2020-03-23-In-class-exercise-5

資料沒有分類（只有V1），要自己分類變項

dat <- read.csv("C:/Users/X510/Desktop/2020-03-23-In-class-exercise-5/aaup2.dat.txt", sep=",", stringsAsFactor=FALSE, header = F)
names(dat)

## [1] "V1"

計算資料所佔的空格，並劃定資料

library(readr)
dta <- readr::read_fwf("C:/Users/X510/Desktop/2020-03-23-In-class-exercise-5/aaup2.dat.txt", fwf_cols(V1 = 6, V2 = 31, V3 = 3, V4 = 4, V5 = 4, V6 = 4, V7 = 4, V8 = 4, V9 = 5, V10 = 4, V11 = 4, V12 = 5, V13 = 4, V14 = 4, V15 = 4, V16 = 4, V17 = 5))

## Parsed with column specification:
## cols(
##   V1 = col_double(),
##   V2 = col_character(),
##   V3 = col_character(),
##   V4 = col_character(),
##   V5 = col_character(),
##   V6 = col_character(),
##   V7 = col_character(),
##   V8 = col_double(),
##   V9 = col_character(),
##   V10 = col_character(),
##   V11 = col_character(),
##   V12 = col_double(),
##   V13 = col_double(),
##   V14 = col_double(),
##   V15 = col_double(),
##   V16 = col_double(),
##   V17 = col_double()
## )

str(dta)

## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 1161 obs. of  17 variables:
##  $ V1 : num  1061 1063 1065 11462 1002 ...
##  $ V2 : chr  "Alaska Pacific University" "Univ.Alaska-Fairbanks" "Univ.Alaska-Southeast" "Univ.Alaska-Anchorage" ...
##  $ V3 : chr  "AK" "AK" "AK" "AK" ...
##  $ V4 : chr  "IIB" "I" "IIA" "IIA" ...
##  $ V5 : chr  "454" "686" "533" "612" ...
##  $ V6 : chr  "382" "560" "494" "507" ...
##  $ V7 : chr  "362" "432" "329" "414" ...
##  $ V8 : num  382 508 415 498 350 388 396 455 401 411 ...
##  $ V9 : chr  "567" "914" "716" "825" ...
##  $ V10: chr  "485" "753" "663" "681" ...
##  $ V11: chr  "471" "572" "442" "557" ...
##  $ V12: num  487 677 559 670 423 477 478 546 523 503 ...
##  $ V13: num  6 74 9 115 59 57 20 366 34 67 ...
##  $ V14: num  11 125 26 124 77 33 18 354 25 40 ...
##  $ V15: num  9 118 20 101 102 35 30 301 27 66 ...
##  $ V16: num  4 40 9 21 24 2 0 66 3 27 ...
##  $ V17: num  32 404 70 392 262 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   V1 = col_double(),
##   ..   V2 = col_character(),
##   ..   V3 = col_character(),
##   ..   V4 = col_character(),
##   ..   V5 = col_character(),
##   ..   V6 = col_character(),
##   ..   V7 = col_character(),
##   ..   V8 = col_double(),
##   ..   V9 = col_character(),
##   ..   V10 = col_character(),
##   ..   V11 = col_character(),
##   ..   V12 = col_double(),
##   ..   V13 = col_double(),
##   ..   V14 = col_double(),
##   ..   V15 = col_double(),
##   ..   V16 = col_double(),
##   ..   V17 = col_double()
##   .. )

修改"*“為”NA"

dta[dta == "*"] <- "NA"
# 或用fix慢慢修改
fix(dta)