105學年度第二學期 巨量資料分析: 作業(1)	
系級:          姓名:

###############################################################################
# 請修課的同學親自打程式練習 [Week03-Lecture] (可互相討論，但不可以複製程式碼)
# http://www.hmwu.idv.tw/web/R/B01-1-hmwu_R-DataManipulation.pdf
# 範圍: Pages 43/112~90/112 (dplyr和tidyr的部份)
#
# 上傳期限: 2017/04/02, 24:00
# 上傳:教學網站【作業考試上傳區】，帳號: bigdata105 密碼: 1fxx (教室號碼) 
# 上傳目錄: 20170402-HW1-dplyr-tidyr
# 
# 可自行寫註解，寫筆記，或修改程式跑跑看
# 不要只照著講義打，要邊打程式，邊想是什麼意思。
# 自學能力真的很重要! 人生是你的，不是老師的。
# 不要投機取巧或不老實，隨便打(或複製)一些程式碼上傳只為了應付，
#     除了浪費時間，也毫無意義。
# 程式學習過程中本來就辛苦乏味，若有一天，你有機會發揮所學到的能力，就會快樂了~
# 有其它問題，請FB私訊老師，加油!!
# 
# 貼上執行程式碼及執行結果(如下範例)
###############################################################################
> # 45/112
> install.packages("nycflights13")
Installing package into ‘C:/Users/userpc/Documents/R/win-library/3.3’
(as ‘lib’ is unspecified)
Warning: package ‘nycflights13’ is in use and will not be installed
> library(nycflights13) # 把套件叫進來
> dim(flights) # 看一下資料的維度
[1] 336776     19
> head(flights, 4)
# A tibble: 4 × 19
   year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time arr_delay carrier flight tailnum origin
  <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>     <dbl>   <chr>  <int>   <chr>  <chr>
1  2013     1     1      517            515         2      830            819        11      UA   1545  N14228    EWR
2  2013     1     1      533            529         4      850            830        20      UA   1714  N24211    LGA
3  2013     1     1      542            540         2      923            850        33      AA   1141  N619AA    JFK
4  2013     1     1      544            545        -1     1004           1022       -18      B6    725  N804JB    JFK
# ... with 6 more variables: dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>
> 
> # 46/112
> library(dplyr)
> filter(flights, month == 1, day == 1) # 寫一下自己的註解
# A tibble: 842 × 19
    year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time arr_delay carrier flight tailnum origin
   <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>     <dbl>   <chr>  <int>   <chr>  <chr>
1   2013     1     1      517            515         2      830            819        11      UA   1545  N14228    EWR
2   2013     1     1      533            529         4      850            830        20      UA   1714  N24211    LGA
3   2013     1     1      542            540         2      923            850        33      AA   1141  N619AA    JFK
4   2013     1     1      544            545        -1     1004           1022       -18      B6    725  N804JB    JFK
5   2013     1     1      554            600        -6      812            837       -25      DL    461  N668DN    LGA
6   2013     1     1      554            558        -4      740            728        12      UA   1696  N39463    EWR
7   2013     1     1      555            600        -5      913            854        19      B6    507  N516JB    EWR
8   2013     1     1      557            600        -3      709            723       -14      EV   5708  N829AS    LGA
9   2013     1     1      557            600        -3      838            846        -8      B6     79  N593JB    JFK
10  2013     1     1      558            600        -2      753            745         8      AA    301  N3ALAA    LGA
# ... with 832 more rows, and 6 more variables: dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
#   time_hour <dttm>
> flights[flights$month == 1 & flights$day == 1, ]
# A tibble: 842 × 19
    year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time arr_delay carrier flight tailnum origin
   <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>     <dbl>   <chr>  <int>   <chr>  <chr>
1   2013     1     1      517            515         2      830            819        11      UA   1545  N14228    EWR
2   2013     1     1      533            529         4      850            830        20      UA   1714  N24211    LGA
3   2013     1     1      542            540         2      923            850        33      AA   1141  N619AA    JFK
4   2013     1     1      544            545        -1     1004           1022       -18      B6    725  N804JB    JFK
5   2013     1     1      554            600        -6      812            837       -25      DL    461  N668DN    LGA
6   2013     1     1      554            558        -4      740            728        12      UA   1696  N39463    EWR
7   2013     1     1      555            600        -5      913            854        19      B6    507  N516JB    EWR
8   2013     1     1      557            600        -3      709            723       -14      EV   5708  N829AS    LGA
9   2013     1     1      557            600        -3      838            846        -8      B6     79  N593JB    JFK
10  2013     1     1      558            600        -2      753            745         8      AA    301  N3ALAA    LGA
# ... with 832 more rows, and 6 more variables: dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
#   time_hour <dttm>
> table(flights$carrier)

   9E    AA    AS    B6    DL    EV    F9    FL    HA    MQ    OO    UA    US    VX    WN    YV 
18460 32729   714 54635 48110 54173   685  3260   342 26397    32 58665 20536  5162 12275   601 
> filter(flights, carrier %in% c("OO", "YV"))
# A tibble: 633 × 19
    year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time arr_delay carrier flight tailnum origin
   <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>     <dbl>   <chr>  <int>   <chr>  <chr>
1   2013     1     3     1428           1435        -7     1539           1559       -20      YV   3750  N509MJ    LGA
2   2013     1     3     1551           1602       -11     1659           1722       -23      YV   3771  N508MJ    LGA
3   2013     1     4     1430           1435        -5     1546           1559       -13      YV   3750  N511MJ    LGA
4   2013     1     4     1731           1602        89     1837           1722        75      YV   3771  N513MJ    LGA
5   2013     1     6     1557           1605        -8     1714           1729       -15      YV   3771  N511MJ    LGA
6   2013     1     7     1430           1435        -5     1541           1559       -18      YV   3750  N507MJ    LGA
7   2013     1     7     1556           1602        -6     1721           1722        -1      YV   3771  N509MJ    LGA
8   2013     1     8     1432           1435        -3     1537           1559       -22      YV   3750  N513MJ    LGA
9   2013     1     8     1555           1602        -7     1727           1722         5      YV   3771  N506MJ    LGA
10  2013     1     9     1432           1435        -3     1543           1559       -16      YV   3750  N505MJ    LGA
# ... with 623 more rows, and 6 more variables: dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
#   time_hour <dttm>
> filter(flights, carrier != "AA") # 修改一下程式試試看
# A tibble: 304,047 × 19
    year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time arr_delay carrier flight tailnum origin
   <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>     <dbl>   <chr>  <int>   <chr>  <chr>
1   2013     1     1      517            515         2      830            819        11      UA   1545  N14228    EWR
2   2013     1     1      533            529         4      850            830        20      UA   1714  N24211    LGA
3   2013     1     1      544            545        -1     1004           1022       -18      B6    725  N804JB    JFK
4   2013     1     1      554            600        -6      812            837       -25      DL    461  N668DN    LGA
5   2013     1     1      554            558        -4      740            728        12      UA   1696  N39463    EWR
6   2013     1     1      555            600        -5      913            854        19      B6    507  N516JB    EWR
7   2013     1     1      557            600        -3      709            723       -14      EV   5708  N829AS    LGA
8   2013     1     1      557            600        -3      838            846        -8      B6     79  N593JB    JFK
9   2013     1     1      558            600        -2      849            851        -2      B6     49  N793JB    JFK
10  2013     1     1      558            600        -2      853            856        -3      B6     71  N657JB    JFK
# ... with 304,037 more rows, and 6 more variables: dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
#   time_hour <dttm>
> 
>