: 'mosaic'
## The following object is masked from 'package:Matrix':
##
## mean
## The following object is masked from 'package:ggplot2':
##
## stat
## The following objects are masked from 'package:dplyr':
##
## count, do, tally
## The following objects are masked from 'package:stats':
##
## binom.test, cor, cor.test, cov, fivenum, IQR, median,
## prop.test, quantile, sd, t.test, var
## The following objects are masked from 'package:base':
##
## max, mean, min, prod, range, sample, sum
##tally判斷f1g項目NA的數量
tally(~ is.na(f1g), data=newds)
## is.na(f1g)
## TRUE FALSE
## 1 452
###favstats描述統計f1g
favstats(~ f1g, data=newds)
## min Q1 median Q3 max mean sd n missing
## 0 1 2 3 3 1.73 1.1 452 1
###cesditems反向建立排序reverse code f1d, f1h, f1l and f1p
cesditems = with(newds, cbind(f1a, f1b, f1c, (3 - f1d), f1e, f1f, f1g,
(3 - f1h), f1i, f1j, f1k, (3 - f1l), f1m, f1n, f1o, (3 - f1p),
f1q, f1r, f1s, f1t))
###apply計算NA數量
nmisscesd = apply(is.na(cesditems), 1, sum)
ncesditems = cesditems
###ncesditems將NA設為0
ncesditems[is.na(cesditems)] = 0
newcesd = apply(ncesditems, 1, sum)
###設定算式
imputemeancesd = 20/(20-nmisscesd)*newcesd
###列出上面設定的資料
data.frame(newcesd, newds$cesd, nmisscesd, imputemeancesd)[nmisscesd>0,]
## newcesd newds.cesd nmisscesd imputemeancesd
## 4 15 15 1 15.8
## 17 19 19 1 20.0
## 87 44 44 1 46.3
## 101 17 17 1 17.9
## 154 29 29 1 30.5
## 177 44 44 1 46.3
## 229 39 39 1 41.1
###借用dplyr語法、memisc檔案----createdrink,message=FALSE-------------------------------------------
library(dplyr)
library(memisc)
## Loading required package: MASS
##
## Attaching package: 'MASS'
## The following object is masked from 'package:dplyr':
##
## select
##
## Attaching package: 'memisc'
## The following object is masked from 'package:Matrix':
##
## as.array
## The following object is masked from 'package:ggplot2':
##
## syms
## The following objects are masked from 'package:dplyr':
##
## collect, recode, rename, syms
## The following objects are masked from 'package:stats':
##
## contr.sum, contr.treatment, contrasts
## The following object is masked from 'package:base':
##
## as.array
###mutate增加新變項
newds = mutate(newds, drinkstat=
cases(
"abstinent" = i1==0,
"moderate" = (i1>0 & i1<=1 & i2<=3 & female==1) |
(i1>0 & i1<=2 & i2<=4 & female==0),
"highrisk" = ((i1>1 | i2>3) & female==1) |
((i1>2 | i2>4) & female==0)))
## i1 i2 female drinkstat
## 365 6 24 0 highrisk
## 366 6 6 0 highrisk
## 367 0 0 0 abstinent
## 368 0 0 1 abstinent
## 369 8 8 0 highrisk
## 370 32 32 0 highrisk
## i1 i2 female drinkstat
## 1 1 1 1 moderate
## 2 1 3 1 moderate
## 3 1 2 1 moderate
## 4 1 1 1 moderate
## 5 1 1 1 moderate
## 6 1 1 1 moderate
## 7 1 1 1 moderate
###運用gmodels語法，CrossTable為描述變數的次數分配
library(gmodels)
with(tmpds, CrossTable(drinkstat))
##
##
## Cell Contents
## |-------------------------|
## | N |
## | N / Table Total |
## |-------------------------|
##
##
## Total Observations in Table: 453
##
##
## | abstinent | moderate | highrisk |
## |-----------|-----------|-----------|
## | 68 | 28 | 357 |
## | 0.150 | 0.062 | 0.788 |
## |-----------|-----------|-----------|
##
##
##
##
###呈現表格 ------------------------------------------------------------------------
with(tmpds, CrossTable(drinkstat, female,
prop.t=FALSE, prop.c=FALSE, prop.chisq=FALSE))
##
##
## Cell Contents
## |-------------------------|
## | N |
## | N / Row Total |
## |-------------------------|
##
##
## Total Observations in Table: 453
##
##
## | female
## drinkstat | 0 | 1 | Row Total |
## -------------|-----------|-----------|-----------|
## abstinent | 42 | 26 | 68 |
## | 0.618 | 0.382 | 0.150 |
## -------------|-----------|-----------|-----------|
## moderate | 21 | 7 | 28 |
## | 0.750 | 0.250 | 0.062 |
## -------------|-----------|-----------|-----------|
## highrisk | 283 | 74 | 357 |
## | 0.793 | 0.207 | 0.788 |
## -------------|-----------|-----------|-----------|
## Column Total | 346 | 107 | 453 |
## -------------|-----------|-----------|-----------|
##
##
###設定男女性別的代數，tally判斷數量------------------------------------------------------------------------
newds = transform(newds,
gender=factor(female, c(0,1), c("Male","Female")))
tally(~ female + gender, margin=FALSE, data=newds)
## gender
## female Male Female
## 0 346 0
## 1 0 107
###運用dplyr語法，排序ds, cesd, i1，顯現第1-5個資料 ------------------------------------------------------------------------
library(dplyr)
newds = arrange(ds, cesd, i1)
newds[1:5, c("cesd", "i1", "id")]
## cesd i1 id
## 1 1 3 233
## 2 3 1 139
## 3 3 13 418
## 4 4 4 251
## 5 4 9 95
###運用dplyr語法，篩選女性，顯現cesd平均------------------------------------------------------------------------
library(dplyr)
females = filter(ds, female==1)
with(females, mean(cesd))
## [1] 36.9
###另一種方法同樣結果an alternative approach
mean(ds$cesd[ds$female==1])
## [1] 36.9
###tapply計算cesd男女平均次數------------------------------------------------------------------------
with(ds, tapply(cesd, female, mean))
## 0 1
## 31.6 36.9
###運用mosaic語法達到同樣結果
library(mosaic)
mean(cesd ~ female, data=ds)
## 0 1
## 31.6 36.9