Week3/26 HW
CKC
2018年3月28日
HW2
# 讀進package中的檔案，檢視形態
pacman::p_load(Ecdat)
pacman::p_load(dplyr)
str(Caschool)## 'data.frame': 420 obs. of 17 variables:
## $ distcod : int 75119 61499 61549 61457 61523 62042 68536 63834 62331 67306 ...
## $ county : Factor w/ 45 levels "Alameda","Butte",..: 1 2 2 2 2 6 29 11 6 25 ...
## $ district: Factor w/ 409 levels "Ackerman Elementary",..: 362 214 367 132 270 53 152 383 263 94 ...
## $ grspan : Factor w/ 2 levels "KK-06","KK-08": 2 2 2 2 2 2 2 2 2 1 ...
## $ enrltot : int 195 240 1550 243 1335 137 195 888 379 2247 ...
## $ teachers: num 10.9 11.1 82.9 14 71.5 ...
## $ calwpct : num 0.51 15.42 55.03 36.48 33.11 ...
## $ mealpct : num 2.04 47.92 76.32 77.05 78.43 ...
## $ computer: int 67 101 169 85 171 25 28 66 35 0 ...
## $ testscr : num 691 661 644 648 641 ...
## $ compstu : num 0.344 0.421 0.109 0.35 0.128 ...
## $ expnstu : num 6385 5099 5502 7102 5236 ...
## $ str : num 17.9 21.5 18.7 17.4 18.7 ...
## $ avginc : num 22.69 9.82 8.98 8.98 9.08 ...
## $ elpct : num 0 4.58 30 0 13.86 ...
## $ readscr : num 692 660 636 652 642 ...
## $ mathscr : num 690 662 651 644 640 ...# 設定種子數量
set.seed(20180327)
# 進行wrangling與繪圖
dta1 <- Caschool %>%
group_by(county) %>%
sample_n(1)
with(dta1, plot(mathscr ~ readscr,
xlab = "average math score",
ylab = "average reading score"))
HW3
## 設定換行、小數點與寬度
options(continue=" ")
options(digits=3)
options(width=72)
# 讀取檔案並從網站存取
ds = read.csv("http://www.amherst.edu/~nhorton/r2/datasets/help.csv")
# 載入package並選擇變項
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)
## 檢視資料名稱與結構
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]) ## '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]) ## 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) ## 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# 加入註腳
comment(newds) = "HELP baseline dataset"
comment(newds) ## [1] "HELP baseline dataset"# 存檔
save(ds, file="savedfile")
## 輸出資料為csv，以及可供不同軟體的格式
write.csv(ds, file="ds.csv")
library(foreign)
write.foreign(newds, "file.dat", "file.sas", package="SAS")
## 檢視各種形式下的dataframe
with(newds, cesd[1:10]) ## [1] 49 30 39 15 39 6 52 32 50 46with(newds, head(cesd, 10))## [1] 49 30 39 15 39 6 52 32 50 46with(newds, cesd[cesd > 56]) ## [1] 57 58 57 60 58 58 57## 整理資料
library(dplyr)
# 選擇newds中cesd大於56的觀察值，並檢視其id和cesd
filter(newds, cesd > 56) %>% select(id, cesd) ## 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 57## 檢視vector
with(newds, sort(cesd)[1:4])## [1] 1 3 3 4with(newds, which.min(cesd))## [1] 199## 檢查資料
library(mosaic)## Warning: package 'mosaic' was built under R version 3.4.3## Loading required package: ggformula## Warning: package 'ggformula' was built under R version 3.4.3##
## New to ggformula? Try the tutorials:
## learnr::run_tutorial("introduction", package = "ggformula")
## learnr::run_tutorial("refining", package = "ggformula")## Loading required package: mosaicData## Warning: package 'mosaicData' was built under R version 3.4.3##
## 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 objects are masked from 'package:dplyr':
##
## count, do, tally## The following object is masked from 'package:memisc':
##
## sample## The following object is masked from 'package:purrr':
##
## cross## The following objects are masked from 'package:car':
##
## deltaMethod, logit## The following object is masked from 'package:lme4':
##
## factorize## The following object is masked from 'package:Matrix':
##
## mean## 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# 取代na
tally(~ is.na(f1g), data=newds)## is.na(f1g)
## TRUE FALSE
## 1 452favstats(~ f1g, data=newds) # 1## min Q1 median Q3 max mean sd n missing
## 0 1 2 3 3 1.73 1.1 452 1## 編碼並計算NA次數
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)
ncesditems = cesditems
ncesditems[is.na(cesditems)] = 0
newcesd = apply(ncesditems, 1, sum)
# 最後將na以平均值取代
imputemeancesd = 20/(20-nmisscesd)*newcesd
## 列出將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## 將連續資料重新定義成類別資料
library(dplyr) # mutate來自dplyr
library(memisc) # cases來自memisc
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)))
library(mosaic); detach(package:memisc); detach(package:MASS)
## 檢視資料
library(dplyr)
tmpds = select(newds, i1, i2, female, drinkstat)
tmpds[365:370,]## 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# 檢視tmpds內飲酒程度為中的女性
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## 製作交叉列聯表
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 |
## |-----------|-----------|-----------|
##
##
##
## 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 |
## -------------|-----------|-----------|-----------|
##
## ## 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 107library(dplyr)
newds = arrange(ds, cesd, i1)
# 使用cesd和id對ds進行排序
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# 對ds中的女性進行計算
females = filter(ds, female==1)
with(females, mean(cesd)) ## [1] 36.9mean(ds$cesd[ds$female==1])## [1] 36.9# 計算男女的cesd平均值
with(ds, tapply(cesd, female, mean))## 0 1
## 31.6 36.9library(mosaic)
mean(cesd ~ female, data=ds)## 0 1
## 31.6 36.9HW4
# 讀取與檢視檔案
pacman::p_load(HSAUR3)
head(dta4 <- backpain)## 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 yes# Summarize and wrangling
dta4 <- backpain %>%
group_by(status, driver, suburban) %>%
summarise(n = n()) %>%
ungroup() %>%
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 221HW5
# 讀取datasets
library(datasets)
# 以rowname為基礎對檔案進行merge
dta5 <- merge(state.x77, USArrests, "row.names")
# 列出所有連續變項的平行相關
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 1.000# ggpairs
ggpairs(dta5[, -1])
## HW6
# 讀取檔案package
library(MASS)## Warning: package 'MASS' was built under R version 3.4.3##
## Attaching package: 'MASS'## The following object is masked from 'package:dplyr':
##
## select## The following object is masked from 'package:Ecdat':
##
## SP500# 對檔案進行merge
dta6 <- merge(rownames_to_column(mammals), rownames_to_column(Animals), all = TRUE)
# duplicated
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] FALSEdim(dta6)## [1] 67 3HW7
# 檔案與表格整理
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))
# 繪圖
library(lattice)
xyplot(readscr ~ ratio | Reading, data = dta7,
type = c("p", "g", "r"), layout = c(3, 1),
xlab = "Student-Teacher Ratio",
ylab = "Reading Score")
## HW8
# 載入package以讀取檔案
pacman::p_load(car)
# 檢視檔案
head(Prestige)## 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 profstr(Prestige)## 'data.frame': 102 obs. of 6 variables:
## $ education: num 13.1 12.3 12.8 11.4 14.6 ...
## $ income : int 12351 25879 9271 8865 8403 11030 8258 14163 11377 11023 ...
## $ women : num 11.16 4.02 15.7 9.11 11.68 ...
## $ prestige : num 68.8 69.1 63.4 56.8 73.5 77.6 72.6 78.1 73.1 68.8 ...
## $ census : int 1113 1130 1171 1175 2111 2113 2133 2141 2143 2153 ...
## $ type : Factor w/ 3 levels "bc","prof","wc": 2 2 2 2 2 2 2 2 2 2 ...HW8.1
# Summarize
dta8.1 <- Prestige %>%
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> 35.0HW8.2
# 整理檔案與表格
dta8.2 <- Prestige %>%
na.omit %>%
group_by(type) %>%
mutate(m = median(prestige),
PrestigeLevel = memisc::cases("High" = prestige >= m,
"Low" = prestige < m))
# 進行繪圖
xyplot(income ~ education |type,
group = PrestigeLevel,
data = dta8.2,
type = c("p", "g", "r"),
layout = c(3, 1),
auto.key = list(columns = 2),
xlab = "Average education of occupational incumbents in 1971",
ylab = "Average income of incumbents in 1971")
從結果可發現，職業類別之聲望高低對於教育程度與收入之間關係存在不同的效果與關係。
HW9
# load data package
pacman::p_load(mlmRev)
# view data structure
head(Hsb82)## 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 0.4564# wrangling
dta9 <- Hsb82 %>%
group_by(school) %>%
summarise(m_math = mean(mAch, na.rm = TRUE),
sd_math = sd(mAch, na.rm = TRUE),
n_math = n()) %>%
mutate(se_math = sd_math / sqrt(n_math),
lower.ci = m_math - qt(1 - (0.05 / 2), n_math - 1) * se_math,
upper.ci = m_math + qt(1 - (0.05 / 2), n_math - 1) * se_math) %>%
dplyr::select(lower.ci, upper.ci)
# view the answer
head(dta9)## # A tibble: 6 x 2
## lower.ci upper.ci
## <dbl> <dbl>
## 1 2.00 7.11
## 2 2.29 6.19
## 3 4.51 7.11
## 4 2.66 5.99
## 5 4.51 7.44
## 6 4.96 9.58