ls()
## character(0)
rm(list = ls())
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.7
## v tidyr 1.1.4 v stringr 1.4.0
## v readr 2.1.0 v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(ggplot2)
data("diamonds")
diamonds %>% head %>% dim
## [1] 6 10
summary(diamonds)
## carat cut color clarity depth
## Min. :0.2000 Fair : 1610 D: 6775 SI1 :13065 Min. :43.00
## 1st Qu.:0.4000 Good : 4906 E: 9797 VS2 :12258 1st Qu.:61.00
## Median :0.7000 Very Good:12082 F: 9542 SI2 : 9194 Median :61.80
## Mean :0.7979 Premium :13791 G:11292 VS1 : 8171 Mean :61.75
## 3rd Qu.:1.0400 Ideal :21551 H: 8304 VVS2 : 5066 3rd Qu.:62.50
## Max. :5.0100 I: 5422 VVS1 : 3655 Max. :79.00
## J: 2808 (Other): 2531
## table price x y
## Min. :43.00 Min. : 326 Min. : 0.000 Min. : 0.000
## 1st Qu.:56.00 1st Qu.: 950 1st Qu.: 4.710 1st Qu.: 4.720
## Median :57.00 Median : 2401 Median : 5.700 Median : 5.710
## Mean :57.46 Mean : 3933 Mean : 5.731 Mean : 5.735
## 3rd Qu.:59.00 3rd Qu.: 5324 3rd Qu.: 6.540 3rd Qu.: 6.540
## Max. :95.00 Max. :18823 Max. :10.740 Max. :58.900
##
## z
## Min. : 0.000
## 1st Qu.: 2.910
## Median : 3.530
## Mean : 3.539
## 3rd Qu.: 4.040
## Max. :31.800
##
#변수이름 변경하기
diamonds1<-diamonds %>% rename(c=clarity,p=price)
str(diamonds1)
## tibble [53,940 x 10] (S3: tbl_df/tbl/data.frame)
## $ carat: num [1:53940] 0.23 0.21 0.23 0.29 0.31 0.24 0.24 0.26 0.22 0.23 ...
## $ cut : Ord.factor w/ 5 levels "Fair"<"Good"<..: 5 4 2 4 2 3 3 3 1 3 ...
## $ color: Ord.factor w/ 7 levels "D"<"E"<"F"<"G"<..: 2 2 2 6 7 7 6 5 2 5 ...
## $ c : Ord.factor w/ 8 levels "I1"<"SI2"<"SI1"<..: 2 3 5 4 2 6 7 3 4 5 ...
## $ depth: num [1:53940] 61.5 59.8 56.9 62.4 63.3 62.8 62.3 61.9 65.1 59.4 ...
## $ table: num [1:53940] 55 61 65 58 58 57 57 55 61 61 ...
## $ p : int [1:53940] 326 326 327 334 335 336 336 337 337 338 ...
## $ x : num [1:53940] 3.95 3.89 4.05 4.2 4.34 3.94 3.95 4.07 3.87 4 ...
## $ y : num [1:53940] 3.98 3.84 4.07 4.23 4.35 3.96 3.98 4.11 3.78 4.05 ...
## $ z : num [1:53940] 2.43 2.31 2.31 2.63 2.75 2.48 2.47 2.53 2.49 2.39 ...
head(diamonds1,3)
## # A tibble: 3 x 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
#빈도분석
count(diamonds,cut)
## # A tibble: 5 x 2
## cut n
## <ord> <int>
## 1 Fair 1610
## 2 Good 4906
## 3 Very Good 12082
## 4 Premium 13791
## 5 Ideal 21551
table(diamonds$cut)
##
## Fair Good Very Good Premium Ideal
## 1610 4906 12082 13791 21551
#데이터 열 추출
df1<-diamonds %>% select(carat,price)
head(df1,3)
## # A tibble: 3 x 2
## carat price
## <dbl> <int>
## 1 0.23 326
## 2 0.21 326
## 3 0.23 327
#불필요한 열변수 제거
df2<-diamonds %>% select(-carat,-price)
head(df2,3)
## # A tibble: 3 x 8
## cut color clarity depth table x y z
## <ord> <ord> <ord> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Ideal E SI2 61.5 55 3.95 3.98 2.43
## 2 Premium E SI1 59.8 61 3.89 3.84 2.31
## 3 Good E VS1 56.9 65 4.05 4.07 2.31
#행의 일부 추출하기
diamonds %>% slice(1:5)
## # A tibble: 5 x 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23 Ideal E SI2 61.5 55 326 3.95 3.98 2.43
## 2 0.21 Premium E SI1 59.8 61 326 3.89 3.84 2.31
## 3 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 4 0.29 Premium I VS2 62.4 58 334 4.2 4.23 2.63
## 5 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
diamonds %>% slice(-1)
## # A tibble: 53,939 x 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.21 Premium E SI1 59.8 61 326 3.89 3.84 2.31
## 2 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 3 0.29 Premium I VS2 62.4 58 334 4.2 4.23 2.63
## 4 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
## 5 0.24 Very Good J VVS2 62.8 57 336 3.94 3.96 2.48
## 6 0.24 Very Good I VVS1 62.3 57 336 3.95 3.98 2.47
## 7 0.26 Very Good H SI1 61.9 55 337 4.07 4.11 2.53
## 8 0.22 Fair E VS2 65.1 61 337 3.87 3.78 2.49
## 9 0.23 Very Good H VS1 59.4 61 338 4 4.05 2.39
## 10 0.3 Good J SI1 64 55 339 4.25 4.28 2.73
## # ... with 53,929 more rows
#코딩넘버 신규 부여
#조건으로 행 추출
diamonds %>% filter(cut=="Good") %>% head(3)
## # A tibble: 3 x 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 2 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
## 3 0.3 Good J SI1 64 55 339 4.25 4.28 2.73
max(diamonds$price)
## [1] 18823
diamonds %>% filter(price==max(price))
## # A tibble: 1 x 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 2.29 Premium I VS2 60.8 60 18823 8.5 8.47 5.16
diamonds %>% filter(price==18823)
## # A tibble: 1 x 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 2.29 Premium I VS2 60.8 60 18823 8.5 8.47 5.16
diamonds %>% filter(cut!="Premium") %>% head(3)
## # A tibble: 3 x 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 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 3 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
diamonds %>% filter(price>=1000) %>% head(3)
## # A tibble: 3 x 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.7 Ideal E SI1 62.5 57 2757 5.7 5.72 3.57
## 2 0.86 Fair E SI2 55.1 69 2757 6.45 6.33 3.52
## 3 0.7 Ideal G VS2 61.6 56 2757 5.7 5.67 3.5
diamonds %>% filter(price!=1000) %>% head(3)
## # A tibble: 3 x 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
diamonds %>% filter(price==1000) %>% head(3)
## # A tibble: 3 x 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.38 Very Good E VVS2 61.8 56 1000 4.66 4.68 2.88
## 2 0.39 Very Good F VS1 57.1 61 1000 4.86 4.91 2.79
## 3 0.38 Very Good E VS1 61.5 58 1000 4.64 4.69 2.87
diamonds %>% filter(price<=1000) %>% head(3)
## # A tibble: 3 x 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
diamonds %>% filter(price!=1000&cut=="Ideal") %>% head(3)
## # A tibble: 3 x 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 0.23 Ideal J VS1 62.8 56 340 3.93 3.9 2.46
## 3 0.31 Ideal J SI2 62.2 54 344 4.35 4.37 2.71
diamonds %>% filter(price!=1000&cut=="Ideal"&color=="E") %>% head(3)
## # A tibble: 3 x 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 0.26 Ideal E VVS2 62.9 58 554 4.02 4.06 2.54
## 3 0.7 Ideal E SI1 62.5 57 2757 5.7 5.72 3.57
diamonds %>% filter(carat<2|carat>5) %>% head(3)
## # A tibble: 3 x 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
#여러 열의 값이 여려가능한 값 가운데 하나라도 맞는 행들을 필터링할때 %in%를 사용함
diamonds %>% filter(cut %in%c("Ideal","Good")) %>% head(3)
## # A tibble: 3 x 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 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 3 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
#열을 추출한 후에 조건에 맞는 행을 추출하기
diamonds %>% select(carat,depth,price) %>% filter(depth==max(depth)|price==min(price))
## # A tibble: 4 x 3
## carat depth price
## <dbl> <dbl> <int>
## 1 0.23 61.5 326
## 2 0.21 59.8 326
## 3 0.5 79 2579
## 4 0.5 79 2579
#파생변수 만들기
diamonds %>% mutate(Ratio=price/carat,Double=Ratio*2) %>% head(3)
## # A tibble: 3 x 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.
#집단멸 통계량 구하기
diamonds %>% summarise(mean(price))
## # A tibble: 1 x 1
## `mean(price)`
## <dbl>
## 1 3933.
#summarize는 mean, max, medium 적용가능
diamonds %>% summarise(AvgPrice=mean(price),MedianPrice=median(price),AvgCarat=mean(carat))
## # A tibble: 1 x 3
## AvgPrice MedianPrice AvgCarat
## <dbl> <dbl> <dbl>
## 1 3933. 2401 0.798
diamonds %>% group_by(cut) %>% summarise(AvgPrice=mean(price),SumCarat=sum(carat))
## # A tibble: 5 x 3
## cut AvgPrice SumCarat
## <ord> <dbl> <dbl>
## 1 Fair 4359. 1684.
## 2 Good 3929. 4166.
## 3 Very Good 3982. 9743.
## 4 Premium 4584. 12301.
## 5 Ideal 3458. 15147.
diamonds %>% group_by(cut) %>% summarize(n=n()) %>%mutate(total=sum(n),pct=n/total*100)
## # A tibble: 5 x 4
## cut n total pct
## <ord> <int> <int> <dbl>
## 1 Fair 1610 53940 2.98
## 2 Good 4906 53940 9.10
## 3 Very Good 12082 53940 22.4
## 4 Premium 13791 53940 25.6
## 5 Ideal 21551 53940 40.0
#연속 데이터로 범주별 변수 만들기
quantile(diamonds$price)
## 0% 25% 50% 75% 100%
## 326.00 950.00 2401.00 5324.25 18823.00
diamonds2<-diamonds %>% mutate(price_class=ifelse(price>=5324.25,"best",ifelse(price>=2401,"good",ifelse(price>=950,"normal","bad"))))
table(diamonds2$price_class)
##
## bad best good normal
## 13483 13485 13496 13476
#데이터 정렬하기
diamonds %>% group_by(cut) %>% summarise(AvgPrice=mean(price)) %>% arrange(desc(AvgPrice))
## # A tibble: 5 x 2
## cut AvgPrice
## <ord> <dbl>
## 1 Premium 4584.
## 2 Fair 4359.
## 3 Very Good 3982.
## 4 Good 3929.
## 5 Ideal 3458.
#데이터 결합하기