Homework 0326
BHWang
library(dplyr)
library(tidyr)
library(ggplot2)Ex2
dta <- Ecdat::Caschool
head(dta)## distcod county district grspan enrltot teachers
## 1 75119 Alameda Sunol Glen Unified KK-08 195 10.90
## 2 61499 Butte Manzanita Elementary KK-08 240 11.15
## 3 61549 Butte Thermalito Union Elementary KK-08 1550 82.90
## 4 61457 Butte Golden Feather Union Elementary KK-08 243 14.00
## 5 61523 Butte Palermo Union Elementary KK-08 1335 71.50
## 6 62042 Fresno Burrel Union Elementary KK-08 137 6.40
## calwpct mealpct computer testscr compstu expnstu str avginc
## 1 0.5102 2.0408 67 690.80 0.3435898 6384.911 17.88991 22.690001
## 2 15.4167 47.9167 101 661.20 0.4208333 5099.381 21.52466 9.824000
## 3 55.0323 76.3226 169 643.60 0.1090323 5501.955 18.69723 8.978000
## 4 36.4754 77.0492 85 647.70 0.3497942 7101.831 17.35714 8.978000
## 5 33.1086 78.4270 171 640.85 0.1280899 5235.988 18.67133 9.080333
## 6 12.3188 86.9565 25 605.55 0.1824818 5580.147 21.40625 10.415000
## elpct readscr mathscr
## 1 0.000000 691.6 690.0
## 2 4.583333 660.5 661.9
## 3 30.000002 636.3 650.9
## 4 0.000000 651.9 643.5
## 5 13.857677 641.8 639.9
## 6 12.408759 605.7 605.4set.seed(123456)
dta2 <- dta %>%
group_by(county) %>%
sample_n(1)
plot(dta2$mathscr,dta2$readscr,
xlab = "Average math score", ylab = "Average reading score")
EX3
options(continue = " ") #設置換行符號
options(digits = 3) #設置小數位數
options(width = 72) #設置資訊寬度
ds = read.csv("http://www.amherst.edu/~nhorton/r2/datasets/help.csv")
library(dplyr)
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) #選取變項存成新的data.frame
names(newds) #檢視變項名稱## [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"summary(newds[,1:10]) #檢視前10個變項的概要## 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. :3.00head(newds, n=3) #檢視資料前3列## 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 0comment(newds) = "HELP baseline dataset" #為data.frame下註解
comment(newds) #檢視註解## [1] "HELP baseline dataset"save(ds, file="savedfile") #將原始資料存檔
write.csv(ds, file="ds.csv") #將原始資料存為csv檔
library(foreign) #載入foreign套件
write.foreign(newds, "file.dat", "file.sas", package="SAS") #將資料存為sas檔
with(newds, cesd[1:10]) #檢視變項cesd的前10個資料## [1] 49 30 39 15 39 6 52 32 50 46with(newds, head(cesd, 10)) #檢視變項cesd的前10個資料## [1] 49 30 39 15 39 6 52 32 50 46with(newds, cesd[cesd > 56]) #檢視變項cesd中大於56的資料## [1] 57 58 57 60 58 58 57library(dplyr)
filter(newds, cesd > 56) %>%
select(id, cesd) #過濾出cesd大於56的資料，並選取id和cesd兩個變項## Warning: package 'bindrcpp' was built under R version 3.4.3## id cesd
## 1 71 57
## 2 127 58
## 3 200 57
## 4 228 60
## 5 273 58
## 6 351 58
## 7 13 57with(newds, sort(cesd)[1:4]) #將變項cesd的資料由小排到大，並選取前4個資料## [1] 1 3 3 4with(newds, which.min(cesd)) #變項cesd中最小值的位置## [1] 199library(mosaic) #載入mosaic套件
tally(~ is.na(f1g), data=newds) #計算f1g變項中是和不是NA的數量## is.na(f1g)
## TRUE FALSE
## 1 452favstats(~ f1g, data=newds) #呈現f1g變項的各項統計屬性（極值、四分位數、平均值、標準差、總數、無效值數）## min Q1 median Q3 max mean sd n missing
## 0 1 2 3 3 1.73 1.1 452 1cesditems = 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f1d、f1h、f1l、f1p值作反轉
nmisscesd = apply(is.na(cesditems), 1, sum) #按列計算NA數
ncesditems = cesditems #用另一個data.frame儲存
ncesditems[is.na(cesditems)] = 0 #將資料中的NA替換成0
newcesd = apply(ncesditems, 1, sum) #按列計算總和
imputemeancesd = 20/(20-nmisscesd)*newcesd #計算各列總和，若有NA值以該列平均值填補
data.frame(newcesd, newds$cesd, nmisscesd, imputemeancesd)[nmisscesd>0,] #檢視有NA值的列資料## 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 41.1library(dplyr) #載入dplyr套件
library(memisc) #載入memisc套件## Warning: package 'memisc' was built under R version 3.4.4## Loading required package: MASS## Warning: package 'MASS' was built under R version 3.4.3##
## 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.arraynewds = mutate(newds, drinkstat= #加入新變項drinkstat
cases( #設條件
"abstinent" = i1==0, #i1為0
"moderate" = (i1>0 & i1<=1 & i2<=3 & female==1) | #i1大於0且小於等於1，i2小於等於3，為女性
(i1>0 & i1<=2 & i2<=4 & female==0), #i1大於0且小於等於2，i2小於等於4，為男性
"highrisk" = ((i1>1 | i2>3) & female==1) | #i1大於1或i2大於3，為女性
((i1>2 | i2>4) & female==0))) #i1大於2或i2大於4，為男性
library(mosaic) #載入mosaic套件
detach(package:memisc) #取消memisc套件的連結
detach(package:MASS) #取消MASS套件的連結
library(dplyr) #載入dplyr套件
tmpds = select(newds, i1, i2, female, drinkstat) #選取變項
tmpds[365:370,] #選取第365筆到第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 highrisklibrary(dplyr) #載入dplyr套件
filter(tmpds, drinkstat=="moderate" & female==1) #篩選出飲酒狀態適中且為女性的資料## 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 moderatelibrary(gmodels) #載入gmodels套件## Warning: package 'gmodels' was built under R version 3.4.4with(tmpds, CrossTable(drinkstat)) #檢視變項drinkstat的表格##
##
## 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)) #檢視變項drinkstat和變項female的交叉表格##
##
## 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 |
## -------------|-----------|-----------|-----------|
##
## newds = transform(newds,
gender=factor(female, c(0,1), c("Male","Female"))) #新增變項gender紀錄性別
tally(~ female + gender, margin=FALSE, data=newds) #檢視變項female和變項gender的數量關係## gender
## female Male Female
## 0 346 0
## 1 0 107library(dplyr) #載入dplyr套件
newds = arrange(ds, cesd, i1) #按照變項cesd和變項i1的大小排序資料
newds[1:5, c("cesd", "i1", "id")] #檢視前5筆資料，並只選取cesd、i1、id三個變項## cesd i1 id
## 1 1 3 233
## 2 3 1 139
## 3 3 13 418
## 4 4 4 251
## 5 4 9 95library(dplyr) #載入dplyr套件
females = filter(ds, female==1) #篩選出變項female等於1的資料
with(females, mean(cesd)) #計算cesd的平均值## [1] 36.9# an alternative approach
mean(ds$cesd[ds$female==1]) #計算變項female等於1的資料中，cesd的平均值## [1] 36.9with(ds, tapply(cesd, female, mean)) #計算變項female的兩個狀況下，cesd的平均值## 0 1
## 31.6 36.9library(mosaic) #載入mosaic套件
mean(cesd ~ female, data=ds) #計算變項female的兩個狀況下，cesd的平均值## 0 1
## 31.6 36.9EX4
dta4 <- HSAUR3::backpain
head(dta4)## ID status driver suburban
## 1 1 case yes yes
## 2 1 control yes no
## 3 2 case yes yes
## 4 2 control yes yes
## 5 3 case yes no
## 6 3 control yes yesdta4 <- dta4 %>%
group_by(status,driver,suburban) %>%
summarise(n = n()) %>%
ungroup() %>%
tidyr::spread(status,n) %>%
mutate(total = case + control); dta4## # A tibble: 4 x 5
## driver suburban case control total
## <fct> <fct> <int> <int> <int>
## 1 no no 26 47 73
## 2 no yes 6 7 13
## 3 yes no 64 63 127
## 4 yes yes 121 100 221Ex5
library(datasets)
dta5 <- merge(state.x77, USArrests,"row.names")
cor(dta5[,-1])## Population Income Illiteracy Life Exp Murder.x HS Grad
## Population 1.0000 0.2082 0.1076 -0.0681 0.3436 -0.0985
## Income 0.2082 1.0000 -0.4371 0.3403 -0.2301 0.6199
## Illiteracy 0.1076 -0.4371 1.0000 -0.5885 0.7030 -0.6572
## Life Exp -0.0681 0.3403 -0.5885 1.0000 -0.7808 0.5822
## Murder.x 0.3436 -0.2301 0.7030 -0.7808 1.0000 -0.4880
## HS Grad -0.0985 0.6199 -0.6572 0.5822 -0.4880 1.0000
## Frost -0.3322 0.2263 -0.6719 0.2621 -0.5389 0.3668
## Area 0.0225 0.3633 0.0773 -0.1073 0.2284 0.3335
## Murder.y 0.3202 -0.2152 0.7068 -0.7785 0.9337 -0.5216
## Assault 0.3170 0.0409 0.5110 -0.6267 0.7398 -0.2303
## UrbanPop 0.5126 0.4805 -0.0622 0.2715 0.0164 0.3587
## Rape 0.3052 0.3574 0.1546 -0.2696 0.5800 0.2707
## Frost Area Murder.y Assault UrbanPop Rape
## Population -0.3322 0.0225 0.3202 0.3170 0.5126 0.305
## Income 0.2263 0.3633 -0.2152 0.0409 0.4805 0.357
## Illiteracy -0.6719 0.0773 0.7068 0.5110 -0.0622 0.155
## Life Exp 0.2621 -0.1073 -0.7785 -0.6267 0.2715 -0.270
## Murder.x -0.5389 0.2284 0.9337 0.7398 0.0164 0.580
## HS Grad 0.3668 0.3335 -0.5216 -0.2303 0.3587 0.271
## Frost 1.0000 0.0592 -0.5414 -0.4682 -0.2462 -0.279
## Area 0.0592 1.0000 0.1481 0.2312 -0.0615 0.525
## Murder.y -0.5414 0.1481 1.0000 0.8019 0.0696 0.564
## Assault -0.4682 0.2312 0.8019 1.0000 0.2589 0.665
## UrbanPop -0.2462 -0.0615 0.0696 0.2589 1.0000 0.411
## Rape -0.2792 0.5250 0.5636 0.6652 0.4113 1.000GGally::ggpairs(dta5[,-1])
Ex6
library(MASS)
library(tibble)
dta6 <- merge(rownames_to_column(mammals), rownames_to_column(Animals), all = TRUE)
duplicated(dta6)## [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [12] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [23] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [34] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [45] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [56] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [67] FALSEEx7
library(Ecdat)
dta7 <- Caschool %>%
mutate(ratio = enrltot/teachers, Reading = cut(readscr, breaks = quantile(readscr, probs = c(0, .33, .67, 1)), label = c("L", "M", "H"), ordered = T))
library(lattice)
xyplot(readscr ~ ratio | Reading, data = dta7,
type = c("p", "g", "r"), layout = c(3, 1),
xlab = "Student-Teacher Ratio",
ylab = "Reading Score")
Ex8-1
dta8<-car::Prestige
head(dta8)## education income women prestige census type
## gov.administrators 13.1 12351 11.16 68.8 1113 prof
## general.managers 12.3 25879 4.02 69.1 1130 prof
## accountants 12.8 9271 15.70 63.4 1171 prof
## purchasing.officers 11.4 8865 9.11 56.8 1175 prof
## chemists 14.6 8403 11.68 73.5 2111 prof
## physicists 15.6 11030 5.13 77.6 2113 profdta8_1 <- dta8 %>%
group_by(type) %>%
summarize(m = median(prestige,na.rm = TRUE));dta8_1## # A tibble: 4 x 2
## type m
## <fct> <dbl>
## 1 bc 35.9
## 2 prof 68.4
## 3 wc 41.5
## 4 <NA> 35.0Ex8-2
dta8_2 <- dta8 %>%
na.omit %>%
group_by(type) %>%
mutate(m = median(prestige),
PrestigeLV = memisc::cases("H" = prestige >= m,"Low" = prestige < m))
#繪圖
xyplot(income ~ education|type,
group = PrestigeLV,
data = dta8_2,
type = c("p","g","r"),
layout = c(3, 1),
auto.key = list(space = "right", row = 2),
xlab = "Average education of occupational incumbents in 1971",
ylab = "Average income of incumbents in 1971")
Ex9
library(mlmRev)## Warning: package 'mlmRev' was built under R version 3.4.4## Loading required package: lme4##
## Attaching package: 'lme4'## The following object is masked from 'package:mosaic':
##
## factorizedta_09 <- Hsb82
head(dta_09)## school minrty sx ses mAch meanses sector cses
## 1 1224 No Female -1.528 5.88 -0.434 Public -1.0936
## 2 1224 No Female -0.588 19.71 -0.434 Public -0.1536
## 3 1224 No Male -0.528 20.35 -0.434 Public -0.0936
## 4 1224 No Male -0.668 8.78 -0.434 Public -0.2336
## 5 1224 No Male -0.158 17.90 -0.434 Public 0.2764
## 6 1224 No Male 0.022 4.58 -0.434 Public 0.4564dta_09 <- Hsb82 %>%
group_by(sector,school) %>%
summarise(m = mean(mAch, na.rm = TRUE),
s = sd(mAch, na.rm = TRUE),
n = n(),
se = s/sqrt(n)) %>%
mutate(lower.ci = m-2*se, upper.ci = m+2*se)
head(dta_09)## # A tibble: 6 x 8
## # Groups: sector [1]
## sector school m s n se lower.ci upper.ci
## <fct> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 Public 8367 4.55 4.43 14 1.18 2.19 6.92
## 2 Public 8854 4.24 5.41 32 0.956 2.33 6.15
## 3 Public 4458 5.81 4.48 48 0.646 4.52 7.10
## 4 Public 5762 4.32 4.99 37 0.821 2.68 5.97
## 5 Public 6990 5.98 5.31 53 0.729 4.52 7.44
## 6 Public 5815 7.27 5.59 25 1.12 5.04 9.51ggplot(dta_09, aes(x = school, y = m)) +
geom_point() +
geom_errorbar(aes(ymax = upper.ci, ymin = lower.ci))+
coord_flip()+
facet_wrap(~sector)+
labs(x = "School",y = "Math Mean Score by School")