In class-Data wrangling
Shang Chi Lee
2021-11-08
In class 1
“Children, Classrooms, Schools”
#目錄設定說明
-html_document: out屬性是html格式 -toc: true 標題可點選 -toc_depth: 2 標題的層級，這裡設定為2層 -toc_float: 在左側顯示浮動的標題點選視窗，這裡沒有設定表示不用視窗 -collapsed: false 是否要展開層級 -smooth_scroll: false 是否要滑動的顯示過程 -theme: readable 選擇需要的theme -highlight: pygments 設定語法的顯示模式（有default, tango, pygments, kate, monochrome, espresso, zenburn, haddock, and textmate 可選）
#Global options
echo = TRUE, 顯示代碼 cache = FALSE 把緩衝的儲存關了 prompt = FALSE, 網路說是R最前面程式的大號顯示關掉，但不管是TRUE 或FALSE，在Rmarkdown中都會有大號> tidy = FALSE, 不用自動排列程式碼, 若自動排列會有段行方式呈現 comment = NA, 在prompt = TRUE時可以在這裡設定呈現方式comment=’’ message = FALSE, 訊息不要在程式欄位顯示，在console出現 warning = FALSE, 程式碼警告訊息不要在程式欄位顯示，在console出現 fig.width = 6, 設定圖形寬度 fig.height = 4 設定圖形高度
#Data
> #在Rmarkdown下載WWGbook
> pacman::p_load(WWGbook)
> data(classroom, package="WWGbook")> #查看classroom是什麼，這裡是data
> ?classroom> #顯示資料類型和結構
> str(classroom)'data.frame': 1190 obs. of 12 variables:
$ sex : int 1 0 1 0 0 1 0 0 1 0 ...
$ minority: int 1 1 1 1 1 1 1 1 1 1 ...
$ mathkind: int 448 460 511 449 425 450 452 443 422 480 ...
$ mathgain: int 32 109 56 83 53 65 51 66 88 -7 ...
$ ses : num 0.46 -0.27 -0.03 -0.38 -0.03 0.76 -0.03 0.2 0.64 0.13 ...
$ yearstea: num 1 1 1 2 2 2 2 2 2 2 ...
$ mathknow: num NA NA NA -0.11 -0.11 -0.11 -0.11 -0.11 -0.11 -0.11 ...
$ housepov: num 0.082 0.082 0.082 0.082 0.082 0.082 0.082 0.082 0.082 0.082 ...
$ mathprep: num 2 2 2 3.25 3.25 3.25 3.25 3.25 3.25 3.25 ...
$ classid : int 160 160 160 217 217 217 217 217 217 217 ...
$ schoolid: int 1 1 1 1 1 1 1 1 1 1 ...
$ childid : int 1 2 3 4 5 6 7 8 9 10 ...#Split data
> #duplicated刪除重複資料，這裡是刪除重複schoolid
> #把"schoolid", "housepov"存到新的資料檔案dta_schl
> dta_schl <- classroom[duplicated(classroom$schoolid)==FALSE,
+ c("schoolid", "housepov")]> #去除重複後把11, 10, 6,7,9欄的資料存出來，並按此順序排序
> dta_cls <- classroom[duplicated(classroom$classid)==FALSE,
+ c(11, 10, 6,7,9)]> #把12, 10, 11, 留下，並針對1～5欄位也留下
> dta_chld <- classroom[, c(12, 10, 11, 1:5)]#呈現ID數量與欄位數
> #sapply和 lapply 功能一樣,給一個 list,它會回傳vector,依指定的功能函數來一項一項做運算。
> #一定要加dim，不然無法跑
> sapply(list(dta_schl, dta_cls, dta_chld), dim) [,1] [,2] [,3]
[1,] 107 312 1190
[2,] 2 5 8#Combine data
> #依據"classid", "schoolid"合併資料
> dta_12 <- merge(x=dta_chld, y=dta_cls, by=c("classid", "schoolid"))> #跟dta_12是一樣程式
> dta_13 <- merge(x=dta_chld, y=dta_cls, by=c("classid", "schoolid"))> #依據"schoolid"相同的合併
> dta_23 <- merge(x=dta_cls, y=dta_schl, by="schoolid")> #by=c()就算只有一個欄位也可用c來combine
> dta_24 <- merge(x=dta_cls, y=dta_schl, by=c("schoolid"))> dta_123 <- merge(x=dta_12, y=dta_schl, by=c("schoolid"))#確認過dta_23, dta_24結果是一樣的，當合併一個變項時，c可用可不用
> sapply(list(dta_12, dta_13, dta_23, dta_24,dta_123), dim) [,1] [,2] [,3] [,4] [,5]
[1,] 1190 1190 312 312 1190
[2,] 11 11 6 6 12In class 2
> str(state.x77) num [1:50, 1:8] 3615 365 2212 2110 21198 ...
- attr(*, "dimnames")=List of 2
..$ : chr [1:50] "Alabama" "Alaska" "Arizona" "Arkansas" ...
..$ : chr [1:8] "Population" "Income" "Illiteracy" "Life Exp" ...> head(state.x77) Population Income Illiteracy Life Exp Murder HS Grad Frost Area
Alabama 3615 3624 2.1 69.05 15.1 41.3 20 50708
Alaska 365 6315 1.5 69.31 11.3 66.7 152 566432
Arizona 2212 4530 1.8 70.55 7.8 58.1 15 113417
Arkansas 2110 3378 1.9 70.66 10.1 39.9 65 51945
California 21198 5114 1.1 71.71 10.3 62.6 20 156361
Colorado 2541 4884 0.7 72.06 6.8 63.9 166 103766> str(USArrests)'data.frame': 50 obs. of 4 variables:
$ Murder : num 13.2 10 8.1 8.8 9 7.9 3.3 5.9 15.4 17.4 ...
$ Assault : int 236 263 294 190 276 204 110 238 335 211 ...
$ UrbanPop: int 58 48 80 50 91 78 77 72 80 60 ...
$ Rape : num 21.2 44.5 31 19.5 40.6 38.7 11.1 15.8 31.9 25.8 ...> head(USArrests) Murder Assault UrbanPop Rape
Alabama 13.2 236 58 21.2
Alaska 10.0 263 48 44.5
Arizona 8.1 294 80 31.0
Arkansas 8.8 190 50 19.5
California 9.0 276 91 40.6
Colorado 7.9 204 78 38.7> dta <- merge(x=state.x77, y=USArrests, by="row.names", all=TRUE)> head(dta) Row.names Population Income Illiteracy Life Exp Murder.x HS Grad Frost
1 Alabama 3615 3624 2.1 69.05 15.1 41.3 20
2 Alaska 365 6315 1.5 69.31 11.3 66.7 152
3 Arizona 2212 4530 1.8 70.55 7.8 58.1 15
4 Arkansas 2110 3378 1.9 70.66 10.1 39.9 65
5 California 21198 5114 1.1 71.71 10.3 62.6 20
6 Colorado 2541 4884 0.7 72.06 6.8 63.9 166
Area Murder.y Assault UrbanPop Rape
1 50708 13.2 236 58 21.2
2 566432 10.0 263 48 44.5
3 113417 8.1 294 80 31.0
4 51945 8.8 190 50 19.5
5 156361 9.0 276 91 40.6
6 103766 7.9 204 78 38.7> View(dta)> library(tidyverse)#此時非矩陣，用kable看資料
> cor(dta[,-1])|> knitr::kable(digits = 2)| Population | Income | Illiteracy | Life Exp | Murder.x | HS Grad | Frost | Area | Murder.y | Assault | UrbanPop | Rape | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Population | 1.00 | 0.21 | 0.11 | -0.07 | 0.34 | -0.10 | -0.33 | 0.02 | 0.32 | 0.32 | 0.51 | 0.31 |
| Income | 0.21 | 1.00 | -0.44 | 0.34 | -0.23 | 0.62 | 0.23 | 0.36 | -0.22 | 0.04 | 0.48 | 0.36 |
| Illiteracy | 0.11 | -0.44 | 1.00 | -0.59 | 0.70 | -0.66 | -0.67 | 0.08 | 0.71 | 0.51 | -0.06 | 0.15 |
| Life Exp | -0.07 | 0.34 | -0.59 | 1.00 | -0.78 | 0.58 | 0.26 | -0.11 | -0.78 | -0.63 | 0.27 | -0.27 |
| Murder.x | 0.34 | -0.23 | 0.70 | -0.78 | 1.00 | -0.49 | -0.54 | 0.23 | 0.93 | 0.74 | 0.02 | 0.58 |
| HS Grad | -0.10 | 0.62 | -0.66 | 0.58 | -0.49 | 1.00 | 0.37 | 0.33 | -0.52 | -0.23 | 0.36 | 0.27 |
| Frost | -0.33 | 0.23 | -0.67 | 0.26 | -0.54 | 0.37 | 1.00 | 0.06 | -0.54 | -0.47 | -0.25 | -0.28 |
| Area | 0.02 | 0.36 | 0.08 | -0.11 | 0.23 | 0.33 | 0.06 | 1.00 | 0.15 | 0.23 | -0.06 | 0.52 |
| Murder.y | 0.32 | -0.22 | 0.71 | -0.78 | 0.93 | -0.52 | -0.54 | 0.15 | 1.00 | 0.80 | 0.07 | 0.56 |
| Assault | 0.32 | 0.04 | 0.51 | -0.63 | 0.74 | -0.23 | -0.47 | 0.23 | 0.80 | 1.00 | 0.26 | 0.67 |
| UrbanPop | 0.51 | 0.48 | -0.06 | 0.27 | 0.02 | 0.36 | -0.25 | -0.06 | 0.07 | 0.26 | 1.00 | 0.41 |
| Rape | 0.31 | 0.36 | 0.15 | -0.27 | 0.58 | 0.27 | -0.28 | 0.52 | 0.56 | 0.67 | 0.41 | 1.00 |
> library(corrplot)
> library(RColorBrewer)#Correlation Matrix for calculating and visualizing easily a correlation matrix 使用 rquery.cormat()計算相關矩陣 相關矩陣的上三角 全相關矩陣 更改相關圖的顏色 繪製熱圖
> source("http://www.sthda.com/upload/rquery_cormat.r")
> require("corrplot")
> rquery.cormat(cor(dta[,-1]))
$r
Income HS Grad Life Exp Frost Population UrbanPop Area Rape
Income 1
HS Grad 0.89 1
Life Exp 0.73 0.88 1
Frost 0.6 0.77 0.74 1
Population -0.11 -0.4 -0.36 -0.66 1
UrbanPop 0.53 0.35 0.34 -0.17 0.57 1
Area 0.24 0.18 -0.18 0.04 -0.18 -0.25 1
Rape -0.061 -0.28 -0.62 -0.63 0.48 0.26 0.52 1
Illiteracy -0.81 -0.93 -0.92 -0.9 0.42 -0.22 0.038 0.52
Assault -0.52 -0.74 -0.91 -0.86 0.55 0.024 0.2 0.82
Murder.x -0.69 -0.86 -0.97 -0.87 0.51 -0.15 0.17 0.72
Murder.y -0.69 -0.87 -0.97 -0.88 0.52 -0.13 0.13 0.71
Illiteracy Assault Murder.x Murder.y
Income
HS Grad
Life Exp
Frost
Population
UrbanPop
Area
Rape
Illiteracy 1
Assault 0.87 1
Murder.x 0.94 0.96 1
Murder.y 0.95 0.97 1 1
$p
Income HS Grad Life Exp Frost Population UrbanPop Area Rape
Income 0
HS Grad 8.4e-05 0
Life Exp 0.0067 0.00015 0
Frost 0.04 0.0035 0.0055 0
Population 0.73 0.2 0.25 0.021 0
UrbanPop 0.078 0.27 0.29 0.6 0.054 0
Area 0.45 0.57 0.57 0.9 0.57 0.43 0
Rape 0.85 0.38 0.032 0.03 0.12 0.42 0.081 0
Illiteracy 0.0014 1e-05 2.8e-05 5.4e-05 0.17 0.49 0.91 0.082
Assault 0.081 0.0057 3.5e-05 0.00036 0.064 0.94 0.53 0.00097
Murder.x 0.014 0.00032 2.5e-07 0.00024 0.089 0.63 0.59 0.0083
Murder.y 0.014 0.00025 3.4e-07 0.00018 0.084 0.7 0.69 0.0092
Illiteracy Assault Murder.x Murder.y
Income
HS Grad
Life Exp
Frost
Population
UrbanPop
Area
Rape
Illiteracy 0
Assault 0.00024 0
Murder.x 3.8e-06 8.1e-07 0
Murder.y 3.4e-06 2.7e-07 1.5e-12 0
$sym
Income HS Grad Life Exp Frost Population UrbanPop Area Rape
Income 1
HS Grad + 1
Life Exp , + 1
Frost . , , 1
Population . . , 1
UrbanPop . . . . 1
Area 1
Rape , , . . 1
Illiteracy + * * + . .
Assault . , * + . +
Murder.x , + B + . ,
Murder.y , + B + . ,
Illiteracy Assault Murder.x Murder.y
Income
HS Grad
Life Exp
Frost
Population
UrbanPop
Area
Rape
Illiteracy 1
Assault + 1
Murder.x * B 1
Murder.y * B 1 1
attr(,"legend")
[1] 0 ' ' 0.3 '.' 0.6 ',' 0.8 '+' 0.9 '*' 0.95 'B' 1In class 3
> library(HSAUR3)> data(backpain, package="HSAUR3")> str(backpain) |> head()'data.frame': 434 obs. of 4 variables:
$ ID : Factor w/ 217 levels "1","2","3","4",..: 1 1 2 2 3 3 4 4 5 5 ...
$ status : Factor w/ 2 levels "case","control": 1 2 1 2 1 2 1 2 1 2 ...
$ driver : Factor w/ 2 levels "no","yes": 2 2 2 2 2 2 1 1 2 2 ...
$ suburban: Factor w/ 2 levels "no","yes": 2 1 2 2 1 2 1 1 1 2 ...NULL> backpain |> head()|>knitr::kable()| ID | status | driver | suburban |
|---|---|---|---|
| 1 | case | yes | yes |
| 1 | control | yes | no |
| 2 | case | yes | yes |
| 2 | control | yes | yes |
| 3 | case | yes | no |
| 3 | control | yes | yes |
> backpain1<- as_tibble(backpain)#說明註解 -spread用來擴展表，把某一列的值（鍵值對）分開拆成多列。 spread(data, key, value, fill = NA, convert = FALSE, drop =TRUE, sep = NULL) key是原來要拆的那一列的名字（變量名），value是拆出來的那些列的值應該填什麼（填原表的哪一列） -Case Control Total 取次數，Total = n()為整合起來的次數 na.rm = TRUE設定遺漏值，不然會有NA出現 - as.data.frame () 為dataframe
> backpain1 %>%
+ dplyr::rename(Group = status,
+ Driver= driver,
+ Suburban = suburban) %>%
+ group_by(Driver, Suburban) %>%
+ tidyr::spread(key="Group", value ="Group") %>%
+ summarize(Case = sum(is.na(case),na.rm = TRUE),
+ Control = sum(is.na(control),na.rm = TRUE),
+ Total = n())%>%
+ as.data.frame () %>%
+ knitr::kable ()| Driver | Suburban | Case | Control | Total |
|---|---|---|---|---|
| no | no | 38 | 17 | 64 |
| no | yes | 5 | 4 | 11 |
| yes | no | 43 | 44 | 107 |
| yes | yes | 37 | 58 | 158 |
In class 4
> library(carData)> data(Vocab, package="carData")> str(Vocab) |> head()'data.frame': 30351 obs. of 4 variables:
$ year : num 1974 1974 1974 1974 1974 ...
$ sex : Factor w/ 2 levels "Female","Male": 2 2 1 1 1 2 2 2 1 1 ...
$ education : num 14 16 10 10 12 16 17 10 12 11 ...
$ vocabulary: num 9 9 9 5 8 8 9 5 3 5 ...
- attr(*, "na.action")= 'omit' Named int [1:32115] 1 2 3 4 5 6 7 8 9 10 ...
..- attr(*, "names")= chr [1:32115] "19720001" "19720002" "19720003" "19720004" ...NULL> head(Vocab) |> knitr::kable ()| year | sex | education | vocabulary | |
|---|---|---|---|---|
| 19740001 | 1974 | Male | 14 | 9 |
| 19740002 | 1974 | Male | 16 | 9 |
| 19740003 | 1974 | Female | 10 | 9 |
| 19740004 | 1974 | Female | 10 | 5 |
| 19740005 | 1974 | Female | 12 | 8 |
| 19740006 | 1974 | Male | 16 | 8 |
> library(lattice)> Vocab %>%
+ mutate(year = as.factor(year)) %>%
+ lattice::xyplot(education ~ vocabulary | year, data=.,
+ groups=sex,
+ type=c("p","g","r"),
+ cex= .3,
+ xlab="Education",
+ ylab="Vocabulary",
+ layout = c(5,6),
+ auto.key=list(columns = 2),
+ par.settings = list(superpose.symbol = list(pch ="*", cex = 1),
+ superpose.line =list(lwd =1.5)))
In class 5
#Supply comments to each code chunk
The data set concerns species and weight of animals caught in plots in a study area in Arizona over time.
Each row holds information for a single animal, and the columns represent:
- record_id: Unique id for the observation
- month: month of observation
- day: day of observation
- year: year of observation
- plot_id: ID of a particular plot
- species_id: 2-letter code
- sex: sex of animal (“M”, “F”)
- hindfoot_length: length of the hindfoot in mm
- weight: weight of the animal in grams
- genus: genus of animal
- species: species of animal
- taxa: e.g. Rodent, Reptile, Bird, Rabbit
- plot_type: type of plot
#用套件來讀取套件，載入tidyverse
> pacman::p_load(tidyverse)#讀網路上的資料
> dta <- read_csv("http://kbroman.org/datacarp/portal_data_joined.csv")#glimpse看一眼資料型態 檢視資料
> glimpse(dta)Rows: 34,786
Columns: 13
$ record_id <dbl> 1, 72, 224, 266, 349, 363, 435, 506, 588, 661, 748, 84~
$ month <dbl> 7, 8, 9, 10, 11, 11, 12, 1, 2, 3, 4, 5, 6, 8, 9, 10, 1~
$ day <dbl> 16, 19, 13, 16, 12, 12, 10, 8, 18, 11, 8, 6, 9, 5, 4, ~
$ year <dbl> 1977, 1977, 1977, 1977, 1977, 1977, 1977, 1978, 1978, ~
$ plot_id <dbl> 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, ~
$ species_id <chr> "NL", "NL", "NL", "NL", "NL", "NL", "NL", "NL", "NL", ~
$ sex <chr> "M", "M", NA, NA, NA, NA, NA, NA, "M", NA, NA, "M", "M~
$ hindfoot_length <dbl> 32, 31, NA, NA, NA, NA, NA, NA, NA, NA, NA, 32, NA, 34~
$ weight <dbl> NA, NA, NA, NA, NA, NA, NA, NA, 218, NA, NA, 204, 200,~
$ genus <chr> "Neotoma", "Neotoma", "Neotoma", "Neotoma", "Neotoma",~
$ species <chr> "albigula", "albigula", "albigula", "albigula", "albig~
$ taxa <chr> "Rodent", "Rodent", "Rodent", "Rodent", "Rodent", "Rod~
$ plot_type <chr> "Control", "Control", "Control", "Control", "Control",~#dim查看各維度長度 顯示資料框列與行的長度
> dim(dta)[1] 34786 13#dplyr語法使用select函數 選dta中的plot_id, species_id, weight三個欄位， %>%然後去 head()看前六筆
> dplyr::select(dta, plot_id, species_id, weight) %>% head()# A tibble: 6 x 3
plot_id species_id weight
<dbl> <chr> <dbl>
1 2 NL NA
2 2 NL NA
3 2 NL NA
4 2 NL NA
5 2 NL NA
6 2 NL NA#dplyr語法使用select函數， 選dta中 不要 -record_id, -species_id這2個變項， %>%然後去 head()看前六筆
> dplyr::select(dta, -record_id, -species_id) %>% head()# A tibble: 6 x 11
month day year plot_id sex hindfoot_length weight genus species taxa
<dbl> <dbl> <dbl> <dbl> <chr> <dbl> <dbl> <chr> <chr> <chr>
1 7 16 1977 2 M 32 NA Neotoma albigula Rodent
2 8 19 1977 2 M 31 NA Neotoma albigula Rodent
3 9 13 1977 2 <NA> NA NA Neotoma albigula Rodent
4 10 16 1977 2 <NA> NA NA Neotoma albigula Rodent
5 11 12 1977 2 <NA> NA NA Neotoma albigula Rodent
6 11 12 1977 2 <NA> NA NA Neotoma albigula Rodent
# ... with 1 more variable: plot_type <chr>#dplyr語法使用filter函數做篩選， 選取year = 1995資料
> dplyr::filter(dta, year == 1995) %>% head()# A tibble: 6 x 13
record_id month day year plot_id species_id sex hindfoot_length weight
<dbl> <dbl> <dbl> <dbl> <dbl> <chr> <chr> <dbl> <dbl>
1 22314 6 7 1995 2 NL M 34 NA
2 22728 9 23 1995 2 NL F 32 165
3 22899 10 28 1995 2 NL F 32 171
4 23032 12 2 1995 2 NL F 33 NA
5 22003 1 11 1995 2 DM M 37 41
6 22042 2 4 1995 2 DM F 36 45
# ... with 4 more variables: genus <chr>, species <chr>, taxa <chr>,
# plot_type <chr>#使用select 選擇函數及filter篩選指定， 看前6筆資料， 這裡要3個變項，weight 要小於等於 5， species_id, sex, weight
> head(dplyr::select(dplyr::filter(dta, weight <= 5), species_id, sex, weight))# A tibble: 6 x 3
species_id sex weight
<chr> <chr> <dbl>
1 PF M 5
2 PF F 5
3 PF F 5
4 PF F 4
5 PF F 5
6 PF F 4#程式簡化使用%>% 代表然後及 接下來的意思
> dta %>%
+ dplyr::filter(weight <= 5) %>%
+ dplyr::select(species_id, sex, weight) %>%
+ head# A tibble: 6 x 3
species_id sex weight
<chr> <chr> <dbl>
1 PF M 5
2 PF F 5
3 PF F 5
4 PF F 4
5 PF F 5
6 PF F 4#mutate建立新變項 生成weight_kg計算weight / 1000;生成weight_lb計算weight_kg * 2.2，只看前六筆
> dta %>%
+ mutate(weight_kg = weight / 1000,
+ weight_lb = weight_kg * 2.2) %>%
+ head()# A tibble: 6 x 15
record_id month day year plot_id species_id sex hindfoot_length weight
<dbl> <dbl> <dbl> <dbl> <dbl> <chr> <chr> <dbl> <dbl>
1 1 7 16 1977 2 NL M 32 NA
2 72 8 19 1977 2 NL M 31 NA
3 224 9 13 1977 2 NL <NA> NA NA
4 266 10 16 1977 2 NL <NA> NA NA
5 349 11 12 1977 2 NL <NA> NA NA
6 363 11 12 1977 2 NL <NA> NA NA
# ... with 6 more variables: genus <chr>, species <chr>, taxa <chr>,
# plot_type <chr>, weight_kg <dbl>, weight_lb <dbl>#常用指令 group_by分組 !is.na(weight)針對weight有值的人 summarize計算mean(weight)放入新變項mean_weight中 desc(mean_weight)排序大到小mean_weight
> dta %>%
+ filter(!is.na(weight)) %>%
+ group_by(sex, species_id) %>%
+ summarize(mean_weight = mean(weight)) %>%
+ arrange(desc(mean_weight)) %>%
+ head()# A tibble: 6 x 3
# Groups: sex [3]
sex species_id mean_weight
<chr> <chr> <dbl>
1 <NA> NL 168.
2 M NL 166.
3 F NL 154.
4 M SS 130
5 <NA> SH 130
6 M DS 122.#看性別分組後的總計
> dta %>%
+ group_by(sex) %>%
+ tally# A tibble: 3 x 2
sex n
<chr> <int>
1 F 15690
2 M 17348
3 <NA> 1748#同上，另一種寫法，計算sex總計
> dta %>%
+ count(sex)# A tibble: 3 x 2
sex n
<chr> <int>
1 F 15690
2 M 17348
3 <NA> 1748#同上，總計計算分組樣本數
> dta %>%
+ group_by(sex) %>%
+ summarize(count = n())# A tibble: 3 x 2
sex count
<chr> <int>
1 F 15690
2 M 17348
3 <NA> 1748#分組計算year有真值的總計樣本數
> dta %>%
+ group_by(sex) %>%
+ summarize(count = sum(!is.na(year)))# A tibble: 3 x 2
sex count
<chr> <int>
1 F 15690
2 M 17348
3 <NA> 1748#制做新檔案 此檔案中filter篩選!is.na(weight)體重為真值的人， group_by(genus, plot_id)依genus, plot_id 2變項作為分組 計算mean(weight)，放入新變項mean_weight中
> dta_gw <- dta %>%
+ filter(!is.na(weight)) %>%
+ group_by(genus, plot_id) %>%
+ summarize(mean_weight = mean(weight))#看一眼新資料dta_gw
> glimpse(dta_gw)Rows: 196
Columns: 3
Groups: genus [10]
$ genus <chr> "Baiomys", "Baiomys", "Baiomys", "Baiomys", "Baiomys", "Ba~
$ plot_id <dbl> 1, 2, 3, 5, 18, 19, 20, 21, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10,~
$ mean_weight <dbl> 7.000000, 6.000000, 8.611111, 7.750000, 9.500000, 9.533333~#spread 把直的轉橫的， 將genus的資料提取出來，內容為mean_weight的值
> dta_w <- dta_gw %>%
+ spread(key = genus, value = mean_weight)#看一眼新轉向後的資料
> glimpse(dta_w)Rows: 24
Columns: 11
$ plot_id <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,~
$ Baiomys <dbl> 7.000000, 6.000000, 8.611111, NA, 7.750000, NA, NA, NA~
$ Chaetodipus <dbl> 22.19939, 25.11014, 24.63636, 23.02381, 17.98276, 24.8~
$ Dipodomys <dbl> 60.23214, 55.68259, 52.04688, 57.52454, 51.11356, 58.6~
$ Neotoma <dbl> 156.2222, 169.1436, 158.2414, 164.1667, 190.0370, 179.~
$ Onychomys <dbl> 27.67550, 26.87302, 26.03241, 28.09375, 27.01695, 25.8~
$ Perognathus <dbl> 9.625000, 6.947368, 7.507812, 7.824427, 8.658537, 7.80~
$ Peromyscus <dbl> 22.22222, 22.26966, 21.37037, 22.60000, 21.23171, 21.8~
$ Reithrodontomys <dbl> 11.375000, 10.680556, 10.516588, 10.263158, 11.154545,~
$ Sigmodon <dbl> NA, 70.85714, 65.61404, 82.00000, 82.66667, 68.77778, ~
$ Spermophilus <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 13~#依未轉向的資料dta_gw整理 將genus, mean_weight 2個欄位中的NA改成0
> dta_gw %>%
+ spread(genus, mean_weight, fill = 0) %>%
+ head()# A tibble: 6 x 11
plot_id Baiomys Chaetodipus Dipodomys Neotoma Onychomys Perognathus Peromyscus
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 7 22.2 60.2 156. 27.7 9.62 22.2
2 2 6 25.1 55.7 169. 26.9 6.95 22.3
3 3 8.61 24.6 52.0 158. 26.0 7.51 21.4
4 4 0 23.0 57.5 164. 28.1 7.82 22.6
5 5 7.75 18.0 51.1 190. 27.0 8.66 21.2
6 6 0 24.9 58.6 180. 25.9 7.81 21.8
# ... with 3 more variables: Reithrodontomys <dbl>, Sigmodon <dbl>,
# Spermophilus <dbl>#gather 把橫的轉成直的,跟spread相反 為long form資料， 依genus變項轉成直的，填入mean_weight值， 不要留plot_id，因轉成直的會自動生程序號，不要序號
> dta_l <- dta_w %>%
+ gather(key = genus, value = mean_weight, -plot_id)#看一眼轉成直的資料
> glimpse(dta_l)Rows: 240
Columns: 3
$ plot_id <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17,~
$ genus <chr> "Baiomys", "Baiomys", "Baiomys", "Baiomys", "Baiomys", "Ba~
$ mean_weight <dbl> 7.000000, 6.000000, 8.611111, NA, 7.750000, NA, NA, NA, NA~#前面一樣，Baiomys:Spermophilus 只要Baiomys:Spermophilus之間的欄位值就好
> dta_w %>%
+ gather(key = genus, value = mean_weight, Baiomys:Spermophilus) %>%
+ head()# A tibble: 6 x 3
plot_id genus mean_weight
<dbl> <chr> <dbl>
1 1 Baiomys 7
2 2 Baiomys 6
3 3 Baiomys 8.61
4 4 Baiomys NA
5 5 Baiomys 7.75
6 6 Baiomys NA #filter 這裡選定weight hindfoot_length sex 3個欄位有真值的資料
> dta_complete <- dta %>%
+ filter(!is.na(weight),
+ !is.na(hindfoot_length),
+ !is.na(sex)) #計算count 針對剛剛選出的3個欄位計算species_id 列出n >= 50的資料
> species_counts <- dta_complete %>%
+ count(species_id) %>%
+ filter(n >= 50)#同上，使用%in%語法 species_counts$species_id計算ID 用法 a %in% table，將有值的輸出在計算欄位中
> dta_complete <- dta_complete %>%
+ filter(species_id %in% species_counts$species_id)