فهرست کلی مطالب



- بخش اول: مدیریت داده ها و ارتباط آن با بسته های Tidyverse

- بخش دوم: تبدیل داده ها با dplyr

- بخش سوم: داده های مرتب با tidyr

- بخش چهارم: داده های رابطه ای با dplyr

بخش اول



مدیریت داده ها و ارتباط آن با بسته های Tidyverse

مدیریت داده ها


بسته های Tidyverse

نصب بسته ها 
install.packages("tidyverse")
فراخوانی بسته های اصلی 
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   2.1.1     v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x tidyr::extract()    masks magrittr::extract()
## x dplyr::filter()     masks stats::filter()
## x dplyr::group_rows() masks kableExtra::group_rows()
## x dplyr::lag()        masks stats::lag()
## x purrr::set_names()  masks magrittr::set_names()

زنجیره کاری بسته ها

بسته های بیشتر Tidyverse

مشاهده تمام بسته ها 
tidyverse_packages()
##  [1] "broom"         "cli"           "crayon"        "dbplyr"       
##  [5] "dplyr"         "dtplyr"        "forcats"       "googledrive"  
##  [9] "googlesheets4" "ggplot2"       "haven"         "hms"          
## [13] "httr"          "jsonlite"      "lubridate"     "magrittr"     
## [17] "modelr"        "pillar"        "purrr"         "readr"        
## [21] "readxl"        "reprex"        "rlang"         "rstudioapi"   
## [25] "rvest"         "stringr"       "tibble"        "tidyr"        
## [29] "xml2"          "tidyverse"

ارتباط بسته های Tidyverse و مدیریت داده ها

بسته های Tidyverse با داده های مرتب (Tidy) کار می کنند

مرجع اصلی کار با بسته های Tidyverse

R for Data Science https://r4ds.had.co.nz/

بخش دوم



تبدیل داده ها با dplyr

تبدیل داده ها با dplyr

اغلب باید متغیرها یا خلاصه های جدیدی ایجاد کنید، یا شاید فقط می خواهید نام متغیرها را تغییر دهید یا مشاهدات را مرتب کنید تا کار با داده ها کمی آسان تر شود.

در این بخش قصد داریم بر نحوه استفاده از بسته dplyr، یکی از اعضای اصلی tidyverse تمرکز کنیم. ما ایده های کلیدی را با استفاده از داده های بسته nycflights13 نشان خواهیم داد. این چارچوب داده شامل تمام 336776 پروازی است که در سال 2013 از شهر نیویورک حرکت کردند.

راهنمای داده ها را با flights? یا https://rdrr.io/cran/nycflights13/man/flights.html می توانید دریافت کنید.

library(tidyverse)
library(nycflights13)
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>
print(flights, n = 5, width = Inf)
## # 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
##   arr_delay carrier flight tailnum origin dest  air_time distance  hour minute
##       <dbl> <chr>    <int> <chr>   <chr>  <chr>    <dbl>    <dbl> <dbl>  <dbl>
## 1        11 UA        1545 N14228  EWR    IAH        227     1400     5     15
## 2        20 UA        1714 N24211  LGA    IAH        227     1416     5     29
## 3        33 AA        1141 N619AA  JFK    MIA        160     1089     5     40
## 4       -18 B6         725 N804JB  JFK    BQN        183     1576     5     45
## 5       -25 DL         461 N668DN  LGA    ATL        116      762     6      0
##   time_hour          
##   <dttm>             
## 1 2013-01-01 05:00:00
## 2 2013-01-01 05:00:00
## 3 2013-01-01 05:00:00
## 4 2013-01-01 05:00:00
## 5 2013-01-01 06:00:00
## # ... with 336,771 more rows
glimpse(flights)
## Rows: 336,776
## Columns: 19
## $ year           <int> 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2~
## $ month          <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1~
## $ day            <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1~
## $ dep_time       <int> 517, 533, 542, 544, 554, 554, 555, 557, 557, 558, 558, ~
## $ sched_dep_time <int> 515, 529, 540, 545, 600, 558, 600, 600, 600, 600, 600, ~
## $ dep_delay      <dbl> 2, 4, 2, -1, -6, -4, -5, -3, -3, -2, -2, -2, -2, -2, -1~
## $ arr_time       <int> 830, 850, 923, 1004, 812, 740, 913, 709, 838, 753, 849,~
## $ sched_arr_time <int> 819, 830, 850, 1022, 837, 728, 854, 723, 846, 745, 851,~
## $ arr_delay      <dbl> 11, 20, 33, -18, -25, 12, 19, -14, -8, 8, -2, -3, 7, -1~
## $ carrier        <chr> "UA", "UA", "AA", "B6", "DL", "UA", "B6", "EV", "B6", "~
## $ flight         <int> 1545, 1714, 1141, 725, 461, 1696, 507, 5708, 79, 301, 4~
## $ tailnum        <chr> "N14228", "N24211", "N619AA", "N804JB", "N668DN", "N394~
## $ origin         <chr> "EWR", "LGA", "JFK", "JFK", "LGA", "EWR", "EWR", "LGA",~
## $ dest           <chr> "IAH", "IAH", "MIA", "BQN", "ATL", "ORD", "FLL", "IAD",~
## $ air_time       <dbl> 227, 227, 160, 183, 116, 150, 158, 53, 140, 138, 149, 1~
## $ distance       <dbl> 1400, 1416, 1089, 1576, 762, 719, 1065, 229, 944, 733, ~
## $ hour           <dbl> 5, 5, 5, 5, 6, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 6~
## $ minute         <dbl> 15, 29, 40, 45, 0, 58, 0, 0, 0, 0, 0, 0, 0, 0, 0, 59, 0~
## $ time_hour      <dttm> 2013-01-01 05:00:00, 2013-01-01 05:00:00, 2013-01-01 0~
View(flights)

فیلتر کردن ردیف ها با ()filter

filter(flights, month == 1, day == 1)
## # A tibble: 842 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 832 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(flights, month == 11 | month == 12)
## # 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
## # ... with 55,393 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(flights, !(arr_delay > 120 | dep_delay > 120))
## # A tibble: 316,050 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 316,040 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(flights, arr_delay <= 120, dep_delay <= 120)
## # A tibble: 316,050 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 316,040 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>

دیگر توابع سطری برای انتخاب ردیف ها

distinct(flights, month)
## # A tibble: 12 x 1
##    month
##    <int>
##  1     1
##  2    10
##  3    11
##  4    12
##  5     2
##  6     3
##  7     4
##  8     5
##  9     6
## 10     7
## 11     8
## 12     9
distinct(flights, month, .keep_all = TRUE)
## # A tibble: 12 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    10     1      447            500       -13      614            648
##  3  2013    11     1        5           2359         6      352            345
##  4  2013    12     1       13           2359        14      446            445
##  5  2013     2     1      456            500        -4      652            648
##  6  2013     3     1        4           2159       125      318             56
##  7  2013     4     1      454            500        -6      636            640
##  8  2013     5     1        9           1655       434      308           2020
##  9  2013     6     1        2           2359         3      341            350
## 10  2013     7     1        1           2029       212      236           2359
## 11  2013     8     1       12           2130       162      257             14
## 12  2013     9     1        9           2359        10      343            340
## # ... with 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>
slice(flights, 21:25, 101:105, 1000)
## # A tibble: 11 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      602            610        -8      812            820
##  2  2013     1     1      602            605        -3      821            805
##  3  2013     1     1      606            610        -4      858            910
##  4  2013     1     1      606            610        -4      837            845
##  5  2013     1     1      607            607         0      858            915
##  6  2013     1     1      753            755        -2     1056           1110
##  7  2013     1     1      754            759        -5     1039           1041
##  8  2013     1     1      754            755        -1     1103           1030
##  9  2013     1     1      758            800        -2     1053           1054
## 10  2013     1     1      759            800        -1     1057           1127
## 11  2013     1     2      809            810        -1      950            948
## # ... with 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>
slice_sample(flights, n = 5)
## # A tibble: 5 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     2      622            630        -8      855            918
## 2  2013     4    18     1222           1210        12     1455           1450
## 3  2013     2    23     1620           1630       -10     1950           2015
## 4  2013     1     2     1249           1245         4     1555           1550
## 5  2013    12    23     2120           1940       100     2344           2153
## # ... with 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>
slice_min(flights, dep_delay, n = 5)
## # A tibble: 5 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     7     2040           2123       -43       40           2352
## 2  2013     2     3     2022           2055       -33     2240           2338
## 3  2013    11    10     1408           1440       -32     1549           1559
## 4  2013     1    11     1900           1930       -30     2233           2243
## 5  2013     1    29     1703           1730       -27     1947           1957
## # ... with 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>
slice_head(flights, n = 5)
## # A tibble: 5 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
## # ... with 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>
slice_head(flights, prop = 1 / 1e5)
## # A tibble: 3 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
## # ... with 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>

مرتب کردن ردیف ها با ()arrange

arrange(flights, 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    12     7     2040           2123       -43       40           2352
##  2  2013     2     3     2022           2055       -33     2240           2338
##  3  2013    11    10     1408           1440       -32     1549           1559
##  4  2013     1    11     1900           1930       -30     2233           2243
##  5  2013     1    29     1703           1730       -27     1947           1957
##  6  2013     8     9      729            755       -26     1002            955
##  7  2013    10    23     1907           1932       -25     2143           2143
##  8  2013     3    30     2030           2055       -25     2213           2250
##  9  2013     3     2     1431           1455       -24     1601           1631
## 10  2013     5     5      934            958       -24     1225           1309
## # ... 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>
مرتب کردن نزولی 
arrange(flights, 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>
مقادیر گم شده همیشه آخر هستند. 
df <- tibble(x = c(5, 2, NA))
arrange(df, x)
## # A tibble: 3 x 1
##       x
##   <dbl>
## 1     2
## 2     5
## 3    NA
arrange(df, desc(x))
## # A tibble: 3 x 1
##       x
##   <dbl>
## 1     5
## 2     2
## 3    NA

انتخاب متغیرها با ()select

انتخاب با استفاده از نام ستون ها 
select(flights, 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 rows
انتخاب ستون های متوالی 
select(flights, 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 rows
انتخاب معکوس 
select(flights, -(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>
انتخاب با استفاده از شماره ستون ها 
select(flights, 1:3, 5)
## # A tibble: 336,776 x 4
##     year month   day sched_dep_time
##    <int> <int> <int>          <int>
##  1  2013     1     1            515
##  2  2013     1     1            529
##  3  2013     1     1            540
##  4  2013     1     1            545
##  5  2013     1     1            600
##  6  2013     1     1            558
##  7  2013     1     1            600
##  8  2013     1     1            600
##  9  2013     1     1            600
## 10  2013     1     1            600
## # ... with 336,766 more rows
select(flights, 1:3, last_col())
## # A tibble: 336,776 x 4
##     year month   day time_hour          
##    <int> <int> <int> <dttm>             
##  1  2013     1     1 2013-01-01 05:00:00
##  2  2013     1     1 2013-01-01 05:00:00
##  3  2013     1     1 2013-01-01 05:00:00
##  4  2013     1     1 2013-01-01 05:00:00
##  5  2013     1     1 2013-01-01 06:00:00
##  6  2013     1     1 2013-01-01 05:00:00
##  7  2013     1     1 2013-01-01 06:00:00
##  8  2013     1     1 2013-01-01 06:00:00
##  9  2013     1     1 2013-01-01 06:00:00
## 10  2013     1     1 2013-01-01 06:00:00
## # ... with 336,766 more rows
انتخاب با استفاده از توابع کمکی 
select(flights, starts_with("dep"))
## # A tibble: 336,776 x 2
##    dep_time dep_delay
##       <int>     <dbl>
##  1      517         2
##  2      533         4
##  3      542         2
##  4      544        -1
##  5      554        -6
##  6      554        -4
##  7      555        -5
##  8      557        -3
##  9      557        -3
## 10      558        -2
## # ... with 336,766 more rows
select(flights, ends_with("time"))
## # A tibble: 336,776 x 5
##    dep_time sched_dep_time arr_time sched_arr_time air_time
##       <int>          <int>    <int>          <int>    <dbl>
##  1      517            515      830            819      227
##  2      533            529      850            830      227
##  3      542            540      923            850      160
##  4      544            545     1004           1022      183
##  5      554            600      812            837      116
##  6      554            558      740            728      150
##  7      555            600      913            854      158
##  8      557            600      709            723       53
##  9      557            600      838            846      140
## 10      558            600      753            745      138
## # ... with 336,766 more rows
select(flights, starts_with("dep"), ends_with("time"))
## # A tibble: 336,776 x 6
##    dep_time dep_delay sched_dep_time arr_time sched_arr_time air_time
##       <int>     <dbl>          <int>    <int>          <int>    <dbl>
##  1      517         2            515      830            819      227
##  2      533         4            529      850            830      227
##  3      542         2            540      923            850      160
##  4      544        -1            545     1004           1022      183
##  5      554        -6            600      812            837      116
##  6      554        -4            558      740            728      150
##  7      555        -5            600      913            854      158
##  8      557        -3            600      709            723       53
##  9      557        -3            600      838            846      140
## 10      558        -2            600      753            745      138
## # ... with 336,766 more rows
select(flights, starts_with("dep") & ends_with("time"))
## # A tibble: 336,776 x 1
##    dep_time
##       <int>
##  1      517
##  2      533
##  3      542
##  4      544
##  5      554
##  6      554
##  7      555
##  8      557
##  9      557
## 10      558
## # ... with 336,766 more rows
select(flights, contains("arr"))
## # A tibble: 336,776 x 4
##    arr_time sched_arr_time arr_delay carrier
##       <int>          <int>     <dbl> <chr>  
##  1      830            819        11 UA     
##  2      850            830        20 UA     
##  3      923            850        33 AA     
##  4     1004           1022       -18 B6     
##  5      812            837       -25 DL     
##  6      740            728        12 UA     
##  7      913            854        19 B6     
##  8      709            723       -14 EV     
##  9      838            846        -8 B6     
## 10      753            745         8 AA     
## # ... with 336,766 more rows
انتخاب با استفاده از توابع شرطی 
select(flights, where(is.numeric))
## # A tibble: 336,776 x 14
##     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 6 more variables: arr_delay <dbl>,
## #   flight <int>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>
select(flights, where(is.character))
## # A tibble: 336,776 x 4
##    carrier tailnum origin dest 
##    <chr>   <chr>   <chr>  <chr>
##  1 UA      N14228  EWR    IAH  
##  2 UA      N24211  LGA    IAH  
##  3 AA      N619AA  JFK    MIA  
##  4 B6      N804JB  JFK    BQN  
##  5 DL      N668DN  LGA    ATL  
##  6 UA      N39463  EWR    ORD  
##  7 B6      N516JB  EWR    FLL  
##  8 EV      N829AS  LGA    IAD  
##  9 B6      N593JB  JFK    MCO  
## 10 AA      N3ALAA  LGA    ORD  
## # ... with 336,766 more rows

ترکیب انتخاب متغیرها و فیلتر کردن

flights %>%
  select(year:sched_arr_time) %>%
  filter(month == 1, day == 1)
## # A tibble: 842 x 8
##     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 832 more rows
برای تعییر نام متغیرها می توان از select استفاده کرد. اما این کار با rename ساده تر است. 
rename(flights, tail_num = tailnum)
## # 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>, tail_num <chr>, origin <chr>, dest <chr>,
## #   air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>
rename_with(flights, toupper, starts_with("dep"))
## # 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>
با استفاده از select می توان ترتیب ستون ها را جابجا کرد. اما این کار با تابع relocate ساده تر است. 
select(flights, 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>
relocate(flights, time_hour, air_time)
## # 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>
relocate(flights, time_hour, air_time, .before = day)
## # A tibble: 336,776 x 19
##     year month time_hour           air_time   day dep_time sched_dep_time
##    <int> <int> <dttm>                 <dbl> <int>    <int>          <int>
##  1  2013     1 2013-01-01 05:00:00      227     1      517            515
##  2  2013     1 2013-01-01 05:00:00      227     1      533            529
##  3  2013     1 2013-01-01 05:00:00      160     1      542            540
##  4  2013     1 2013-01-01 05:00:00      183     1      544            545
##  5  2013     1 2013-01-01 06:00:00      116     1      554            600
##  6  2013     1 2013-01-01 05:00:00      150     1      554            558
##  7  2013     1 2013-01-01 06:00:00      158     1      555            600
##  8  2013     1 2013-01-01 06:00:00       53     1      557            600
##  9  2013     1 2013-01-01 06:00:00      140     1      557            600
## 10  2013     1 2013-01-01 06:00:00      138     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>
relocate(flights, time_hour, air_time, .after = day)
## # A tibble: 336,776 x 19
##     year month   day time_hour           air_time dep_time sched_dep_time
##    <int> <int> <int> <dttm>                 <dbl>    <int>          <int>
##  1  2013     1     1 2013-01-01 05:00:00      227      517            515
##  2  2013     1     1 2013-01-01 05:00:00      227      533            529
##  3  2013     1     1 2013-01-01 05:00:00      160      542            540
##  4  2013     1     1 2013-01-01 05:00:00      183      544            545
##  5  2013     1     1 2013-01-01 06:00:00      116      554            600
##  6  2013     1     1 2013-01-01 05:00:00      150      554            558
##  7  2013     1     1 2013-01-01 06:00:00      158      555            600
##  8  2013     1     1 2013-01-01 06:00:00       53      557            600
##  9  2013     1     1 2013-01-01 06:00:00      140      557            600
## 10  2013     1     1 2013-01-01 06:00:00      138      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>

افزودن متغیرهای جدید با ()mutate

Mutate به معنی جهش و دگرگونی است.

flights_sml <- select(
  flights,
  year:day,
  ends_with("delay"),
  distance,
  air_time
)
mutate(flights_sml,
  gain = dep_delay - arr_delay,
  speed = distance / air_time * 60
)
## # A tibble: 336,776 x 9
##     year month   day dep_delay arr_delay distance air_time  gain speed
##    <int> <int> <int>     <dbl>     <dbl>    <dbl>    <dbl> <dbl> <dbl>
##  1  2013     1     1         2        11     1400      227    -9  370.
##  2  2013     1     1         4        20     1416      227   -16  374.
##  3  2013     1     1         2        33     1089      160   -31  408.
##  4  2013     1     1        -1       -18     1576      183    17  517.
##  5  2013     1     1        -6       -25      762      116    19  394.
##  6  2013     1     1        -4        12      719      150   -16  288.
##  7  2013     1     1        -5        19     1065      158   -24  404.
##  8  2013     1     1        -3       -14      229       53    11  259.
##  9  2013     1     1        -3        -8      944      140     5  405.
## 10  2013     1     1        -2         8      733      138   -10  319.
## # ... with 336,766 more rows
توجه داشته باشید که می توانید به ستون هایی که به تازگی ایجاد کرده اید ارجاع دهید. 
mutate(flights_sml,
  gain = dep_delay - arr_delay,
  hours = air_time / 60,
  gain_per_hour = 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_hour <dbl>
توابع برداری زیادی برای ساختن متغیرهای جدید وجود دارد. اگر می خواهید فقط متغیرهای جدید را حفظ کنید، از transmute استفاده کنید. Transmute به معنای تبدیل است. 
transmute(flights_sml,
  gain = dep_delay - arr_delay,
  hours = air_time / 60,
  gain_per_hour = gain / hours
)
## # A tibble: 336,776 x 3
##     gain hours gain_per_hour
##    <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 rows
transmute(flights, across(ends_with("delay"), abs))
## # A tibble: 336,776 x 2
##    dep_delay arr_delay
##        <dbl>     <dbl>
##  1         2        11
##  2         4        20
##  3         2        33
##  4         1        18
##  5         6        25
##  6         4        12
##  7         5        19
##  8         3        14
##  9         3         8
## 10         2         8
## # ... with 336,766 more rows

خلاصه های گروه بندی شده با ()summarise

summarise(flights, delay = mean(dep_delay, na.rm = TRUE))
## # A tibble: 1 x 1
##   delay
##   <dbl>
## 1  12.6
ترکیب summarise و group_by 
by_day <- group_by(flights, year, month, day)
summarise(by_day, delay = mean(dep_delay, na.rm = TRUE))
## # A tibble: 365 x 4
## # Groups:   year, month [12]
##     year month   day delay
##    <int> <int> <int> <dbl>
##  1  2013     1     1 11.5 
##  2  2013     1     2 13.9 
##  3  2013     1     3 11.0 
##  4  2013     1     4  8.95
##  5  2013     1     5  5.73
##  6  2013     1     6  7.15
##  7  2013     1     7  5.42
##  8  2013     1     8  2.55
##  9  2013     1     9  2.28
## 10  2013     1    10  2.84
## # ... with 355 more rows

ترکیب چندین عملیات با pipe

flights %>%
  group_by(dest) %>%
  summarise(
    count = n(),
    dist = mean(distance, na.rm = TRUE),
    delay = mean(arr_delay, na.rm = TRUE)
  ) %>%
  filter(count > 20, dest != "HNL")
## # A tibble: 96 x 4
##    dest  count  dist delay
##    <chr> <int> <dbl> <dbl>
##  1 ABQ     254 1826   4.38
##  2 ACK     265  199   4.85
##  3 ALB     439  143  14.4 
##  4 ATL   17215  757. 11.3 
##  5 AUS    2439 1514.  6.02
##  6 AVL     275  584.  8.00
##  7 BDL     443  116   7.05
##  8 BGR     375  378   8.03
##  9 BHM     297  866. 16.9 
## 10 BNA    6333  758. 11.8 
## # ... with 86 more rows

توابع زیادی برای بدست آوردن خلاصه های وجود دارد. در بالا محاسبه تعداد هر گروه با استفاده از ()n دیده شد. اگر هدف فقط به دست آوردن تعداد باشد، این کار با استفاده توابع tally و count ساده تر است.

flights %>% tally()
## # A tibble: 1 x 1
##        n
##    <int>
## 1 336776
flights %>% count(dest)
## # A tibble: 105 x 2
##    dest      n
##    <chr> <int>
##  1 ABQ     254
##  2 ACK     265
##  3 ALB     439
##  4 ANC       8
##  5 ATL   17215
##  6 AUS    2439
##  7 AVL     275
##  8 BDL     443
##  9 BGR     375
## 10 BHM     297
## # ... with 95 more rows
flights %>% count(dest, sort = TRUE, name = "size")
## # A tibble: 105 x 2
##    dest   size
##    <chr> <int>
##  1 ORD   17283
##  2 ATL   17215
##  3 LAX   16174
##  4 BOS   15508
##  5 MCO   14082
##  6 CLT   14064
##  7 SFO   13331
##  8 FLL   12055
##  9 MIA   11728
## 10 DCA    9705
## # ... with 95 more rows
flights %>%
  count(dest, sort = TRUE, name = "size") %>%
  filter(size > 12000)
## # A tibble: 8 x 2
##   dest   size
##   <chr> <int>
## 1 ORD   17283
## 2 ATL   17215
## 3 LAX   16174
## 4 BOS   15508
## 5 MCO   14082
## 6 CLT   14064
## 7 SFO   13331
## 8 FLL   12055

توابع add_tally و add_count همان محاسبات را انجام می دهند، اما تعداد را به صورت یک ستون به داده های اصلی اضافه می کنند.

بخش سوم



داده های مرتب با tidyr

داده های مرتب با tidyr

همانطور که قبلاً اشاره شد، داده های مرتب (tidy) اساس کار بسته های Tidyverse را تشکیل می دهند.

کار بر روی ساختمان این داده ها با استفاده از بسته tidyr امکان پذیر است.

چرخاندن (pivoting)

ممکن است داده ها در انواع عریض و طویل دیده شوند. در اینجا یک مجموعه داده در چند قالب دیده می شود. این داده ها، تعداد مبتلایان بیماری سل در سالهای 1999 و 2000 در کشورهای افغانستان، برزیل و چین را گزارش می کنند.

table1
## # A tibble: 6 x 4
##   country      year  cases population
##   <chr>       <int>  <int>      <int>
## 1 Afghanistan  1999    745   19987071
## 2 Afghanistan  2000   2666   20595360
## 3 Brazil       1999  37737  172006362
## 4 Brazil       2000  80488  174504898
## 5 China        1999 212258 1272915272
## 6 China        2000 213766 1280428583
table2
## # A tibble: 12 x 4
##    country      year type            count
##    <chr>       <int> <chr>           <int>
##  1 Afghanistan  1999 cases             745
##  2 Afghanistan  1999 population   19987071
##  3 Afghanistan  2000 cases            2666
##  4 Afghanistan  2000 population   20595360
##  5 Brazil       1999 cases           37737
##  6 Brazil       1999 population  172006362
##  7 Brazil       2000 cases           80488
##  8 Brazil       2000 population  174504898
##  9 China        1999 cases          212258
## 10 China        1999 population 1272915272
## 11 China        2000 cases          213766
## 12 China        2000 population 1280428583
table3
## # A tibble: 6 x 3
##   country      year rate             
## * <chr>       <int> <chr>            
## 1 Afghanistan  1999 745/19987071     
## 2 Afghanistan  2000 2666/20595360    
## 3 Brazil       1999 37737/172006362  
## 4 Brazil       2000 80488/174504898  
## 5 China        1999 212258/1272915272
## 6 China        2000 213766/1280428583
table4a # cases
## # A tibble: 3 x 3
##   country     `1999` `2000`
## * <chr>        <int>  <int>
## 1 Afghanistan    745   2666
## 2 Brazil       37737  80488
## 3 China       212258 213766
table4b # population
## # A tibble: 3 x 3
##   country         `1999`     `2000`
## * <chr>            <int>      <int>
## 1 Afghanistan   19987071   20595360
## 2 Brazil       172006362  174504898
## 3 China       1272915272 1280428583

تبدیل جدول عریض به طویل با ()pivot_longer

table4b
## # A tibble: 3 x 3
##   country         `1999`     `2000`
## * <chr>            <int>      <int>
## 1 Afghanistan   19987071   20595360
## 2 Brazil       172006362  174504898
## 3 China       1272915272 1280428583
table4a %>%
  pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "cases")
## # A tibble: 6 x 3
##   country     year   cases
##   <chr>       <chr>  <int>
## 1 Afghanistan 1999     745
## 2 Afghanistan 2000    2666
## 3 Brazil      1999   37737
## 4 Brazil      2000   80488
## 5 China       1999  212258
## 6 China       2000  213766

تبدیل جدول طویل به عریض با ()pivot_wider

table2
## # A tibble: 12 x 4
##    country      year type            count
##    <chr>       <int> <chr>           <int>
##  1 Afghanistan  1999 cases             745
##  2 Afghanistan  1999 population   19987071
##  3 Afghanistan  2000 cases            2666
##  4 Afghanistan  2000 population   20595360
##  5 Brazil       1999 cases           37737
##  6 Brazil       1999 population  172006362
##  7 Brazil       2000 cases           80488
##  8 Brazil       2000 population  174504898
##  9 China        1999 cases          212258
## 10 China        1999 population 1272915272
## 11 China        2000 cases          213766
## 12 China        2000 population 1280428583
table2 %>%
  pivot_wider(names_from = type, values_from = count)
## # A tibble: 6 x 4
##   country      year  cases population
##   <chr>       <int>  <int>      <int>
## 1 Afghanistan  1999    745   19987071
## 2 Afghanistan  2000   2666   20595360
## 3 Brazil       1999  37737  172006362
## 4 Brazil       2000  80488  174504898
## 5 China        1999 212258 1272915272
## 6 China        2000 213766 1280428583

منفصل کردن ستون ها با ()separate

table3
## # A tibble: 6 x 3
##   country      year rate             
## * <chr>       <int> <chr>            
## 1 Afghanistan  1999 745/19987071     
## 2 Afghanistan  2000 2666/20595360    
## 3 Brazil       1999 37737/172006362  
## 4 Brazil       2000 80488/174504898  
## 5 China        1999 212258/1272915272
## 6 China        2000 213766/1280428583
table3 %>%
  separate(rate, into = c("cases", "population"))
## # A tibble: 6 x 4
##   country      year cases  population
##   <chr>       <int> <chr>  <chr>     
## 1 Afghanistan  1999 745    19987071  
## 2 Afghanistan  2000 2666   20595360  
## 3 Brazil       1999 37737  172006362 
## 4 Brazil       2000 80488  174504898 
## 5 China        1999 212258 1272915272
## 6 China        2000 213766 1280428583

table3 %>%
  separate(rate, into = c("cases", "population"), convert = TRUE, remove = FALSE)
## # A tibble: 6 x 5
##   country      year rate               cases population
##   <chr>       <int> <chr>              <int>      <int>
## 1 Afghanistan  1999 745/19987071         745   19987071
## 2 Afghanistan  2000 2666/20595360       2666   20595360
## 3 Brazil       1999 37737/172006362    37737  172006362
## 4 Brazil       2000 80488/174504898    80488  174504898
## 5 China        1999 212258/1272915272 212258 1272915272
## 6 China        2000 213766/1280428583 213766 1280428583
table3 %>%
  separate(year, into = c("century", "year"), sep = 2)
## # A tibble: 6 x 4
##   country     century year  rate             
##   <chr>       <chr>   <chr> <chr>            
## 1 Afghanistan 19      99    745/19987071     
## 2 Afghanistan 20      00    2666/20595360    
## 3 Brazil      19      99    37737/172006362  
## 4 Brazil      20      00    80488/174504898  
## 5 China       19      99    212258/1272915272
## 6 China       20      00    213766/1280428583

متصل کردن ستون ها با ()unite

table5
## # A tibble: 6 x 4
##   country     century year  rate             
## * <chr>       <chr>   <chr> <chr>            
## 1 Afghanistan 19      99    745/19987071     
## 2 Afghanistan 20      00    2666/20595360    
## 3 Brazil      19      99    37737/172006362  
## 4 Brazil      20      00    80488/174504898  
## 5 China       19      99    212258/1272915272
## 6 China       20      00    213766/1280428583
table5 %>%
  unite(new, century, year)
## # A tibble: 6 x 3
##   country     new   rate             
##   <chr>       <chr> <chr>            
## 1 Afghanistan 19_99 745/19987071     
## 2 Afghanistan 20_00 2666/20595360    
## 3 Brazil      19_99 37737/172006362  
## 4 Brazil      20_00 80488/174504898  
## 5 China       19_99 212258/1272915272
## 6 China       20_00 213766/1280428583
table5 %>%
  unite(new, century, year, sep = "")
## # A tibble: 6 x 3
##   country     new   rate             
##   <chr>       <chr> <chr>            
## 1 Afghanistan 1999  745/19987071     
## 2 Afghanistan 2000  2666/20595360    
## 3 Brazil      1999  37737/172006362  
## 4 Brazil      2000  80488/174504898  
## 5 China       1999  212258/1272915272
## 6 China       2000  213766/1280428583

بسط جداول با ()expand و ()complete

df1 <- tibble(x1 = c("A", "B", "B"), x2 = c(1, 1, 2), x3 = c(3, 4, 5))
df1
## # A tibble: 3 x 3
##   x1       x2    x3
##   <chr> <dbl> <dbl>
## 1 A         1     3
## 2 B         1     4
## 3 B         2     5
expand(df1, x1, x2)
## # A tibble: 4 x 2
##   x1       x2
##   <chr> <dbl>
## 1 A         1
## 2 A         2
## 3 B         1
## 4 B         2
complete(df1, x1, x2)
## # A tibble: 4 x 3
##   x1       x2    x3
##   <chr> <dbl> <dbl>
## 1 A         1     3
## 2 A         2    NA
## 3 B         1     4
## 4 B         2     5
برای مدیریت مقادیر گم شده می توان به صورت زیر عمل کرد: 
df2 <- complete(df1, x1, x2)
drop_na(df2) # na.omit
## # A tibble: 3 x 3
##   x1       x2    x3
##   <chr> <dbl> <dbl>
## 1 A         1     3
## 2 B         1     4
## 3 B         2     5
drop_na(df2, x3)
## # A tibble: 3 x 3
##   x1       x2    x3
##   <chr> <dbl> <dbl>
## 1 A         1     3
## 2 B         1     4
## 3 B         2     5
fill(df2, x3)
## # A tibble: 4 x 3
##   x1       x2    x3
##   <chr> <dbl> <dbl>
## 1 A         1     3
## 2 A         2     3
## 3 B         1     4
## 4 B         2     5
replace_na(df2, list(x3 = 0))
## # A tibble: 4 x 3
##   x1       x2    x3
##   <chr> <dbl> <dbl>
## 1 A         1     3
## 2 A         2     0
## 3 B         1     4
## 4 B         2     5

بخش چهارم



داده های رابطه ای با dplyr

داده های رابطه ای با dplyr

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>
airlines
## # A tibble: 16 x 2
##    carrier name                       
##    <chr>   <chr>                      
##  1 9E      Endeavor Air Inc.          
##  2 AA      American Airlines Inc.     
##  3 AS      Alaska Airlines Inc.       
##  4 B6      JetBlue Airways            
##  5 DL      Delta Air Lines Inc.       
##  6 EV      ExpressJet Airlines Inc.   
##  7 F9      Frontier Airlines Inc.     
##  8 FL      AirTran Airways Corporation
##  9 HA      Hawaiian Airlines Inc.     
## 10 MQ      Envoy Air                  
## 11 OO      SkyWest Airlines Inc.      
## 12 UA      United Air Lines Inc.      
## 13 US      US Airways Inc.            
## 14 VX      Virgin America             
## 15 WN      Southwest Airlines Co.     
## 16 YV      Mesa Airlines Inc.
airports
## # A tibble: 1,458 x 8
##    faa   name                             lat    lon   alt    tz dst   tzone    
##    <chr> <chr>                          <dbl>  <dbl> <dbl> <dbl> <chr> <chr>    
##  1 04G   Lansdowne Airport               41.1  -80.6  1044    -5 A     America/~
##  2 06A   Moton Field Municipal Airport   32.5  -85.7   264    -6 A     America/~
##  3 06C   Schaumburg Regional             42.0  -88.1   801    -6 A     America/~
##  4 06N   Randall Airport                 41.4  -74.4   523    -5 A     America/~
##  5 09J   Jekyll Island Airport           31.1  -81.4    11    -5 A     America/~
##  6 0A9   Elizabethton Municipal Airport  36.4  -82.2  1593    -5 A     America/~
##  7 0G6   Williams County Airport         41.5  -84.5   730    -5 A     America/~
##  8 0G7   Finger Lakes Regional Airport   42.9  -76.8   492    -5 A     America/~
##  9 0P2   Shoestring Aviation Airfield    39.8  -76.6  1000    -5 U     America/~
## 10 0S9   Jefferson County Intl           48.1 -123.    108    -8 A     America/~
## # ... with 1,448 more rows
planes
## # A tibble: 3,322 x 9
##    tailnum  year type          manufacturer   model  engines seats speed engine 
##    <chr>   <int> <chr>         <chr>          <chr>    <int> <int> <int> <chr>  
##  1 N10156   2004 Fixed wing m~ EMBRAER        EMB-1~       2    55    NA Turbo-~
##  2 N102UW   1998 Fixed wing m~ AIRBUS INDUST~ A320-~       2   182    NA Turbo-~
##  3 N103US   1999 Fixed wing m~ AIRBUS INDUST~ A320-~       2   182    NA Turbo-~
##  4 N104UW   1999 Fixed wing m~ AIRBUS INDUST~ A320-~       2   182    NA Turbo-~
##  5 N10575   2002 Fixed wing m~ EMBRAER        EMB-1~       2    55    NA Turbo-~
##  6 N105UW   1999 Fixed wing m~ AIRBUS INDUST~ A320-~       2   182    NA Turbo-~
##  7 N107US   1999 Fixed wing m~ AIRBUS INDUST~ A320-~       2   182    NA Turbo-~
##  8 N108UW   1999 Fixed wing m~ AIRBUS INDUST~ A320-~       2   182    NA Turbo-~
##  9 N109UW   1999 Fixed wing m~ AIRBUS INDUST~ A320-~       2   182    NA Turbo-~
## 10 N110UW   1999 Fixed wing m~ AIRBUS INDUST~ A320-~       2   182    NA Turbo-~
## # ... with 3,312 more rows
weather
## # A tibble: 26,115 x 15
##    origin  year month   day  hour  temp  dewp humid wind_dir wind_speed
##    <chr>  <int> <int> <int> <int> <dbl> <dbl> <dbl>    <dbl>      <dbl>
##  1 EWR     2013     1     1     1  39.0  26.1  59.4      270      10.4 
##  2 EWR     2013     1     1     2  39.0  27.0  61.6      250       8.06
##  3 EWR     2013     1     1     3  39.0  28.0  64.4      240      11.5 
##  4 EWR     2013     1     1     4  39.9  28.0  62.2      250      12.7 
##  5 EWR     2013     1     1     5  39.0  28.0  64.4      260      12.7 
##  6 EWR     2013     1     1     6  37.9  28.0  67.2      240      11.5 
##  7 EWR     2013     1     1     7  39.0  28.0  64.4      240      15.0 
##  8 EWR     2013     1     1     8  39.9  28.0  62.2      250      10.4 
##  9 EWR     2013     1     1     9  39.9  28.0  62.2      260      15.0 
## 10 EWR     2013     1     1    10  41    28.0  59.6      260      13.8 
## # ... with 26,105 more rows, and 5 more variables: wind_gust <dbl>,
## #   precip <dbl>, pressure <dbl>, visib <dbl>, time_hour <dttm>

تشخیص کلید اصلی

کلید اصلی کلیدی است که به طور یکتا یک مشاهده در داده ها را تعیین می کند. 
planes %>%
  count(tailnum) %>%
  filter(n > 1)
## # A tibble: 0 x 2
## # ... with 2 variables: tailnum <chr>, n <int>
weather %>%
  count(year, month, day, hour, origin) %>%
  filter(n > 1)
## # A tibble: 3 x 6
##    year month   day  hour origin     n
##   <int> <int> <int> <int> <chr>  <int>
## 1  2013    11     3     1 EWR        2
## 2  2013    11     3     1 JFK        2
## 3  2013    11     3     1 LGA        2
flights %>%
  count(year, month, day, flight) %>%
  filter(n > 1)
## # A tibble: 29,768 x 5
##     year month   day flight     n
##    <int> <int> <int>  <int> <int>
##  1  2013     1     1      1     2
##  2  2013     1     1      3     2
##  3  2013     1     1      4     2
##  4  2013     1     1     11     3
##  5  2013     1     1     15     2
##  6  2013     1     1     21     2
##  7  2013     1     1     27     4
##  8  2013     1     1     31     2
##  9  2013     1     1     32     2
## 10  2013     1     1     35     2
## # ... with 29,758 more rows
flights %>%
  count(year, month, day, tailnum) %>%
  filter(n > 1)
## # A tibble: 64,928 x 5
##     year month   day tailnum     n
##    <int> <int> <int> <chr>   <int>
##  1  2013     1     1 N0EGMQ      2
##  2  2013     1     1 N11189      2
##  3  2013     1     1 N11536      2
##  4  2013     1     1 N11544      3
##  5  2013     1     1 N11551      2
##  6  2013     1     1 N12540      2
##  7  2013     1     1 N12567      2
##  8  2013     1     1 N13123      2
##  9  2013     1     1 N13538      3
## 10  2013     1     1 N13566      3
## # ... with 64,918 more rows

انواع اتصالات داده های رابطه ای

برای کار با داده های رابطه ای به توابعی نیاز دارید که با جفت جداول کار کنند. سه خانواده از توابع برای کار با داده های رابطه ای طراحی شده اند:

  • اتصالات جهشی (Mutating joins)، که متغیرهای جدیدی را به یک چارچوب داده از مشاهدات مشابه در دیگری اضافه می کنند.
  • اتصالات فیلتری (Filtering joins)، که مشاهدات یک چارچوب داده را بر اساس مطابقت یا عدم مطابقت با مشاهدات در جدول دیگر فیلتر می کنند.
  • عملگرهای مجموعه ای (Set operations)، که با مشاهدات به گونه ای رفتار می کند که گویی عناصر مجموعه هستند.

اتصالات جهشی (Mutating joins)

flights2 <- flights %>%
  select(year:day, hour, origin, dest, tailnum, carrier)
flights2
## # A tibble: 336,776 x 8
##     year month   day  hour origin dest  tailnum carrier
##    <int> <int> <int> <dbl> <chr>  <chr> <chr>   <chr>  
##  1  2013     1     1     5 EWR    IAH   N14228  UA     
##  2  2013     1     1     5 LGA    IAH   N24211  UA     
##  3  2013     1     1     5 JFK    MIA   N619AA  AA     
##  4  2013     1     1     5 JFK    BQN   N804JB  B6     
##  5  2013     1     1     6 LGA    ATL   N668DN  DL     
##  6  2013     1     1     5 EWR    ORD   N39463  UA     
##  7  2013     1     1     6 EWR    FLL   N516JB  B6     
##  8  2013     1     1     6 LGA    IAD   N829AS  EV     
##  9  2013     1     1     6 JFK    MCO   N593JB  B6     
## 10  2013     1     1     6 LGA    ORD   N3ALAA  AA     
## # ... with 336,766 more rows
flights2 %>%
  select(-origin, -dest) %>%
  left_join(airlines, by = "carrier")
## # A tibble: 336,776 x 7
##     year month   day  hour tailnum carrier name                    
##    <int> <int> <int> <dbl> <chr>   <chr>   <chr>                   
##  1  2013     1     1     5 N14228  UA      United Air Lines Inc.   
##  2  2013     1     1     5 N24211  UA      United Air Lines Inc.   
##  3  2013     1     1     5 N619AA  AA      American Airlines Inc.  
##  4  2013     1     1     5 N804JB  B6      JetBlue Airways         
##  5  2013     1     1     6 N668DN  DL      Delta Air Lines Inc.    
##  6  2013     1     1     5 N39463  UA      United Air Lines Inc.   
##  7  2013     1     1     6 N516JB  B6      JetBlue Airways         
##  8  2013     1     1     6 N829AS  EV      ExpressJet Airlines Inc.
##  9  2013     1     1     6 N593JB  B6      JetBlue Airways         
## 10  2013     1     1     6 N3ALAA  AA      American Airlines Inc.  
## # ... with 336,766 more rows
flights2 %>%
  select(-origin, -dest) %>%
  mutate(name = airlines$name[match(carrier, airlines$carrier)])
## # A tibble: 336,776 x 7
##     year month   day  hour tailnum carrier name                    
##    <int> <int> <int> <dbl> <chr>   <chr>   <chr>                   
##  1  2013     1     1     5 N14228  UA      United Air Lines Inc.   
##  2  2013     1     1     5 N24211  UA      United Air Lines Inc.   
##  3  2013     1     1     5 N619AA  AA      American Airlines Inc.  
##  4  2013     1     1     5 N804JB  B6      JetBlue Airways         
##  5  2013     1     1     6 N668DN  DL      Delta Air Lines Inc.    
##  6  2013     1     1     5 N39463  UA      United Air Lines Inc.   
##  7  2013     1     1     6 N516JB  B6      JetBlue Airways         
##  8  2013     1     1     6 N829AS  EV      ExpressJet Airlines Inc.
##  9  2013     1     1     6 N593JB  B6      JetBlue Airways         
## 10  2013     1     1     6 N3ALAA  AA      American Airlines Inc.  
## # ... with 336,766 more rows

درک اتصالات

x <- tribble(
  ~key, ~val_x,
  1, "x1",
  2, "x2",
  3, "x3"
)
x
## # A tibble: 3 x 2
##     key val_x
##   <dbl> <chr>
## 1     1 x1   
## 2     2 x2   
## 3     3 x3
y <- tribble(
  ~key, ~val_y,
  1, "y1",
  2, "y2",
  4, "y3"
)
y
## # A tibble: 3 x 2
##     key val_y
##   <dbl> <chr>
## 1     1 y1   
## 2     2 y2   
## 3     4 y3

Inner join

x %>%
  inner_join(y, by = "key")
## # A tibble: 2 x 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2

Outer joins

x %>%
  left_join(y, by = "key")
## # A tibble: 3 x 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2   
## 3     3 x3    <NA>
x %>%
  right_join(y, by = "key")
## # A tibble: 3 x 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2   
## 3     4 <NA>  y3
x %>%
  full_join(y, by = "key")
## # A tibble: 4 x 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2   
## 3     3 x3    <NA> 
## 4     4 <NA>  y3

تعریف ستون های کلید

flights2 %>%
  left_join(weather)
## Joining, by = c("year", "month", "day", "hour", "origin")
## # A tibble: 336,776 x 18
##     year month   day  hour origin dest  tailnum carrier  temp  dewp humid
##    <int> <int> <int> <dbl> <chr>  <chr> <chr>   <chr>   <dbl> <dbl> <dbl>
##  1  2013     1     1     5 EWR    IAH   N14228  UA       39.0  28.0  64.4
##  2  2013     1     1     5 LGA    IAH   N24211  UA       39.9  25.0  54.8
##  3  2013     1     1     5 JFK    MIA   N619AA  AA       39.0  27.0  61.6
##  4  2013     1     1     5 JFK    BQN   N804JB  B6       39.0  27.0  61.6
##  5  2013     1     1     6 LGA    ATL   N668DN  DL       39.9  25.0  54.8
##  6  2013     1     1     5 EWR    ORD   N39463  UA       39.0  28.0  64.4
##  7  2013     1     1     6 EWR    FLL   N516JB  B6       37.9  28.0  67.2
##  8  2013     1     1     6 LGA    IAD   N829AS  EV       39.9  25.0  54.8
##  9  2013     1     1     6 JFK    MCO   N593JB  B6       37.9  27.0  64.3
## 10  2013     1     1     6 LGA    ORD   N3ALAA  AA       39.9  25.0  54.8
## # ... with 336,766 more rows, and 7 more variables: wind_dir <dbl>,
## #   wind_speed <dbl>, wind_gust <dbl>, precip <dbl>, pressure <dbl>,
## #   visib <dbl>, time_hour <dttm>
flights2 %>%
  left_join(planes, by = "tailnum")
## # A tibble: 336,776 x 16
##    year.x month   day  hour origin dest  tailnum carrier year.y type            
##     <int> <int> <int> <dbl> <chr>  <chr> <chr>   <chr>    <int> <chr>           
##  1   2013     1     1     5 EWR    IAH   N14228  UA        1999 Fixed wing mult~
##  2   2013     1     1     5 LGA    IAH   N24211  UA        1998 Fixed wing mult~
##  3   2013     1     1     5 JFK    MIA   N619AA  AA        1990 Fixed wing mult~
##  4   2013     1     1     5 JFK    BQN   N804JB  B6        2012 Fixed wing mult~
##  5   2013     1     1     6 LGA    ATL   N668DN  DL        1991 Fixed wing mult~
##  6   2013     1     1     5 EWR    ORD   N39463  UA        2012 Fixed wing mult~
##  7   2013     1     1     6 EWR    FLL   N516JB  B6        2000 Fixed wing mult~
##  8   2013     1     1     6 LGA    IAD   N829AS  EV        1998 Fixed wing mult~
##  9   2013     1     1     6 JFK    MCO   N593JB  B6        2004 Fixed wing mult~
## 10   2013     1     1     6 LGA    ORD   N3ALAA  AA          NA <NA>            
## # ... with 336,766 more rows, and 6 more variables: manufacturer <chr>,
## #   model <chr>, engines <int>, seats <int>, speed <int>, engine <chr>
flights2 %>%
  left_join(airports, by = c("dest" = "faa"))
## # A tibble: 336,776 x 15
##     year month   day  hour origin dest  tailnum carrier name     lat   lon   alt
##    <int> <int> <int> <dbl> <chr>  <chr> <chr>   <chr>   <chr>  <dbl> <dbl> <dbl>
##  1  2013     1     1     5 EWR    IAH   N14228  UA      Georg~  30.0 -95.3    97
##  2  2013     1     1     5 LGA    IAH   N24211  UA      Georg~  30.0 -95.3    97
##  3  2013     1     1     5 JFK    MIA   N619AA  AA      Miami~  25.8 -80.3     8
##  4  2013     1     1     5 JFK    BQN   N804JB  B6      <NA>    NA    NA      NA
##  5  2013     1     1     6 LGA    ATL   N668DN  DL      Harts~  33.6 -84.4  1026
##  6  2013     1     1     5 EWR    ORD   N39463  UA      Chica~  42.0 -87.9   668
##  7  2013     1     1     6 EWR    FLL   N516JB  B6      Fort ~  26.1 -80.2     9
##  8  2013     1     1     6 LGA    IAD   N829AS  EV      Washi~  38.9 -77.5   313
##  9  2013     1     1     6 JFK    MCO   N593JB  B6      Orlan~  28.4 -81.3    96
## 10  2013     1     1     6 LGA    ORD   N3ALAA  AA      Chica~  42.0 -87.9   668
## # ... with 336,766 more rows, and 3 more variables: tz <dbl>, dst <chr>,
## #   tzone <chr>
flights2 %>%
  left_join(airports, by = c("origin" = "faa"))
## # A tibble: 336,776 x 15
##     year month   day  hour origin dest  tailnum carrier name     lat   lon   alt
##    <int> <int> <int> <dbl> <chr>  <chr> <chr>   <chr>   <chr>  <dbl> <dbl> <dbl>
##  1  2013     1     1     5 EWR    IAH   N14228  UA      Newar~  40.7 -74.2    18
##  2  2013     1     1     5 LGA    IAH   N24211  UA      La Gu~  40.8 -73.9    22
##  3  2013     1     1     5 JFK    MIA   N619AA  AA      John ~  40.6 -73.8    13
##  4  2013     1     1     5 JFK    BQN   N804JB  B6      John ~  40.6 -73.8    13
##  5  2013     1     1     6 LGA    ATL   N668DN  DL      La Gu~  40.8 -73.9    22
##  6  2013     1     1     5 EWR    ORD   N39463  UA      Newar~  40.7 -74.2    18
##  7  2013     1     1     6 EWR    FLL   N516JB  B6      Newar~  40.7 -74.2    18
##  8  2013     1     1     6 LGA    IAD   N829AS  EV      La Gu~  40.8 -73.9    22
##  9  2013     1     1     6 JFK    MCO   N593JB  B6      John ~  40.6 -73.8    13
## 10  2013     1     1     6 LGA    ORD   N3ALAA  AA      La Gu~  40.8 -73.9    22
## # ... with 336,766 more rows, and 3 more variables: tz <dbl>, dst <chr>,
## #   tzone <chr>

اتصالات فیلتری (Filtering joins)

top_dest <- flights %>%
  count(dest, sort = TRUE) %>%
  head(10)
top_dest
## # A tibble: 10 x 2
##    dest      n
##    <chr> <int>
##  1 ORD   17283
##  2 ATL   17215
##  3 LAX   16174
##  4 BOS   15508
##  5 MCO   14082
##  6 CLT   14064
##  7 SFO   13331
##  8 FLL   12055
##  9 MIA   11728
## 10 DCA    9705

Semi join

flights %>%
  semi_join(top_dest)
## # A tibble: 141,145 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      542            540         2      923            850
##  2  2013     1     1      554            600        -6      812            837
##  3  2013     1     1      554            558        -4      740            728
##  4  2013     1     1      555            600        -5      913            854
##  5  2013     1     1      557            600        -3      838            846
##  6  2013     1     1      558            600        -2      753            745
##  7  2013     1     1      558            600        -2      924            917
##  8  2013     1     1      558            600        -2      923            937
##  9  2013     1     1      559            559         0      702            706
## 10  2013     1     1      600            600         0      851            858
## # ... with 141,135 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(dest %in% top_dest$dest)
## # A tibble: 141,145 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      542            540         2      923            850
##  2  2013     1     1      554            600        -6      812            837
##  3  2013     1     1      554            558        -4      740            728
##  4  2013     1     1      555            600        -5      913            854
##  5  2013     1     1      557            600        -3      838            846
##  6  2013     1     1      558            600        -2      753            745
##  7  2013     1     1      558            600        -2      924            917
##  8  2013     1     1      558            600        -2      923            937
##  9  2013     1     1      559            559         0      702            706
## 10  2013     1     1      600            600         0      851            858
## # ... with 141,135 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>

x %>%
  semi_join(y, by = "key")
## # A tibble: 2 x 2
##     key val_x
##   <dbl> <chr>
## 1     1 x1   
## 2     2 x2

Anti join

flights %>%
  anti_join(planes, by = "tailnum") %>%
  count(tailnum, sort = TRUE)
## # A tibble: 722 x 2
##    tailnum     n
##    <chr>   <int>
##  1 <NA>     2512
##  2 N725MQ    575
##  3 N722MQ    513
##  4 N723MQ    507
##  5 N713MQ    483
##  6 N735MQ    396
##  7 N0EGMQ    371
##  8 N534MQ    364
##  9 N542MQ    363
## 10 N531MQ    349
## # ... with 712 more rows

عملگرهای مجموعه ای (Set operations)

df1 <- tribble(
  ~x, ~y,
  1, 1,
  2, 1
)
df2 <- tribble(
  ~x, ~y,
  1, 1,
  1, 2
)
intersect(df1, df2)
## # A tibble: 1 x 2
##       x     y
##   <dbl> <dbl>
## 1     1     1
union(df1, df2)
## # A tibble: 3 x 2
##       x     y
##   <dbl> <dbl>
## 1     1     1
## 2     2     1
## 3     1     2
# compared with bind_rows
bind_rows(df1, df2, .id = "DF")
## # A tibble: 4 x 3
##   DF        x     y
##   <chr> <dbl> <dbl>
## 1 1         1     1
## 2 1         2     1
## 3 2         1     1
## 4 2         1     2
bind_cols(df1, df2)
## # A tibble: 2 x 4
##   x...1 y...2 x...3 y...4
##   <dbl> <dbl> <dbl> <dbl>
## 1     1     1     1     1
## 2     2     1     1     2
setdiff(df1, df2)
## # A tibble: 1 x 2
##       x     y
##   <dbl> <dbl>
## 1     2     1
setdiff(df2, df1)
## # A tibble: 1 x 2
##       x     y
##   <dbl> <dbl>
## 1     1     2

به پایان آمد این دفتر، حکایت همچنان باقیست