Exercise 5
ds <- read.csv("C:\\Users\\shabby\\Desktop\\DataManagement\\week6\\help.csv") #讀取數據
library(dplyr) #加載包
##
## 载入程辑包：'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
newds = dplyr::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) # 選取變項
## ------------------------------------------------------------------------
names(newds) # 查看變項名
## [1] "cesd" "female" "i1" "i2" "id" "treat" "f1a" "f1b"
## [9] "f1c" "f1d" "f1e" "f1f" "f1g" "f1h" "f1i" "f1j"
## [17] "f1k" "f1l" "f1m" "f1n" "f1o" "f1p" "f1q" "f1r"
## [25] "f1s" "f1t"
str(newds[,1:10]) # structure of the first 10 variables顯示前十個變項類型
## '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]) # summary of the first 10 variables顯示前十筆資料摘要
## cesd female i1 i2
## Min. : 1.00 Min. :0.0000 Min. : 0.00 Min. : 0.00
## 1st Qu.:25.00 1st Qu.:0.0000 1st Qu.: 3.00 1st Qu.: 3.00
## Median :34.00 Median :0.0000 Median : 13.00 Median : 15.00
## Mean :32.85 Mean :0.2362 Mean : 17.91 Mean : 22.65
## 3rd Qu.:41.00 3rd Qu.:0.0000 3rd Qu.: 26.00 3rd Qu.: 32.00
## Max. :60.00 Max. :1.0000 Max. :142.00 Max. :184.00
## id treat f1a f1b
## Min. : 1.0 Min. :0.0000 Min. :0.000 Min. :0.000
## 1st Qu.:119.0 1st Qu.:0.0000 1st Qu.:1.000 1st Qu.:0.000
## Median :233.0 Median :0.0000 Median :2.000 Median :1.000
## Mean :233.4 Mean :0.4967 Mean :1.634 Mean :1.391
## 3rd Qu.:348.0 3rd Qu.:1.0000 3rd Qu.:3.000 3rd Qu.:2.000
## Max. :470.0 Max. :1.0000 Max. :3.000 Max. :3.000
## f1c f1d
## Min. :0.000 Min. :0.000
## 1st Qu.:1.000 1st Qu.:0.000
## Median :2.000 Median :1.000
## Mean :1.923 Mean :1.565
## 3rd Qu.:3.000 3rd Qu.:3.000
## Max. :3.000 Max. :3.000
## ------------------------------------------------------------------------
head(newds, n=3)#展示前三筆數據
## cesd female i1 i2 id treat f1a f1b f1c f1d f1e f1f f1g f1h f1i f1j f1k f1l
## 1 49 0 13 26 1 1 3 2 3 0 2 3 3 0 2 3 3 0
## 2 30 0 56 62 2 1 3 2 0 3 3 2 0 0 3 0 3 0
## 3 39 0 0 0 3 0 3 2 3 0 2 2 1 3 2 3 1 0
## f1m f1n f1o f1p f1q f1r f1s f1t
## 1 1 2 2 2 2 3 3 2
## 2 0 3 0 0 0 2 0 0
## 3 1 3 2 0 0 3 2 0
## ------------------------------------------------------------------------
comment(newds) = "HELP baseline dataset"
comment(newds)#寫進comment
## [1] "HELP baseline dataset"
save(ds, file="savedfile")#將變數ds儲存，儲存格式file="savedfile"
## ------------------------------------------------------------------------
write.csv(ds, file="ds.csv") #將數據儲存為csv文件
## ------------------------------------------------------------------------
library(foreign)
write.foreign(newds, "file.dat", "file.sas", package="SAS")
#存成SAS可讀形式
## ------------------------------------------------------------------------
with(newds, cesd[1:10]) #用with列出cesd前10的數值
## [1] 49 30 39 15 39 6 52 32 50 46
with(newds, head(cesd, 10)) #用head列出前10數值
## [1] 49 30 39 15 39 6 52 32 50 46
## ------------------------------------------------------------------------
with(newds, cesd[cesd > 56]) # 在cesd變項中篩選出cesd > 56的值
## [1] 57 58 57 60 58 58 57
## ------------------------------------------------------------------------
library(dplyr)
filter(newds, cesd > 56) %>% select(id, cesd) #同上，篩選出cesd大於56的值
## id cesd
## 1 71 57
## 2 127 58
## 3 200 57
## 4 228 60
## 5 273 58
## 6 351 58
## 7 13 57
## ------------------------------------------------------------------------
with(newds, sort(cesd)[1:4])#將cesd由高到低排序，並展示4個最小值
## [1] 1 3 3 4
with(newds, which.min(cesd))#找到最小值的位置
## [1] 199
## ------------------------------------------------------------------------
library(mosaic)
## 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.
##
## 载入程辑包：'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(~ is.na(f1g), data=newds) # 找出f1g中缺失值
## is.na(f1g)
## TRUE FALSE
## 1 452
favstats(~ f1g, data=newds) #對f1g變項求和
## min Q1 median Q3 max mean sd n missing
## 0 1 2 3 3 1.730088 1.095314 452 1
## ------------------------------------------------------------------------
# reverse code f1d, f1h, f1l and f1p 有點沒看懂，好像是要增加列數，但不知道3-的含義
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))
nmisscesd = apply(is.na(cesditems), 1, sum)#計算每一列在cesditems 的NA總數
ncesditems = cesditems # 將cesditems 放入 ncesditems中
ncesditems[is.na(cesditems)] = 0 #若有缺失值，將其記作0
newcesd = apply(ncesditems, 1, sum) # 計算每一列在ncesditems 的總分
imputemeancesd = 20/(20-nmisscesd)*newcesd #填補分數並說明計算方式
## ------------------------------------------------------------------------
data.frame(newcesd, newds$cesd, nmisscesd, imputemeancesd)[nmisscesd>0,]
## newcesd newds.cesd nmisscesd imputemeancesd
## 4 15 15 1 15.78947
## 17 19 19 1 20.00000
## 87 44 44 1 46.31579
## 101 17 17 1 17.89474
## 154 29 29 1 30.52632
## 177 44 44 1 46.31579
## 229 39 39 1 41.05263
#比較cesd分數，不關注缺失值
## ----createdrink,message=FALSE-------------------------------------------
library(dplyr)
library(memisc)
## 载入需要的程辑包：MASS
##
## 载入程辑包：'MASS'
## The following object is masked from 'package:dplyr':
##
## select
##
## 载入程辑包：'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
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)))
#生成drinkstat變項，並透過條件設定將之分為abstinent、moderate、highrisk三種
## ----echo=FALSE----------------------------------------------------------
library(mosaic)
## ----echo=FALSE----------------------------------------------------------
detach(package:memisc)
detach(package:MASS)
## ------------------------------------------------------------------------
library(dplyr)
tmpds <- dplyr::select(newds, i1, i2, female, drinkstat) #取newds中的四個變項， i1, i2, female, drinkstat
tmpds[365:370,] #展示365到370行數據
## 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
## ------------------------------------------------------------------------
library(dplyr)
filter(tmpds, drinkstat=="moderate" & female==1)
## 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
#從tmpds 中選出drinkstat=moderate ， female=1的列
## ----message=FALSE-------------------------------------------------------
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 |
## |-----------|-----------|-----------|
##
##
##
##
#顯示 drinkstat 三組的數量與比重
## ------------------------------------------------------------------------
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 |
## -------------|-----------|-----------|-----------|
##
##
#顯示 drinkstat 和 female 變項的列連表
## ------------------------------------------------------------------------
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
#生成gender變項，以原有的變項進行轉化
## ------------------------------------------------------------------------
library(dplyr)
newds = arrange(ds, cesd, i1) #將ds 資料重新由小到大排列，第一層依據為 cesd，第二層依據為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
#顯示 newds 中，變項 cesd、i1 和 id 的前五筆資料
## ------------------------------------------------------------------------
library(dplyr)
females = filter(ds, female==1)# 篩選 ds 的資料，篩選條件為 female 值為 1 的資料，存為一個新物件 females
with(females, mean(cesd))
## [1] 36.88785
# an alternative approach
mean(ds$cesd[ds$female==1]) #計算females中cesd的平均數
## [1] 36.88785
## ------------------------------------------------------------------------
with(ds, tapply(cesd, female, mean))
## 0 1
## 31.59827 36.88785
library(mosaic)
mean(cesd ~ female, data=ds)
## 0 1
## 31.59827 36.88785
#兩者都是按性別計算cesd的平均數