EX03
options(continue=" ") #設置換行符號
options(digits=3) #設置小數點顯示位數
options(width=72) #設置輸出資訊的寬度
ds = read.csv("http://www.amherst.edu/~nhorton/r2/datasets/help.csv") #從網址讀取資料
library(dplyr) # 載入package 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
# 選擇變項
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(newds) #檢查變項名稱
## [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]) # 檢視前10項資料結構
## '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]) # 檢視前10項資料摘要
## 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(newds, n=3) # 檢視前3筆資料
## 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(newds) = "HELP baseline dataset" #在物件newds上添加文字註腳
comment(newds) # 看看物件newds的文字註腳
## [1] "HELP baseline dataset"
save(ds, file="savedfile") # 存檔
write.csv(ds, file="ds.csv") #將ds資料輸出成逗號分隔的 CSV 格式檔案
library(foreign) # 載入package foreign
write.foreign(newds, "file.dat", "file.sas", package="SAS") #轉換成SAS可讀格式
with(newds, cesd[1:10]) # newds物件中，變項cesd的1到10筆資料
## [1] 49 30 39 15 39 6 52 32 50 46
with(newds, head(cesd, 10)) #檢視newds物件中，變項cesd的前10筆資料
## [1] 49 30 39 15 39 6 52 32 50 46
with(newds, cesd[cesd > 56]) # newds物件中，變項cesd中數值>56的資料
## [1] 57 58 57 60 58 58 57
library(dplyr) # 載入package dplyr
filter(newds, cesd > 56) %>% select(id, cesd)# 先選擇newds中cesd大於56的觀察值，再選擇id和cesd兩欄資料檢視，結果只有7筆
## 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由小到大排序後，第1~4筆的數值
## [1] 1 3 3 4
with(newds, which.min(cesd)) # 查詢cesd中最小值在第幾列
## [1] 199
library(mosaic) # 載入package mosaic
## Loading required package: lattice
## Loading required package: ggformula
## Loading required package: ggplot2
##
## 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
##
## 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.
##
## Attaching package: 'mosaic'
## The following object is masked from 'package:Matrix':
##
## mean
## 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) # 檢查f1g變項的NA值，輸出成tbl
## is.na(f1g)
## TRUE FALSE
## 1 452
favstats(~ f1g, data=newds) # 對f1g變項做一些敘述統計，輸出成tbl
## min Q1 median Q3 max mean sd n missing
## 0 1 2 3 3 1.73 1.1 452 1
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)) # 將反向題重新編碼(f1d, f1h, f1l and f1p)
nmisscesd = apply(is.na(cesditems), 1, sum) # 計算NA數量
ncesditems = cesditems # 備份cesditems
ncesditems[is.na(cesditems)] = 0 # 把ncesditems中的NA指派為0
newcesd = apply(ncesditems, 1, sum) # 計算扣除NA後的cesd
imputemeancesd = 20/(20-nmisscesd)*newcesd # 使用平均值來取代NA
# 列出上述將NA改成其他數值的表格
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
# 把連續資料定義成類別資料(abstinent, moderate & highrisk)
library(dplyr) # 載入package dplyr(mutate出處)
library(memisc) # 載入package memisc(cases出處)
## 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 objects are masked from 'package:dplyr':
##
## collect, recode, rename
## 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)))
# 載入package mosaic，解除package memisc與MASS
library(mosaic); detach(package:memisc); detach(package:MASS)
library(dplyr) # 載入package dplyr(arrange, filter出處)
tmpds = select(newds, i1, i2, female, drinkstat) # 選擇i1, i2, female, drinkstat四個變項
tmpds[365:370,] # 檢視第365到370筆資料
## 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
filter(tmpds, drinkstat=="moderate" & female==1) # 檢視tmpds內中度飲酒的女性
## 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
library(gmodels) # 載入package gmodels(CrossTable出處)
with(tmpds, CrossTable(drinkstat)) # 次數與機率表
##
##
## Cell Contents
## |-------------------------|
## | N |
## | N / Table Total |
## |-------------------------|
##
##
## Total Observations in Table: 453
##
##
## | abstinent | moderate | highrisk |
## |-----------|-----------|-----------|
## | 68 | 28 | 357 |
## | 0.150 | 0.062 | 0.788 |
## |-----------|-----------|-----------|
##
##
##
##
with(tmpds, CrossTable(drinkstat, female,
prop.t=FALSE, prop.c=FALSE, prop.chisq=FALSE)) # 列為飲酒、欄為性別，根據性別標明百分比(預設prop.r ?)
##
##
## 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 |
## -------------|-----------|-----------|-----------|
##
##
# 根據女性(0, 1)變項創一個性別("Male","Female")變項
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
library(dplyr) # 載入package dplyr(arrange, filter出處)
newds = arrange(ds, cesd, i1) # 依序使用cesd和id排序ds資料框
newds[1:5, c("cesd", "i1", "id")] # 展示1到5筆
## cesd i1 id
## 1 1 3 233
## 2 3 1 139
## 3 3 13 418
## 4 4 4 251
## 5 4 9 95
females = filter(ds, female==1) # 選出ds中的女性
with(females, mean(cesd)) # 計算女性平均cesd
## [1] 36.9
mean(ds$cesd[ds$female==1]) # 結果同上
## [1] 36.9
with(ds, tapply(cesd, female, mean)) # 計算男女cesd的平均值
## 0 1
## 31.6 36.9
library(mosaic) # mosaic版本的平均值
mean(cesd ~ female, data=ds) # 用~來界定根據什麼變項算平均值
## 0 1
## 31.6 36.9