ADSP_7

'
install.packages("caret")
library(caret)

nrow(iris)
idx <- createDataPartition(iris$Species,
                           p=0.6, list=FALSE)
train <- iris[idx,]
test <- iris[-idx,]
nrow(train) # 60% 학습용
nrow(test) # 40% 평가용
'

## [1] "\ninstall.packages(\"caret\")\nlibrary(caret)\n\nnrow(iris)\nidx <- createDataPartition(iris$Species,\n                           p=0.6, list=FALSE)\ntrain <- iris[idx,]\ntest <- iris[-idx,]\nnrow(train) # 60% 학습용\nnrow(test) # 40% 평가용\n"

round(0.7811159, 2)

## [1] 0.78

#install.packages("dplyr")
library(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

library(ggplot2)
data("diamonds")
'%>%' # 파이프 연산자

## [1] "%>%"

diamonds %>% head

## # A tibble: 6 × 10
##   carat cut       color clarity depth table price     x     y     z
##   <dbl> <ord>     <ord> <ord>   <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1  0.23 Ideal     E     SI2      61.5    55   326  3.95  3.98  2.43
## 2  0.21 Premium   E     SI1      59.8    61   326  3.89  3.84  2.31
## 3  0.23 Good      E     VS1      56.9    65   327  4.05  4.07  2.31
## 4  0.29 Premium   I     VS2      62.4    58   334  4.2   4.23  2.63
## 5  0.31 Good      J     SI2      63.3    58   335  4.34  4.35  2.75
## 6  0.24 Very Good J     VVS2     62.8    57   336  3.94  3.96  2.48

diamonds1 <- diamonds %>% head %>% 
  rename(c=clarity, p=price)#변수명 수정
head(diamonds1, 3)

## # A tibble: 3 × 10
##   carat cut     color c     depth table     p     x     y     z
##   <dbl> <ord>   <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1  0.23 Ideal   E     SI2    61.5    55   326  3.95  3.98  2.43
## 2  0.21 Premium E     SI1    59.8    61   326  3.89  3.84  2.31
## 3  0.23 Good    E     VS1    56.9    65   327  4.05  4.07  2.31

count(diamonds, cut) # 빈도 분석

## # A tibble: 5 × 2
##   cut           n
##   <ord>     <int>
## 1 Fair       1610
## 2 Good       4906
## 3 Very Good 12082
## 4 Premium   13791
## 5 Ideal     21551

# 필요한 열만 추출
df1 <- diamonds %>% select(carat, price)
head(df1, 3)

## # A tibble: 3 × 2
##   carat price
##   <dbl> <int>
## 1  0.23   326
## 2  0.21   326
## 3  0.23   327

# 비교값이 같은 데이터 추출
diamonds %>% filter(cut == "Good") %>% 
  head(3)

## # A tibble: 3 × 10
##   carat cut   color clarity depth table price     x     y     z
##   <dbl> <ord> <ord> <ord>   <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1  0.23 Good  E     VS1      56.9    65   327  4.05  4.07  2.31
## 2  0.31 Good  J     SI2      63.3    58   335  4.34  4.35  2.75
## 3  0.3  Good  J     SI1      64      55   339  4.25  4.28  2.73

# 파생변수 만들기
diamonds %>% mutate(Ratio=price/carat,
                    Double=Ratio*2) %>% head(3)

## # A tibble: 3 × 12
##   carat cut     color clarity depth table price     x     y     z Ratio Double
##   <dbl> <ord>   <ord> <ord>   <dbl> <dbl> <int> <dbl> <dbl> <dbl> <dbl>  <dbl>
## 1  0.23 Ideal   E     SI2      61.5    55   326  3.95  3.98  2.43 1417.  2835.
## 2  0.21 Premium E     SI1      59.8    61   326  3.89  3.84  2.31 1552.  3105.
## 3  0.23 Good    E     VS1      56.9    65   327  4.05  4.07  2.31 1422.  2843.