Data mining theory and reality04
Share on
데이터마이닝의 이론과 실제 4주차
01.R설치 및 사용법
#install.packages(“tidyverse”) #install.packages(“tidymodels”) #install.packages(“rstatix”)
library 불러오기
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 1.0.8
## v tidyr 1.2.0 v stringr 1.4.0
## v readr 2.1.2 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(tidymodels)## -- Attaching packages -------------------------------------- tidymodels 0.2.0 --## v broom 0.8.0 v rsample 0.1.1
## v dials 0.1.1 v tune 0.2.0
## v infer 1.0.0 v workflows 0.2.6
## v modeldata 0.1.1 v workflowsets 0.2.1
## v parsnip 0.2.1 v yardstick 0.0.9
## v recipes 0.2.0## -- Conflicts ----------------------------------------- tidymodels_conflicts() --
## x scales::discard() masks purrr::discard()
## x dplyr::filter() masks stats::filter()
## x recipes::fixed() masks stringr::fixed()
## x dplyr::lag() masks stats::lag()
## x yardstick::spec() masks readr::spec()
## x recipes::step() masks stats::step()
## * Dig deeper into tidy modeling with R at https://www.tmwr.orglibrary(rstatix)##
## 다음의 패키지를 부착합니다: 'rstatix'## The following objects are masked from 'package:infer':
##
## chisq_test, prop_test, t_test## The following object is masked from 'package:dials':
##
## get_n## The following object is masked from 'package:stats':
##
## filter데이터 구조
data(iris)str(iris)## 'data.frame': 150 obs. of 5 variables:
## $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...iris## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
## 7 4.6 3.4 1.4 0.3 setosa
## 8 5.0 3.4 1.5 0.2 setosa
## 9 4.4 2.9 1.4 0.2 setosa
## 10 4.9 3.1 1.5 0.1 setosa
## 11 5.4 3.7 1.5 0.2 setosa
## 12 4.8 3.4 1.6 0.2 setosa
## 13 4.8 3.0 1.4 0.1 setosa
## 14 4.3 3.0 1.1 0.1 setosa
## 15 5.8 4.0 1.2 0.2 setosa
## 16 5.7 4.4 1.5 0.4 setosa
## 17 5.4 3.9 1.3 0.4 setosa
## 18 5.1 3.5 1.4 0.3 setosa
## 19 5.7 3.8 1.7 0.3 setosa
## 20 5.1 3.8 1.5 0.3 setosa
## 21 5.4 3.4 1.7 0.2 setosa
## 22 5.1 3.7 1.5 0.4 setosa
## 23 4.6 3.6 1.0 0.2 setosa
## 24 5.1 3.3 1.7 0.5 setosa
## 25 4.8 3.4 1.9 0.2 setosa
## 26 5.0 3.0 1.6 0.2 setosa
## 27 5.0 3.4 1.6 0.4 setosa
## 28 5.2 3.5 1.5 0.2 setosa
## 29 5.2 3.4 1.4 0.2 setosa
## 30 4.7 3.2 1.6 0.2 setosa
## 31 4.8 3.1 1.6 0.2 setosa
## 32 5.4 3.4 1.5 0.4 setosa
## 33 5.2 4.1 1.5 0.1 setosa
## 34 5.5 4.2 1.4 0.2 setosa
## 35 4.9 3.1 1.5 0.2 setosa
## 36 5.0 3.2 1.2 0.2 setosa
## 37 5.5 3.5 1.3 0.2 setosa
## 38 4.9 3.6 1.4 0.1 setosa
## 39 4.4 3.0 1.3 0.2 setosa
## 40 5.1 3.4 1.5 0.2 setosa
## 41 5.0 3.5 1.3 0.3 setosa
## 42 4.5 2.3 1.3 0.3 setosa
## 43 4.4 3.2 1.3 0.2 setosa
## 44 5.0 3.5 1.6 0.6 setosa
## 45 5.1 3.8 1.9 0.4 setosa
## 46 4.8 3.0 1.4 0.3 setosa
## 47 5.1 3.8 1.6 0.2 setosa
## 48 4.6 3.2 1.4 0.2 setosa
## 49 5.3 3.7 1.5 0.2 setosa
## 50 5.0 3.3 1.4 0.2 setosa
## 51 7.0 3.2 4.7 1.4 versicolor
## 52 6.4 3.2 4.5 1.5 versicolor
## 53 6.9 3.1 4.9 1.5 versicolor
## 54 5.5 2.3 4.0 1.3 versicolor
## 55 6.5 2.8 4.6 1.5 versicolor
## 56 5.7 2.8 4.5 1.3 versicolor
## 57 6.3 3.3 4.7 1.6 versicolor
## 58 4.9 2.4 3.3 1.0 versicolor
## 59 6.6 2.9 4.6 1.3 versicolor
## 60 5.2 2.7 3.9 1.4 versicolor
## 61 5.0 2.0 3.5 1.0 versicolor
## 62 5.9 3.0 4.2 1.5 versicolor
## 63 6.0 2.2 4.0 1.0 versicolor
## 64 6.1 2.9 4.7 1.4 versicolor
## 65 5.6 2.9 3.6 1.3 versicolor
## 66 6.7 3.1 4.4 1.4 versicolor
## 67 5.6 3.0 4.5 1.5 versicolor
## 68 5.8 2.7 4.1 1.0 versicolor
## 69 6.2 2.2 4.5 1.5 versicolor
## 70 5.6 2.5 3.9 1.1 versicolor
## 71 5.9 3.2 4.8 1.8 versicolor
## 72 6.1 2.8 4.0 1.3 versicolor
## 73 6.3 2.5 4.9 1.5 versicolor
## 74 6.1 2.8 4.7 1.2 versicolor
## 75 6.4 2.9 4.3 1.3 versicolor
## 76 6.6 3.0 4.4 1.4 versicolor
## 77 6.8 2.8 4.8 1.4 versicolor
## 78 6.7 3.0 5.0 1.7 versicolor
## 79 6.0 2.9 4.5 1.5 versicolor
## 80 5.7 2.6 3.5 1.0 versicolor
## 81 5.5 2.4 3.8 1.1 versicolor
## 82 5.5 2.4 3.7 1.0 versicolor
## 83 5.8 2.7 3.9 1.2 versicolor
## 84 6.0 2.7 5.1 1.6 versicolor
## 85 5.4 3.0 4.5 1.5 versicolor
## 86 6.0 3.4 4.5 1.6 versicolor
## 87 6.7 3.1 4.7 1.5 versicolor
## 88 6.3 2.3 4.4 1.3 versicolor
## 89 5.6 3.0 4.1 1.3 versicolor
## 90 5.5 2.5 4.0 1.3 versicolor
## 91 5.5 2.6 4.4 1.2 versicolor
## 92 6.1 3.0 4.6 1.4 versicolor
## 93 5.8 2.6 4.0 1.2 versicolor
## 94 5.0 2.3 3.3 1.0 versicolor
## 95 5.6 2.7 4.2 1.3 versicolor
## 96 5.7 3.0 4.2 1.2 versicolor
## 97 5.7 2.9 4.2 1.3 versicolor
## 98 6.2 2.9 4.3 1.3 versicolor
## 99 5.1 2.5 3.0 1.1 versicolor
## 100 5.7 2.8 4.1 1.3 versicolor
## 101 6.3 3.3 6.0 2.5 virginica
## 102 5.8 2.7 5.1 1.9 virginica
## 103 7.1 3.0 5.9 2.1 virginica
## 104 6.3 2.9 5.6 1.8 virginica
## 105 6.5 3.0 5.8 2.2 virginica
## 106 7.6 3.0 6.6 2.1 virginica
## 107 4.9 2.5 4.5 1.7 virginica
## 108 7.3 2.9 6.3 1.8 virginica
## 109 6.7 2.5 5.8 1.8 virginica
## 110 7.2 3.6 6.1 2.5 virginica
## 111 6.5 3.2 5.1 2.0 virginica
## 112 6.4 2.7 5.3 1.9 virginica
## 113 6.8 3.0 5.5 2.1 virginica
## 114 5.7 2.5 5.0 2.0 virginica
## 115 5.8 2.8 5.1 2.4 virginica
## 116 6.4 3.2 5.3 2.3 virginica
## 117 6.5 3.0 5.5 1.8 virginica
## 118 7.7 3.8 6.7 2.2 virginica
## 119 7.7 2.6 6.9 2.3 virginica
## 120 6.0 2.2 5.0 1.5 virginica
## 121 6.9 3.2 5.7 2.3 virginica
## 122 5.6 2.8 4.9 2.0 virginica
## 123 7.7 2.8 6.7 2.0 virginica
## 124 6.3 2.7 4.9 1.8 virginica
## 125 6.7 3.3 5.7 2.1 virginica
## 126 7.2 3.2 6.0 1.8 virginica
## 127 6.2 2.8 4.8 1.8 virginica
## 128 6.1 3.0 4.9 1.8 virginica
## 129 6.4 2.8 5.6 2.1 virginica
## 130 7.2 3.0 5.8 1.6 virginica
## 131 7.4 2.8 6.1 1.9 virginica
## 132 7.9 3.8 6.4 2.0 virginica
## 133 6.4 2.8 5.6 2.2 virginica
## 134 6.3 2.8 5.1 1.5 virginica
## 135 6.1 2.6 5.6 1.4 virginica
## 136 7.7 3.0 6.1 2.3 virginica
## 137 6.3 3.4 5.6 2.4 virginica
## 138 6.4 3.1 5.5 1.8 virginica
## 139 6.0 3.0 4.8 1.8 virginica
## 140 6.9 3.1 5.4 2.1 virginica
## 141 6.7 3.1 5.6 2.4 virginica
## 142 6.9 3.1 5.1 2.3 virginica
## 143 5.8 2.7 5.1 1.9 virginica
## 144 6.8 3.2 5.9 2.3 virginica
## 145 6.7 3.3 5.7 2.5 virginica
## 146 6.7 3.0 5.2 2.3 virginica
## 147 6.3 2.5 5.0 1.9 virginica
## 148 6.5 3.0 5.2 2.0 virginica
## 149 6.2 3.4 5.4 2.3 virginica
## 150 5.9 3.0 5.1 1.8 virginicaglimpse(iris)## Rows: 150
## Columns: 5
## $ Sepal.Length <dbl> 5.1, 4.9, 4.7, 4.6, 5.0, 5.4, 4.6, 5.0, 4.4, 4.9, 5.4, 4.~
## $ Sepal.Width <dbl> 3.5, 3.0, 3.2, 3.1, 3.6, 3.9, 3.4, 3.4, 2.9, 3.1, 3.7, 3.~
## $ Petal.Length <dbl> 1.4, 1.4, 1.3, 1.5, 1.4, 1.7, 1.4, 1.5, 1.4, 1.5, 1.5, 1.~
## $ Petal.Width <dbl> 0.2, 0.2, 0.2, 0.2, 0.2, 0.4, 0.3, 0.2, 0.2, 0.1, 0.2, 0.~
## $ Species <fct> setosa, setosa, setosa, setosa, setosa, setosa, setosa, s~dim(iris)## [1] 150 5iris$Species## [1] setosa setosa setosa setosa setosa setosa
## [7] setosa setosa setosa setosa setosa setosa
## [13] setosa setosa setosa setosa setosa setosa
## [19] setosa setosa setosa setosa setosa setosa
## [25] setosa setosa setosa setosa setosa setosa
## [31] setosa setosa setosa setosa setosa setosa
## [37] setosa setosa setosa setosa setosa setosa
## [43] setosa setosa setosa setosa setosa setosa
## [49] setosa setosa versicolor versicolor versicolor versicolor
## [55] versicolor versicolor versicolor versicolor versicolor versicolor
## [61] versicolor versicolor versicolor versicolor versicolor versicolor
## [67] versicolor versicolor versicolor versicolor versicolor versicolor
## [73] versicolor versicolor versicolor versicolor versicolor versicolor
## [79] versicolor versicolor versicolor versicolor versicolor versicolor
## [85] versicolor versicolor versicolor versicolor versicolor versicolor
## [91] versicolor versicolor versicolor versicolor versicolor versicolor
## [97] versicolor versicolor versicolor versicolor virginica virginica
## [103] virginica virginica virginica virginica virginica virginica
## [109] virginica virginica virginica virginica virginica virginica
## [115] virginica virginica virginica virginica virginica virginica
## [121] virginica virginica virginica virginica virginica virginica
## [127] virginica virginica virginica virginica virginica virginica
## [133] virginica virginica virginica virginica virginica virginica
## [139] virginica virginica virginica virginica virginica virginica
## [145] virginica virginica virginica virginica virginica virginica
## Levels: setosa versicolor virginicairis[5:10,1:3]## Sepal.Length Sepal.Width Petal.Length
## 5 5.0 3.6 1.4
## 6 5.4 3.9 1.7
## 7 4.6 3.4 1.4
## 8 5.0 3.4 1.5
## 9 4.4 2.9 1.4
## 10 4.9 3.1 1.5iris <- as_tibble(iris)str(iris)## tibble [150 x 5] (S3: tbl_df/tbl/data.frame)
## $ Sepal.Length: num [1:150] 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num [1:150] 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length: num [1:150] 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num [1:150] 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...head(iris)## # A tibble: 6 x 5
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## <dbl> <dbl> <dbl> <dbl> <fct>
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosapipe %>%
print(iris, n=15,width=Inf)## # A tibble: 150 x 5
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## <dbl> <dbl> <dbl> <dbl> <fct>
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
## 7 4.6 3.4 1.4 0.3 setosa
## 8 5 3.4 1.5 0.2 setosa
## 9 4.4 2.9 1.4 0.2 setosa
## 10 4.9 3.1 1.5 0.1 setosa
## 11 5.4 3.7 1.5 0.2 setosa
## 12 4.8 3.4 1.6 0.2 setosa
## 13 4.8 3 1.4 0.1 setosa
## 14 4.3 3 1.1 0.1 setosa
## 15 5.8 4 1.2 0.2 setosa
## # ... with 135 more rowsiris %>%
print(n=15, width=Inf)## # A tibble: 150 x 5
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## <dbl> <dbl> <dbl> <dbl> <fct>
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
## 7 4.6 3.4 1.4 0.3 setosa
## 8 5 3.4 1.5 0.2 setosa
## 9 4.4 2.9 1.4 0.2 setosa
## 10 4.9 3.1 1.5 0.1 setosa
## 11 5.4 3.7 1.5 0.2 setosa
## 12 4.8 3.4 1.6 0.2 setosa
## 13 4.8 3 1.4 0.1 setosa
## 14 4.3 3 1.1 0.1 setosa
## 15 5.8 4 1.2 0.2 setosa
## # ... with 135 more rowsiris %>%
.$Species## [1] setosa setosa setosa setosa setosa setosa
## [7] setosa setosa setosa setosa setosa setosa
## [13] setosa setosa setosa setosa setosa setosa
## [19] setosa setosa setosa setosa setosa setosa
## [25] setosa setosa setosa setosa setosa setosa
## [31] setosa setosa setosa setosa setosa setosa
## [37] setosa setosa setosa setosa setosa setosa
## [43] setosa setosa setosa setosa setosa setosa
## [49] setosa setosa versicolor versicolor versicolor versicolor
## [55] versicolor versicolor versicolor versicolor versicolor versicolor
## [61] versicolor versicolor versicolor versicolor versicolor versicolor
## [67] versicolor versicolor versicolor versicolor versicolor versicolor
## [73] versicolor versicolor versicolor versicolor versicolor versicolor
## [79] versicolor versicolor versicolor versicolor versicolor versicolor
## [85] versicolor versicolor versicolor versicolor versicolor versicolor
## [91] versicolor versicolor versicolor versicolor versicolor versicolor
## [97] versicolor versicolor versicolor versicolor virginica virginica
## [103] virginica virginica virginica virginica virginica virginica
## [109] virginica virginica virginica virginica virginica virginica
## [115] virginica virginica virginica virginica virginica virginica
## [121] virginica virginica virginica virginica virginica virginica
## [127] virginica virginica virginica virginica virginica virginica
## [133] virginica virginica virginica virginica virginica virginica
## [139] virginica virginica virginica virginica virginica virginica
## [145] virginica virginica virginica virginica virginica virginica
## Levels: setosa versicolor virginicairis_df <- as.data.frame(iris)str(iris_df)## 'data.frame': 150 obs. of 5 variables:
## $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...외부 데이터 불러오기
#기존 df으로 불러오기
ist_df <- read.csv("01.ist_num.csv",
header = TRUE,
na.strings = ".")ist_df$t_group <- factor(ist_df$t_group,
levels = c(1,2),
labels = c("A자동차","B자동차"))str(ist_df)## 'data.frame': 60 obs. of 2 variables:
## $ t_group: Factor w/ 2 levels "A자동차","B자동차": 1 1 1 1 1 1 1 1 1 1 ...
## $ t_time : int 48187 47245 51020 50732 52416 49278 38214 46742 48706 54280 ...테이블 형태로 만들어서 barplot으로 찍기
ist_df$t_group %>%
table() %>%
barplot()
tibble 로 불러오기
ist_tb <- read_csv("01.ist_num.csv",
col_names = TRUE,
na = ".")## Rows: 60 Columns: 2
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## dbl (2): t_group, t_time
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.ist_tb %>%
print(n=50)## # A tibble: 60 x 2
## t_group t_time
## <dbl> <dbl>
## 1 1 48187
## 2 1 47245
## 3 1 51020
## 4 1 50732
## 5 1 52416
## 6 1 49278
## 7 1 38214
## 8 1 46742
## 9 1 48706
## 10 1 54280
## 11 1 50635
## 12 1 51052
## 13 1 51568
## 14 1 51569
## 15 1 48825
## 16 1 49674
## 17 1 55750
## 18 1 46432
## 19 1 46935
## 20 1 44890
## 21 1 46346
## 22 1 42332
## 23 1 43990
## 24 1 50691
## 25 1 45578
## 26 1 48000
## 27 1 50428
## 28 1 49269
## 29 1 46539
## 30 1 52794
## 31 2 48683
## 32 2 56285
## 33 2 52456
## 34 2 51816
## 35 2 49664
## 36 2 51276
## 37 2 45520
## 38 2 50476
## 39 2 48537
## 40 2 53594
## 41 2 52261
## 42 2 51515
## 43 2 48338
## 44 2 46375
## 45 2 50706
## 46 2 58032
## 47 2 59299
## 48 2 51178
## 49 2 49792
## 50 2 56355
## # ... with 10 more rowsist_tb <- ist_tb %>%
mutate(t_group = factor(t_group,
levels = c(1,2),
labels = c("A자동차","B자동차")))tibble 형식 문자로 저장된 파일 불러오기
ist_tb_ch <- read_csv("01.ist_chr.csv",
col_names = TRUE,
locale = locale("ko",encoding ="euc-kr"),
na = ".") %>%
mutate_if(is.character,as.factor)## Rows: 60 Columns: 2
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (1): t_group
## dbl (1): t_time
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.ist_tb_ch## # A tibble: 60 x 2
## t_group t_time
## <fct> <dbl>
## 1 A자동차 48187
## 2 A자동차 47245
## 3 A자동차 51020
## 4 A자동차 50732
## 5 A자동차 52416
## 6 A자동차 49278
## 7 A자동차 38214
## 8 A자동차 46742
## 9 A자동차 48706
## 10 A자동차 54280
## # ... with 50 more rows저장하기
write_csv(ist_tb_ch, "ist_tb_ch.csv")library(tidyverse)
library(tidymodels)
#install.packages("nycflights13")
library(nycflights13)data("flights")str(flights)## tibble [336,776 x 19] (S3: tbl_df/tbl/data.frame)
## $ year : int [1:336776] 2013 2013 2013 2013 2013 2013 2013 2013 2013 2013 ...
## $ month : int [1:336776] 1 1 1 1 1 1 1 1 1 1 ...
## $ day : int [1:336776] 1 1 1 1 1 1 1 1 1 1 ...
## $ dep_time : int [1:336776] 517 533 542 544 554 554 555 557 557 558 ...
## $ sched_dep_time: int [1:336776] 515 529 540 545 600 558 600 600 600 600 ...
## $ dep_delay : num [1:336776] 2 4 2 -1 -6 -4 -5 -3 -3 -2 ...
## $ arr_time : int [1:336776] 830 850 923 1004 812 740 913 709 838 753 ...
## $ sched_arr_time: int [1:336776] 819 830 850 1022 837 728 854 723 846 745 ...
## $ arr_delay : num [1:336776] 11 20 33 -18 -25 12 19 -14 -8 8 ...
## $ carrier : chr [1:336776] "UA" "UA" "AA" "B6" ...
## $ flight : int [1:336776] 1545 1714 1141 725 461 1696 507 5708 79 301 ...
## $ tailnum : chr [1:336776] "N14228" "N24211" "N619AA" "N804JB" ...
## $ origin : chr [1:336776] "EWR" "LGA" "JFK" "JFK" ...
## $ dest : chr [1:336776] "IAH" "IAH" "MIA" "BQN" ...
## $ air_time : num [1:336776] 227 227 160 183 116 150 158 53 140 138 ...
## $ distance : num [1:336776] 1400 1416 1089 1576 762 ...
## $ hour : num [1:336776] 5 5 5 5 6 5 6 6 6 6 ...
## $ minute : num [1:336776] 15 29 40 45 0 58 0 0 0 0 ...
## $ time_hour : POSIXct[1:336776], format: "2013-01-01 05:00:00" "2013-01-01 05:00:00" ...flights## # A tibble: 336,776 x 19
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 1 1 517 515 2 830 819
## 2 2013 1 1 533 529 4 850 830
## 3 2013 1 1 542 540 2 923 850
## 4 2013 1 1 544 545 -1 1004 1022
## 5 2013 1 1 554 600 -6 812 837
## 6 2013 1 1 554 558 -4 740 728
## 7 2013 1 1 555 600 -5 913 854
## 8 2013 1 1 557 600 -3 709 723
## 9 2013 1 1 557 600 -3 838 846
## 10 2013 1 1 558 600 -2 753 745
## # ... with 336,766 more rows, and 11 more variables: arr_delay <dbl>,
## # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>filter(): 행 선택
flights %>%
filter(month == 12, day == 31)## # A tibble: 776 x 19
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 12 31 13 2359 14 439 437
## 2 2013 12 31 18 2359 19 449 444
## 3 2013 12 31 26 2245 101 129 2353
## 4 2013 12 31 459 500 -1 655 651
## 5 2013 12 31 514 515 -1 814 812
## 6 2013 12 31 549 551 -2 925 900
## 7 2013 12 31 550 600 -10 725 745
## 8 2013 12 31 552 600 -8 811 826
## 9 2013 12 31 553 600 -7 741 754
## 10 2013 12 31 554 550 4 1024 1027
## # ... with 766 more rows, and 11 more variables: arr_delay <dbl>,
## # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>flights %>%
filter(month == 11|month == 12) %>% # or => |
print(n=100)## # A tibble: 55,403 x 19
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 11 1 5 2359 6 352 345
## 2 2013 11 1 35 2250 105 123 2356
## 3 2013 11 1 455 500 -5 641 651
## 4 2013 11 1 539 545 -6 856 827
## 5 2013 11 1 542 545 -3 831 855
## 6 2013 11 1 549 600 -11 912 923
## 7 2013 11 1 550 600 -10 705 659
## 8 2013 11 1 554 600 -6 659 701
## 9 2013 11 1 554 600 -6 826 827
## 10 2013 11 1 554 600 -6 749 751
## 11 2013 11 1 555 600 -5 847 854
## 12 2013 11 1 555 600 -5 839 846
## 13 2013 11 1 555 600 -5 929 943
## 14 2013 11 1 556 600 -4 834 851
## 15 2013 11 1 558 600 -2 727 730
## 16 2013 11 1 558 600 -2 650 658
## 17 2013 11 1 558 600 -2 914 905
## 18 2013 11 1 558 600 -2 720 715
## 19 2013 11 1 559 600 -1 756 730
## 20 2013 11 1 600 600 0 709 716
## 21 2013 11 1 600 600 0 725 721
## 22 2013 11 1 601 600 1 853 856
## 23 2013 11 1 601 610 -9 803 813
## 24 2013 11 1 602 600 2 843 815
## 25 2013 11 1 603 600 3 717 711
## 26 2013 11 1 604 610 -6 855 855
## 27 2013 11 1 606 615 -9 746 750
## 28 2013 11 1 606 615 -9 807 817
## 29 2013 11 1 606 610 -4 752 745
## 30 2013 11 1 607 611 -4 857 912
## 31 2013 11 1 608 615 -7 816 821
## 32 2013 11 1 609 615 -6 807 818
## 33 2013 11 1 613 620 -7 810 810
## 34 2013 11 1 615 619 -4 753 819
## 35 2013 11 1 618 625 -7 725 735
## 36 2013 11 1 619 620 -1 723 728
## 37 2013 11 1 620 622 -2 837 827
## 38 2013 11 1 620 620 0 754 740
## 39 2013 11 1 623 630 -7 839 839
## 40 2013 11 1 623 630 -7 806 808
## 41 2013 11 1 623 600 23 806 758
## 42 2013 11 1 623 630 -7 834 914
## 43 2013 11 1 624 630 -6 927 922
## 44 2013 11 1 624 629 -5 926 929
## 45 2013 11 1 625 630 -5 907 850
## 46 2013 11 1 625 630 -5 901 851
## 47 2013 11 1 626 630 -4 806 805
## 48 2013 11 1 626 630 -4 920 919
## 49 2013 11 1 627 630 -3 818 813
## 50 2013 11 1 628 630 -2 905 840
## 51 2013 11 1 628 630 -2 946 919
## 52 2013 11 1 628 630 -2 801 806
## 53 2013 11 1 628 632 -4 938 940
## 54 2013 11 1 628 635 -7 920 929
## 55 2013 11 1 630 630 0 921 918
## 56 2013 11 1 633 635 -2 735 747
## 57 2013 11 1 636 641 -5 812 805
## 58 2013 11 1 636 637 -1 931 923
## 59 2013 11 1 636 645 -9 936 907
## 60 2013 11 1 637 640 -3 918 905
## 61 2013 11 1 638 630 8 948 946
## 62 2013 11 1 639 635 4 830 833
## 63 2013 11 1 640 640 0 838 838
## 64 2013 11 1 640 630 10 837 833
## 65 2013 11 1 643 645 -2 817 821
## 66 2013 11 1 644 650 -6 814 819
## 67 2013 11 1 646 655 -9 837 840
## 68 2013 11 1 646 650 -4 758 759
## 69 2013 11 1 648 648 0 926 913
## 70 2013 11 1 651 640 11 812 807
## 71 2013 11 1 651 600 51 801 717
## 72 2013 11 1 651 652 -1 945 954
## 73 2013 11 1 652 700 -8 842 838
## 74 2013 11 1 652 659 -7 912 859
## 75 2013 11 1 652 700 -8 956 1025
## 76 2013 11 1 653 655 -2 913 914
## 77 2013 11 1 653 700 -7 802 808
## 78 2013 11 1 653 700 -7 803 809
## 79 2013 11 1 653 701 -8 850 831
## 80 2013 11 1 653 700 -7 947 1001
## 81 2013 11 1 654 700 -6 816 833
## 82 2013 11 1 654 700 -6 NA 1015
## 83 2013 11 1 655 659 -4 944 912
## 84 2013 11 1 655 659 -4 910 903
## 85 2013 11 1 655 700 -5 1030 1051
## 86 2013 11 1 655 655 0 1036 1101
## 87 2013 11 1 656 659 -3 936 955
## 88 2013 11 1 656 700 -4 1005 1020
## 89 2013 11 1 657 705 -8 940 953
## 90 2013 11 1 657 655 2 809 810
## 91 2013 11 1 658 700 -2 952 1005
## 92 2013 11 1 658 700 -2 936 942
## 93 2013 11 1 658 700 -2 1329 1015
## 94 2013 11 1 659 705 -6 832 845
## 95 2013 11 1 700 704 -4 1016 1025
## 96 2013 11 1 701 710 -9 841 845
## 97 2013 11 1 701 655 6 954 920
## 98 2013 11 1 703 705 -2 1018 955
## 99 2013 11 1 705 710 -5 911 911
## 100 2013 11 1 706 700 6 1011 1008
## # ... with 55,303 more rows, and 11 more variables: arr_delay <dbl>,
## # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>select(): 열
flights %>%
select(year, month,day)## # A tibble: 336,776 x 3
## year month day
## <int> <int> <int>
## 1 2013 1 1
## 2 2013 1 1
## 3 2013 1 1
## 4 2013 1 1
## 5 2013 1 1
## 6 2013 1 1
## 7 2013 1 1
## 8 2013 1 1
## 9 2013 1 1
## 10 2013 1 1
## # ... with 336,766 more rows연속 컬럼은 :표시
flights %>%
select(year:day)## # A tibble: 336,776 x 3
## year month day
## <int> <int> <int>
## 1 2013 1 1
## 2 2013 1 1
## 3 2013 1 1
## 4 2013 1 1
## 5 2013 1 1
## 6 2013 1 1
## 7 2013 1 1
## 8 2013 1 1
## 9 2013 1 1
## 10 2013 1 1
## # ... with 336,766 more rowsyear:day 뺀 나머지 칼럼 가져오기
flights %>%
select(-(year:day))## # A tibble: 336,776 x 16
## dep_time sched_dep_time dep_delay arr_time sched_arr_time arr_delay carrier
## <int> <int> <dbl> <int> <int> <dbl> <chr>
## 1 517 515 2 830 819 11 UA
## 2 533 529 4 850 830 20 UA
## 3 542 540 2 923 850 33 AA
## 4 544 545 -1 1004 1022 -18 B6
## 5 554 600 -6 812 837 -25 DL
## 6 554 558 -4 740 728 12 UA
## 7 555 600 -5 913 854 19 B6
## 8 557 600 -3 709 723 -14 EV
## 9 557 600 -3 838 846 -8 B6
## 10 558 600 -2 753 745 8 AA
## # ... with 336,766 more rows, and 9 more variables: flight <int>,
## # tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## # hour <dbl>, minute <dbl>, time_hour <dttm>flights %>%
select(time_hour, air_time, everything())## # A tibble: 336,776 x 19
## time_hour air_time year month day dep_time sched_dep_time
## <dttm> <dbl> <int> <int> <int> <int> <int>
## 1 2013-01-01 05:00:00 227 2013 1 1 517 515
## 2 2013-01-01 05:00:00 227 2013 1 1 533 529
## 3 2013-01-01 05:00:00 160 2013 1 1 542 540
## 4 2013-01-01 05:00:00 183 2013 1 1 544 545
## 5 2013-01-01 06:00:00 116 2013 1 1 554 600
## 6 2013-01-01 05:00:00 150 2013 1 1 554 558
## 7 2013-01-01 06:00:00 158 2013 1 1 555 600
## 8 2013-01-01 06:00:00 53 2013 1 1 557 600
## 9 2013-01-01 06:00:00 140 2013 1 1 557 600
## 10 2013-01-01 06:00:00 138 2013 1 1 558 600
## # ... with 336,766 more rows, and 12 more variables: dep_delay <dbl>,
## # arr_time <int>, sched_arr_time <int>, arr_delay <dbl>, carrier <chr>,
## # flight <int>, tailnum <chr>, origin <chr>, dest <chr>, distance <dbl>,
## # hour <dbl>, minute <dbl>arrange()
flights %>%
arrange(month, desc(day))## # A tibble: 336,776 x 19
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 1 31 1 2100 181 124 2225
## 2 2013 1 31 4 2359 5 455 444
## 3 2013 1 31 7 2359 8 453 437
## 4 2013 1 31 12 2250 82 132 7
## 5 2013 1 31 26 2154 152 328 50
## 6 2013 1 31 34 2159 155 135 2315
## 7 2013 1 31 37 2249 108 132 2357
## 8 2013 1 31 54 2250 124 152 2359
## 9 2013 1 31 453 500 -7 651 648
## 10 2013 1 31 522 525 -3 820 820
## # ... with 336,766 more rows, and 11 more variables: arr_delay <dbl>,
## # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>desc 가장 큰수부터 출력됨
flights %>%
arrange(desc(dep_delay))## # A tibble: 336,776 x 19
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 1 9 641 900 1301 1242 1530
## 2 2013 6 15 1432 1935 1137 1607 2120
## 3 2013 1 10 1121 1635 1126 1239 1810
## 4 2013 9 20 1139 1845 1014 1457 2210
## 5 2013 7 22 845 1600 1005 1044 1815
## 6 2013 4 10 1100 1900 960 1342 2211
## 7 2013 3 17 2321 810 911 135 1020
## 8 2013 6 27 959 1900 899 1236 2226
## 9 2013 7 22 2257 759 898 121 1026
## 10 2013 12 5 756 1700 896 1058 2020
## # ... with 336,766 more rows, and 11 more variables: arr_delay <dbl>,
## # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>mutate(): 새로운 열 추가(기존+새로운 변수) -> dplyr 패키지
flights %>%
select(year:day, dep_delay, arr_delay, distance, air_time) %>%
mutate(gain = dep_delay - arr_delay,
hours = air_time/ 60,
gain_per_hours = gain / hours)## # A tibble: 336,776 x 10
## year month day dep_delay arr_delay distance air_time gain hours
## <int> <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2013 1 1 2 11 1400 227 -9 3.78
## 2 2013 1 1 4 20 1416 227 -16 3.78
## 3 2013 1 1 2 33 1089 160 -31 2.67
## 4 2013 1 1 -1 -18 1576 183 17 3.05
## 5 2013 1 1 -6 -25 762 116 19 1.93
## 6 2013 1 1 -4 12 719 150 -16 2.5
## 7 2013 1 1 -5 19 1065 158 -24 2.63
## 8 2013 1 1 -3 -14 229 53 11 0.883
## 9 2013 1 1 -3 -8 944 140 5 2.33
## 10 2013 1 1 -2 8 733 138 -10 2.3
## # ... with 336,766 more rows, and 1 more variable: gain_per_hours <dbl>transmute(): 새로운 열 추가(새로운 변수만)
flights %>%
select(year:day, dep_delay, arr_delay, distance, air_time) %>%
transmute(gain = dep_delay - arr_delay,
hours = air_time/ 60,
gain_per_hours = gain / hours)## # A tibble: 336,776 x 3
## gain hours gain_per_hours
## <dbl> <dbl> <dbl>
## 1 -9 3.78 -2.38
## 2 -16 3.78 -4.23
## 3 -31 2.67 -11.6
## 4 17 3.05 5.57
## 5 19 1.93 9.83
## 6 -16 2.5 -6.4
## 7 -24 2.63 -9.11
## 8 11 0.883 12.5
## 9 5 2.33 2.14
## 10 -10 2.3 -4.35
## # ... with 336,766 more rowssummarise()
flights %>%
summarise(delay_mean = mean(dep_delay, na.rm=TRUE)) # NAN 처리 ## # A tibble: 1 x 1
## delay_mean
## <dbl>
## 1 12.6str(flights)## tibble [336,776 x 19] (S3: tbl_df/tbl/data.frame)
## $ year : int [1:336776] 2013 2013 2013 2013 2013 2013 2013 2013 2013 2013 ...
## $ month : int [1:336776] 1 1 1 1 1 1 1 1 1 1 ...
## $ day : int [1:336776] 1 1 1 1 1 1 1 1 1 1 ...
## $ dep_time : int [1:336776] 517 533 542 544 554 554 555 557 557 558 ...
## $ sched_dep_time: int [1:336776] 515 529 540 545 600 558 600 600 600 600 ...
## $ dep_delay : num [1:336776] 2 4 2 -1 -6 -4 -5 -3 -3 -2 ...
## $ arr_time : int [1:336776] 830 850 923 1004 812 740 913 709 838 753 ...
## $ sched_arr_time: int [1:336776] 819 830 850 1022 837 728 854 723 846 745 ...
## $ arr_delay : num [1:336776] 11 20 33 -18 -25 12 19 -14 -8 8 ...
## $ carrier : chr [1:336776] "UA" "UA" "AA" "B6" ...
## $ flight : int [1:336776] 1545 1714 1141 725 461 1696 507 5708 79 301 ...
## $ tailnum : chr [1:336776] "N14228" "N24211" "N619AA" "N804JB" ...
## $ origin : chr [1:336776] "EWR" "LGA" "JFK" "JFK" ...
## $ dest : chr [1:336776] "IAH" "IAH" "MIA" "BQN" ...
## $ air_time : num [1:336776] 227 227 160 183 116 150 158 53 140 138 ...
## $ distance : num [1:336776] 1400 1416 1089 1576 762 ...
## $ hour : num [1:336776] 5 5 5 5 6 5 6 6 6 6 ...
## $ minute : num [1:336776] 15 29 40 45 0 58 0 0 0 0 ...
## $ time_hour : POSIXct[1:336776], format: "2013-01-01 05:00:00" "2013-01-01 05:00:00" ...flights_new <- flights %>%
group_by(dest) %>%
summarise(count = n(),
dist_m = mean(distance, na.rm =T),
delay_m = mean(arr_delay , na.rm = T)) %>%
filter(count >20,
dest != "CAE") %>% # ABQ
arrange(desc(delay_m)) %>%
ungroup() # group_by를 통해 발생할 수 있는 error 방지flights_new## # A tibble: 96 x 4
## dest count dist_m delay_m
## <chr> <int> <dbl> <dbl>
## 1 TUL 315 1215 33.7
## 2 OKC 346 1325 30.6
## 3 JAC 25 1876. 28.1
## 4 TYS 631 639. 24.1
## 5 MSN 572 804. 20.2
## 6 RIC 2454 281. 20.1
## 7 CAK 864 397 19.7
## 8 DSM 569 1021. 19.0
## 9 GRR 765 606. 18.2
## 10 BHM 297 866. 16.9
## # ... with 86 more rowsShare on
Copy URL
Kakao
Facebook
Twitter
LinkedIn
Leave a comment