표에 대한 거의 모든 것

class: center, middle, inverse, title-slide

# 표에 대한 거의 모든 것
### Tidyverse Korea, 이광춘, 2020-10-30

---

## .left[🛠 &nbsp; &nbsp; 발표 목차]

<br>
.alert[
  .large[
- &nbsp; 범주형 자료
- &nbsp; 표 자료구조
- &nbsp; 시각화
- &nbsp; 모형
- &nbsp; 표 작성
  ]
]

---
class: inverse middle center

.pull-left[
.animate__animated.animate__bounceInDown[
![:scale 50%](fig/forcats.png)
]
]
.pull-right[
<br>
<br>
# 범주형 자료 🔍
<hr>
### 자료구조
### 요인(Factor)
### forcats
]

<div>
<style type="text/css">.xaringan-extra-logo {
width: 110px;
height: 128px;
z-index: 0;
background-image: url(fig/Tidyverse_Korea_logo_transparent.png);
background-size: contain;
background-repeat: no-repeat;
position: absolute;
top:0.5em;right:0.5em;
}
</style>
<script>(function () {
  let tries = 0
  function addLogo () {
    if (typeof slideshow === 'undefined') {
      tries += 1
      if (tries < 10) {
        setTimeout(addLogo, 100)
      }
    } else {
      document.querySelectorAll('.remark-slide-content:not(.title-slide):not(.inverse):not(.hide_logo)')
        .forEach(function (slide) {
          const logo = document.createElement('a')
          logo.classList = 'xaringan-extra-logo'
          logo.href = 'https://tidyverse-korea.github.io/seoul-R/'
          slide.appendChild(logo)
        })
    }
  }
  document.addEventListener('DOMContentLoaded', addLogo)
})()</script>
</div>

---
class: middle

.left-column[
.center[![:scale 50%](fig/forcats.png)]
### - 자료구조
]

.right-column[
### Stevens, Stanley Smith. “On the theory of scales of measurement.” (1946)

.center[
![:scale 100%](fig/data-structure-factor.png)
]

.footnote[reference: https://statkclee.github.io/data-science/ds-data-structure.html]

]

---
class: middle

.left-column[
.center[![:scale 50%](fig/forcats.png)]
### - 자료구조
]

.right-column[
### R 자료구조

.center[
![:scale 100%](fig/data-structure-R.png)
]

.footnote[reference: https://statkclee.github.io/data-science/ds-data-structure.html]

]

---
class: middle

.left-column[
.center[![:scale 50%](fig/forcats.png)]
### - 자료구조
### - Factor
]

.right-column[
### 요인(Factor)

```r
library(tidyverse)
x1 <- c("Dec", "Apr", "Jan", "Mar")
sort(x1)
```

```
#> [1] "Apr" "Dec" "Jan" "Mar"
```

```r
month_levels <- c(
  "Jan", "Feb", "Mar", "Apr", "May", "Jun", 
  "Jul", "Aug", "Sep", "Oct", "Nov", "Dec")

y1 <- factor(x1, levels = month_levels)
y1
```

```
#> [1] Dec Apr Jan Mar
#> Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
```

.footnote[reference: https://statkclee.github.io/data-science/ds-factor-cdata.html]

]

---
class: middle

.left-column[
.center[![:scale 50%](fig/forcats.png)]
### - 자료구조
### - Factor
### - forcats
]

.right-column[
### `forcats`

- 요인 수준(factor level)에 대한 라벨(label) 바꿈 &rarr; `forcats::fct_recode`, `dplyr::recode`
- 요인 수준 순서 바꾸기 &rarr; `fct_relevel()`
- 요인 범주수준을 줄이기 &rarr; `if_else()`
- 파생 요인 변수 생성시킴 &rarr; `case_when()`

.footnote[reference: https://statkclee.github.io/data-science/ds-factor-cdata.html]

]

---
class: inverse middle center

.pull-left[
.animate__animated.animate__bounceInDown[
![:scale 50%](fig/forcats.png)
]
]
.pull-right[
<br>
<br>
# 표 자료구조 🔍
<hr>
## 큰 그림
### Case-by-Case
### Frequency
### Table
### 변환
]

---
class: middle

.left-column[
.center[![:scale 50%](fig/forcats.png)]
### 큰 그림

]

.right-column[
### 큰 그림
.center[
![:scale 60%](fig/category-data-structure.png)
]

.footnote[reference: https://cran.r-project.org/web/packages/DescTools/vignettes/TablesInR.pdf]

]

---
class: middle

.left-column[
.center[![:scale 50%](fig/forcats.png)]
#### Case-by-Case

]

.right-column[
### Case-by-Case

```r
library(DescTools)

Untable(UCBAdmissions) %>% head
```

```
#>      Admit Gender Dept
#> 1 Admitted   Male    A
#> 2 Admitted   Male    A
#> 3 Admitted   Male    A
#> 4 Admitted   Male    A
#> 5 Admitted   Male    A
#> 6 Admitted   Male    A
```

.footnote[reference: https://cran.r-project.org/web/packages/DescTools/vignettes/TablesInR.pdf]

]

---
class: middle

.left-column[
.center[![:scale 50%](fig/forcats.png)]
#### Case-by-Case
### Frequency

]

.right-column[
### 빈도수 (Frequency)

```r
data.frame(UCBAdmissions) %>% head
```

```
#>      Admit Gender Dept Freq
#> 1 Admitted   Male    A  512
#> 2 Rejected   Male    A  313
#> 3 Admitted Female    A   89
#> 4 Rejected Female    A   19
#> 5 Admitted   Male    B  353
#> 6 Rejected   Male    B  207
```

.footnote[reference: https://cran.r-project.org/web/packages/DescTools/vignettes/TablesInR.pdf]

]

---
class: middle

.left-column[
.center[![:scale 50%](fig/forcats.png)]
#### Case-by-Case
### Frequency
### Table
]

.right-column[
### 표(Table)

```r
UCBAdmissions[,,Dept=c("A", "B")]
```

```
#> , , Dept = A
#> 
#>           Gender
#> Admit      Male Female
#>   Admitted  512     89
#>   Rejected  313     19
#> 
#> , , Dept = B
#> 
#>           Gender
#> Admit      Male Female
#>   Admitted  353     17
#>   Rejected  207      8
```

.footnote[reference: https://cran.r-project.org/web/packages/DescTools/vignettes/TablesInR.pdf]
]

---
class: middle

.left-column[
.center[![:scale 50%](fig/forcats.png)]
#### Case-by-Case
### Frequency
### Table
### 변환
]

.right-column[
### 변환
.center[
![:scale 80%](fig/table-conversion.png)
]

.footnote[reference: https://cran.r-project.org/web/packages/DescTools/vignettes/TablesInR.pdf]
]

---
class: inverse middle center

.pull-left[
.animate__animated.animate__bounceInDown[
![:scale 50%](fig/ggplot-logo.png)
]
]
.pull-right[
<br>
<br>
# 시각화 📊
<hr>
## 큰 그림
## 깔끔한 데이터
## ggplot
## ggmosaic
]

---
class: middle

.left-column[
.center[![:scale 50%](fig/ggplot-logo.png)]
### 큰 그림
]

.right-column[
### 큰 그림
.center[
![:scale 100%](fig/categorical-data-viz.png)
]

.footnote[reference: https://statkclee.github.io/data-science/ds-factor-dplyr-mosaic.html]
]

---
class: middle

.left-column[
.center[![:scale 50%](fig/ggplot-logo.png)]
### 큰 그림
]

.right-column[
### 큰 그림
.center[
![:scale 100%](fig/categorical-data-viz.png)
]

.footnote[reference: https://statkclee.github.io/data-science/ds-factor-dplyr-mosaic.html]
]

---
class: middle

.left-column[
.center[ ![:scale 50%](fig/ggplot-logo.png) ]
### 큰 그림
### Tidy 데이터
]

.right-column[
### 깔끔한 데이터

```r
data("HairEyeColor")
hair_df <- as_tibble(HairEyeColor) %>% 
  janitor::clean_names()

hair_df %>% sample_n(3)
```

```
#> [38;5;246m# A tibble: 3 x 4[39m
#>   hair  eye   sex        n
#>   [3m[38;5;246m<chr>[39m[23m [3m[38;5;246m<chr>[39m[23m [3m[38;5;246m<chr>[39m[23m  [3m[38;5;246m<dbl>[39m[23m
#> [38;5;250m1[39m Red   Hazel Male       7
#> [38;5;250m2[39m Black Green Female     2
#> [38;5;250m3[39m Black Hazel Male      10
```

.footnote[reference: https://statkclee.github.io/data-science/ds-factor-dplyr-mosaic.html]
]

---
class: middle

.left-column[
.center[ ![:scale 50%](fig/ggplot-logo.png) ]
### 큰 그림
### Tidy 데이터
### ggplot
]

.right-column[
### 깔끔한 데이터

.pull-left[

```r
hair_df %>% 
  unite(appearance, hair:sex, sep="_") %>% 
  filter(n > 10) %>% 
  mutate(appearance = fct_reorder(appearance, n)) %>% 
  ggplot(aes(x=appearance, y=n)) +
    geom_col() +
    coord_flip() +
    theme_bw() +
    labs(x="", y="")
```
]
.pull-right[
<img src="figure/unnamed-chunk-1-1.png" width="100%" style="display: block; margin: auto;" />
]

.footnote[reference: https://statkclee.github.io/data-science/ds-factor-dplyr-mosaic.html]
]

---
class: middle

.left-column[
.center[ ![:scale 50%](fig/ggplot-logo.png) ]
### 큰 그림
### Tidy 데이터
### ggplot
### `ggmosaic`
]

.right-column[
### 모자이크 플롯

.pull-left[

```r
library(ggmosaic)
ggplot(data = hair_df) +
  geom_mosaic(aes(weight = n, x= product(hair), conds=product(sex), fill=eye)) +
  theme_minimal()
```
]
.pull-right[
<img src="figure/unnamed-chunk-2-1.png" width="100%" style="display: block; margin: auto;" />
]

.footnote[reference: https://statkclee.github.io/data-science/ds-factor-dplyr-mosaic.html]
]

---
class: inverse middle center

.pull-left[
.animate__animated.animate__bounceInDown[
![:scale 50%](fig/infer_gnome.png)
]
]
.pull-right[
<br>
<br>
# 모형 💻
<hr>
### V2 로켓
### 통계 검정

]

---
class: middle

.left-column[
.center[ ![:scale 100%](fig/infer_gnome.png) ]
### V2 로켓
]

.right-column[
### V2 로켓 🚀

.pull-left[

```r
library(spatstat)
par(mar = rep(0, 4))

hit <- 537
area <- 576

lambda <- hit/area

south_london <- rpoispp(lambda, win = owin(c(0, 24), c(0, 24)))
plot(south_london, main="", cex=0.5)
abline(h = 0:24, v = 0:24, col = "lightgray", lty = 3)
```
]
.pull-right[
<img src="figure/unnamed-chunk-3-1.png" width="100%" style="display: block; margin: auto;" />
]

.footnote[reference: https://statkclee.github.io/statistics/stat-flying-bomb-poisson.html]
]

---
class: middle

.left-column[
.center[ ![:scale 100%](fig/infer_gnome.png) ]
### V2 로켓
### 통계 검정
]

.right-column[
### 통계 검정

```r
library(infer)

gss_cat_df  <- gss_cat %>% filter(year==2014) %>% 
    mutate(marital = fct_lump(marital, 1),
           race = fct_lump(race, 1)) %>% 
    mutate(marital = fct_recode(marital, 
                                Non_Married = "Other"),
           race    = fct_recode(race, 
                                Non_White = "Other"))

## 교차표 -----
gss_cat_df %>% 
    count(marital, race) %>% 
    spread(marital, n)
```

.footnote[reference: https://statkclee.github.io/statistics/stat-categorical-data-chisquared.html]
]

---
class: inverse middle center

.pull-left[
.animate__animated.animate__bounceInDown[
![:scale 50%](fig/gt-logo.svg)
]
]
.pull-right[
<br>
<br>
# 표 작성 📖
<hr>
### gt
### reactable
]

---
class: middle

.left-column[
.center[ ![:scale 50%](fig/gt-logo.svg) ]
### `gt`
]

.right-column[
### `gt`

![](fig/gt-concept.png)

.footnote[reference: https://statkclee.github.io/data-science/ds-table-gt-kable.html]
]

---
class: middle

.left-column[
.center[ ![:scale 50%](fig/reactR-logo.svg) ]
### `gt`
### `reactable`
]

.right-column[
### `reactable`

<div id="htmlwidget-15e90381add3c3bbf493" class="reactable html-widget" style="width:auto;height:auto;"></div>
<script type="application/json" data-for="htmlwidget-15e90381add3c3bbf493">{"x":{"tag":{"name":"Reactable","attribs":{"data":{"country":["United States","Japan","Germany","France","United Kingdom"],"flags":["🇺🇸","🇯🇵","🇩🇪","🇫🇷","🇬🇧"],"gdp":[19391,5487,4188,2876,2857],"area":[9831510,377962,357380,549087,243610],"gdp_per_capita":[59532,43279,50639,42850,43269]},"columns":[{"accessor":"country","name":"country","type":"character","cell":"function(cell) {\n            return '<a href=\"https://wikipedia.org/wiki/' + cell.value + '\">' + cell.value + '<\/a>'\n          }","html":true},{"accessor":"flags","name":"flags","type":"character"},{"accessor":"gdp","name":"gdp","type":"numeric","format":{"cell":{"separators":true},"aggregated":{"separators":true}}},{"accessor":"area","name":"area","type":"numeric","format":{"cell":{"separators":true},"aggregated":{"separators":true}}},{"accessor":"gdp_per_capita","name":"gdp_per_capita","type":"numeric","format":{"cell":{"separators":true},"aggregated":{"separators":true}}}],"filterable":true,"searchable":true,"defaultPageSize":10,"paginationType":"numbers","showPageInfo":true,"minRows":10,"highlight":true,"dataKey":"4a6fbcf72e119d5d01f4e2c81c14ec17","key":"4a6fbcf72e119d5d01f4e2c81c14ec17"},"children":[]},"class":"reactR_markup"},"evals":["tag.attribs.columns.0.cell"],"jsHooks":[]}</script>

.footnote[reference: https://statkclee.github.io/ds-authoring/krila-digital-new-deal.html]
]

---
class: center middle inverse

# 감사합니다.

# 질문?

# 끝

---
class: center middle inverse

.animate__animated.animate__hinge[

# 감사합니다.
# 질문?
# 끝
]