ADSP_7

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


# data(iris)
# nrow(iris) #행의 수

# idx <- createDataPartition(iris$Species, p=0.6, list=FALSE)

# idx
# train <- iris[idx,]
# test <- iris[-idx,]

# nrow(train)
# nrow(test)

# 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

# install.packages("ggplot2")
library(ggplot2)
data("diamonds")
diamonds %>% head %>% dim

## [1]  6 10

diamonds1 <- diamonds %>%  rename(c=clarity, p=price)
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)

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

glimpse(diamonds)

## Rows: 53,940
## Columns: 10
## $ carat   <dbl> 0.23, 0.21, 0.23, 0.29, 0.31, 0.24, 0.24, 0.26, 0.22, 0.23, 0.…
## $ cut     <ord> Ideal, Premium, Good, Premium, Good, Very Good, Very Good, Ver…
## $ color   <ord> E, E, E, I, J, J, I, H, E, H, J, J, F, J, E, E, I, J, J, J, I,…
## $ clarity <ord> SI2, SI1, VS1, VS2, SI2, VVS2, VVS1, SI1, VS2, VS1, SI1, VS1, …
## $ depth   <dbl> 61.5, 59.8, 56.9, 62.4, 63.3, 62.8, 62.3, 61.9, 65.1, 59.4, 64…
## $ table   <dbl> 55, 61, 65, 58, 58, 57, 57, 55, 61, 61, 55, 56, 61, 54, 62, 58…
## $ price   <int> 326, 326, 327, 334, 335, 336, 336, 337, 337, 338, 339, 340, 34…
## $ x       <dbl> 3.95, 3.89, 4.05, 4.20, 4.34, 3.94, 3.95, 4.07, 3.87, 4.00, 4.…
## $ y       <dbl> 3.98, 3.84, 4.07, 4.23, 4.35, 3.96, 3.98, 4.11, 3.78, 4.05, 4.…
## $ z       <dbl> 2.43, 2.31, 2.31, 2.63, 2.75, 2.48, 2.47, 2.53, 2.49, 2.39, 2.…

# 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

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.

#