ls()
## character(0)
library(dplyr)
## 
## 다음의 패키지를 부착합니다: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
getwd()
## [1] "C:/data"
setwd("c:/data")
getwd()
## [1] "c:/data"
library(ggplot2)
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
diamonds %>% dim
## [1] 53940    10
diamonds %>% filter(price!=1000&cut=="Ideal") %>% 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 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
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.…
diamonds %>% count(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
diamonds %>% count(color)
## # A tibble: 7 × 2
##   color     n
##   <ord> <int>
## 1 D      6775
## 2 E      9797
## 3 F      9542
## 4 G     11292
## 5 H      8304
## 6 I      5422
## 7 J      2808
diamonds %>% count(clarity)
## # A tibble: 8 × 2
##   clarity     n
##   <ord>   <int>
## 1 I1        741
## 2 SI2      9194
## 3 SI1     13065
## 4 VS2     12258
## 5 VS1      8171
## 6 VVS2     5066
## 7 VVS1     3655
## 8 IF       1790
data("airquality")
View(airquality)
diamonds %>% filter(carat<1|carat>5) %>% 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 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(cut%in%c("Ideal","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 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
library(dplyr)
library(ggplot2)
diamonds %>% select(carat,depth,price) %>% filter(depth==max(depth)|price==min(price))
## # A tibble: 4 × 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
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ lubridate 1.9.2     ✔ tibble    3.2.1
## ✔ purrr     1.0.1     ✔ tidyr     1.3.0
## ✔ readr     2.1.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
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.
diamonds %>% summarize(mean(price))
## # A tibble: 1 × 1
##   `mean(price)`
##           <dbl>
## 1         3933.
diamonds %>% summarize(AvgPrice=mean(price),
                       MedianPrice=median(price),AvgCarat=mean(carat))
## # A tibble: 1 × 3
##   AvgPrice MedianPrice AvgCarat
##      <dbl>       <dbl>    <dbl>
## 1    3933.        2401    0.798
diamonds %>% group_by(cut) %>%
  summarize(n=n()) %>%
  mutate(total=sum(n),pct=n/total*100)
## # A tibble: 5 × 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
#quantile사분위수
quantile(diamonds$price)
##       0%      25%      50%      75%     100% 
##   326.00   950.00  2401.00  5324.25 18823.00
diamonds<-diamonds %>% mutate(price_class=ifelse(price>5324.25,"best",
                                                 ifelse(price>=2401,"good",
                                                        ifelse(price>=950,"normal","bad"))))

table(diamonds$price_class)
## 
##    bad   best   good normal 
##  13483  13485  13496  13476
diamonds %>% group_by(cut) %>% summarize(AvgPrice=mean(price)) %>% arrange(desc(AvgPrice))
## # A tibble: 5 × 2
##   cut       AvgPrice
##   <ord>        <dbl>
## 1 Premium      4584.
## 2 Fair         4359.
## 3 Very Good    3982.
## 4 Good         3929.
## 5 Ideal        3458.
library(hflights)
glimpse(hflights)
## Rows: 227,496
## Columns: 21
## $ Year              <int> 2011, 2011, 2011, 2011, 2011, 2011, 2011, 2011, 2011…
## $ Month             <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ DayofMonth        <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 1…
## $ DayOfWeek         <int> 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2…
## $ DepTime           <int> 1400, 1401, 1352, 1403, 1405, 1359, 1359, 1355, 1443…
## $ ArrTime           <int> 1500, 1501, 1502, 1513, 1507, 1503, 1509, 1454, 1554…
## $ UniqueCarrier     <chr> "AA", "AA", "AA", "AA", "AA", "AA", "AA", "AA", "AA"…
## $ FlightNum         <int> 428, 428, 428, 428, 428, 428, 428, 428, 428, 428, 42…
## $ TailNum           <chr> "N576AA", "N557AA", "N541AA", "N403AA", "N492AA", "N…
## $ ActualElapsedTime <int> 60, 60, 70, 70, 62, 64, 70, 59, 71, 70, 70, 56, 63, …
## $ AirTime           <int> 40, 45, 48, 39, 44, 45, 43, 40, 41, 45, 42, 41, 44, …
## $ ArrDelay          <int> -10, -9, -8, 3, -3, -7, -1, -16, 44, 43, 29, 5, -9, …
## $ DepDelay          <int> 0, 1, -8, 3, 5, -1, -1, -5, 43, 43, 29, 19, -2, -3, …
## $ Origin            <chr> "IAH", "IAH", "IAH", "IAH", "IAH", "IAH", "IAH", "IA…
## $ Dest              <chr> "DFW", "DFW", "DFW", "DFW", "DFW", "DFW", "DFW", "DF…
## $ Distance          <int> 224, 224, 224, 224, 224, 224, 224, 224, 224, 224, 22…
## $ TaxiIn            <int> 7, 6, 5, 9, 9, 6, 12, 7, 8, 6, 8, 4, 6, 5, 6, 12, 8,…
## $ TaxiOut           <int> 13, 9, 17, 22, 9, 13, 15, 12, 22, 19, 20, 11, 13, 15…
## $ Cancelled         <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ CancellationCode  <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", …
## $ Diverted          <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
hflights %>% count(Dest) %>% filter(n==max(n)|n==min(n))
##   Dest    n
## 1  AGS    1
## 2  DAL 9820