2주차 과제

Q1

test <- c(80, 60, 70, 50, 90)

Q2

mean(test)
## [1] 70

Q3

(mean.test <- mean(test))
## [1] 70

3주차 과제

Q2. Find out about the function β€˜rep’ by typing ?rep and generate a vector containing 10 repetitions of the word β€œnoun”, and another vector containing 10 repetitions of the word β€œnoun” and 20 repetitions of β€œverb”.

μš°μ„  ?rep을 μž‘λ™μ‹œμΌœλ³΄λ©΄ μ•„λž˜μ™€ 같은 ꡬ쑰와 μ˜ˆμ‹œκ°€ λ‚˜μ˜¨λ‹€.

#rep(x, times = 1, length.out = NA, each = 1)

rep(1:4, 2)
## [1] 1 2 3 4 1 2 3 4
rep(1:4, each = 2)       # not the same.
## [1] 1 1 2 2 3 3 4 4
rep(1:4, c(2,2,2,2))     # same as second.
## [1] 1 1 2 2 3 3 4 4
rep(1:4, c(2,1,2,1))
## [1] 1 1 2 3 3 4
rep(1:4, each = 2, len = 4)    # first 4 only.
## [1] 1 1 2 2
rep(1:4, each = 2, len = 10)   # 8 integers plus two recycled 1's.
##  [1] 1 1 2 2 3 3 4 4 1 1
rep(1:4, each = 2, times = 3)  # length 24, 3 complete replications
##  [1] 1 1 2 2 3 3 4 4 1 1 2 2 3 3 4 4 1 1 2 2 3 3 4 4

즉, rep(x, times = 1, length.out = NA, each = 1)μ—μ„œ 각각 μ˜λ―Έν•˜λŠ” 것은
x: vector
times: 반볡 횟수
length.out: 길이 μ œν•œ
each: xμ•ˆμ— λ“€μ–΄ μžˆλŠ” 각 element의 반볡 횟수

κ·ΈλŸ¬λ―€λ‘œ β€œnoun”을 10번, β€œverb”λ₯Ό 20번 λ°˜λ³΅ν•˜λŠ” vectorλ₯Ό λ§Œλ“€λ €λ©΄ μ•„λž˜μ™€ 같이 μž…λ ₯ν•˜λ©΄ λœλ‹€.

(nounverb <- c(rep("noun", 10), rep("verb", 20)))
##  [1] "noun" "noun" "noun" "noun" "noun" "noun" "noun" "noun" "noun" "noun"
## [11] "verb" "verb" "verb" "verb" "verb" "verb" "verb" "verb" "verb" "verb"
## [21] "verb" "verb" "verb" "verb" "verb" "verb" "verb" "verb" "verb" "verb"

Q3. Find out what the funciton β€˜seq’ does, and generate a user-defined regular sequence.

μš°μ„  ?rep을 μž‘λ™μ‹œμΌœλ³΄λ©΄ μ•„λž˜μ™€ 같은 ꡬ쑰와 μ˜ˆμ‹œκ°€ λ‚˜μ˜¨λ‹€.

#seq(from = 1, to = 1, by = ((to - from)/(length.out - 1)), length.out = NULL)

seq(0, 1, length.out = 11)
##  [1] 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
seq(1, 9, by = 2)     # matches 'end'
## [1] 1 3 5 7 9
seq(1, 9, by = pi)    # stays below 'end'
## [1] 1.000000 4.141593 7.283185
seq(1, 6, by = 3)
## [1] 1 4
seq(1.575, 5.125, by = 0.05)
##  [1] 1.575 1.625 1.675 1.725 1.775 1.825 1.875 1.925 1.975 2.025 2.075 2.125
## [13] 2.175 2.225 2.275 2.325 2.375 2.425 2.475 2.525 2.575 2.625 2.675 2.725
## [25] 2.775 2.825 2.875 2.925 2.975 3.025 3.075 3.125 3.175 3.225 3.275 3.325
## [37] 3.375 3.425 3.475 3.525 3.575 3.625 3.675 3.725 3.775 3.825 3.875 3.925
## [49] 3.975 4.025 4.075 4.125 4.175 4.225 4.275 4.325 4.375 4.425 4.475 4.525
## [61] 4.575 4.625 4.675 4.725 4.775 4.825 4.875 4.925 4.975 5.025 5.075 5.125
seq(17) # same as 1:17, or even better seq_len(17)
##  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17

즉, seq(from = 1, to = 1, by = ((to - from)/(length.out - 1)), length.out = NULL)μ—μ„œ μ˜λ―Έν•˜λŠ” 것은
from, to: sequence의 μ‹œμž‘κ³Ό 끝
by: sequence의 μ¦κ°€λŸ‰
length.out: sequence의 길이

κ·ΈλŸ¬λ―€λ‘œ μ•„λž˜μ™€ 같은 seqλ₯Ό λ§Œλ“€ 수 μžˆλ‹€.

seq(0, 100, by = 20)
## [1]   0  20  40  60  80 100

4주차 과제

Q1. p112 ν˜Όμžμ„œ 해보기

install.packages("ggplot2")
install.packages("dplyr")
library(ggplot2)
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
mpg.new <- mpg
mpg.new  <- rename(mpg.new, city = cty, highway = hwy)
head(mpg.new)
## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans    drv    city highway fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>    <chr> <int>   <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5) f        18      29 p     compa~
## 2 audi         a4      1.8  1999     4 manual(~ f        21      29 p     compa~
## 3 audi         a4      2    2008     4 manual(~ f        20      31 p     compa~
## 4 audi         a4      2    2008     4 auto(av) f        21      30 p     compa~
## 5 audi         a4      2.8  1999     6 auto(l5) f        16      26 p     compa~
## 6 audi         a4      2.8  1999     6 manual(~ f        18      26 p     compa~

Q2. p123 뢄석 도전!

midwest <- as.data.frame(ggplot2::midwest)
dim(midwest) #ν–‰, μ—΄ 개수 νŒŒμ•…ν•˜κΈ°
## [1] 437  28
str(midwest) #데이터 ν”„λ ˆμž„ ꡬ쑰 확인
## 'data.frame':    437 obs. of  28 variables:
##  $ PID                 : int  561 562 563 564 565 566 567 568 569 570 ...
##  $ county              : chr  "ADAMS" "ALEXANDER" "BOND" "BOONE" ...
##  $ state               : chr  "IL" "IL" "IL" "IL" ...
##  $ area                : num  0.052 0.014 0.022 0.017 0.018 0.05 0.017 0.027 0.024 0.058 ...
##  $ poptotal            : int  66090 10626 14991 30806 5836 35688 5322 16805 13437 173025 ...
##  $ popdensity          : num  1271 759 681 1812 324 ...
##  $ popwhite            : int  63917 7054 14477 29344 5264 35157 5298 16519 13384 146506 ...
##  $ popblack            : int  1702 3496 429 127 547 50 1 111 16 16559 ...
##  $ popamerindian       : int  98 19 35 46 14 65 8 30 8 331 ...
##  $ popasian            : int  249 48 16 150 5 195 15 61 23 8033 ...
##  $ popother            : int  124 9 34 1139 6 221 0 84 6 1596 ...
##  $ percwhite           : num  96.7 66.4 96.6 95.3 90.2 ...
##  $ percblack           : num  2.575 32.9 2.862 0.412 9.373 ...
##  $ percamerindan       : num  0.148 0.179 0.233 0.149 0.24 ...
##  $ percasian           : num  0.3768 0.4517 0.1067 0.4869 0.0857 ...
##  $ percother           : num  0.1876 0.0847 0.2268 3.6973 0.1028 ...
##  $ popadults           : int  43298 6724 9669 19272 3979 23444 3583 11323 8825 95971 ...
##  $ perchsd             : num  75.1 59.7 69.3 75.5 68.9 ...
##  $ percollege          : num  19.6 11.2 17 17.3 14.5 ...
##  $ percprof            : num  4.36 2.87 4.49 4.2 3.37 ...
##  $ poppovertyknown     : int  63628 10529 14235 30337 4815 35107 5241 16455 13081 154934 ...
##  $ percpovertyknown    : num  96.3 99.1 95 98.5 82.5 ...
##  $ percbelowpoverty    : num  13.15 32.24 12.07 7.21 13.52 ...
##  $ percchildbelowpovert: num  18 45.8 14 11.2 13 ...
##  $ percadultpoverty    : num  11.01 27.39 10.85 5.54 11.14 ...
##  $ percelderlypoverty  : num  12.44 25.23 12.7 6.22 19.2 ...
##  $ inmetro             : int  0 0 0 1 0 0 0 0 0 1 ...
##  $ category            : chr  "AAR" "LHR" "AAR" "ALU" ...
summary(midwest) #데이터 ν”„λ ˆμž„ μš”μ•½
##       PID          county             state                area        
##  Min.   : 561   Length:437         Length:437         Min.   :0.00500  
##  1st Qu.: 670   Class :character   Class :character   1st Qu.:0.02400  
##  Median :1221   Mode  :character   Mode  :character   Median :0.03000  
##  Mean   :1437                                         Mean   :0.03317  
##  3rd Qu.:2059                                         3rd Qu.:0.03800  
##  Max.   :3052                                         Max.   :0.11000  
##     poptotal         popdensity          popwhite          popblack      
##  Min.   :   1701   Min.   :   85.05   Min.   :    416   Min.   :      0  
##  1st Qu.:  18840   1st Qu.:  622.41   1st Qu.:  18630   1st Qu.:     29  
##  Median :  35324   Median : 1156.21   Median :  34471   Median :    201  
##  Mean   :  96130   Mean   : 3097.74   Mean   :  81840   Mean   :  11024  
##  3rd Qu.:  75651   3rd Qu.: 2330.00   3rd Qu.:  72968   3rd Qu.:   1291  
##  Max.   :5105067   Max.   :88018.40   Max.   :3204947   Max.   :1317147  
##  popamerindian        popasian         popother        percwhite    
##  Min.   :    4.0   Min.   :     0   Min.   :     0   Min.   :10.69  
##  1st Qu.:   44.0   1st Qu.:    35   1st Qu.:    20   1st Qu.:94.89  
##  Median :   94.0   Median :   102   Median :    66   Median :98.03  
##  Mean   :  343.1   Mean   :  1310   Mean   :  1613   Mean   :95.56  
##  3rd Qu.:  288.0   3rd Qu.:   401   3rd Qu.:   345   3rd Qu.:99.07  
##  Max.   :10289.0   Max.   :188565   Max.   :384119   Max.   :99.82  
##    percblack       percamerindan        percasian        percother      
##  Min.   : 0.0000   Min.   : 0.05623   Min.   :0.0000   Min.   :0.00000  
##  1st Qu.: 0.1157   1st Qu.: 0.15793   1st Qu.:0.1737   1st Qu.:0.09102  
##  Median : 0.5390   Median : 0.21502   Median :0.2972   Median :0.17844  
##  Mean   : 2.6763   Mean   : 0.79894   Mean   :0.4872   Mean   :0.47906  
##  3rd Qu.: 2.6014   3rd Qu.: 0.38362   3rd Qu.:0.5212   3rd Qu.:0.48050  
##  Max.   :40.2100   Max.   :89.17738   Max.   :5.0705   Max.   :7.52427  
##    popadults          perchsd        percollege        percprof      
##  Min.   :   1287   Min.   :46.91   Min.   : 7.336   Min.   : 0.5203  
##  1st Qu.:  12271   1st Qu.:71.33   1st Qu.:14.114   1st Qu.: 2.9980  
##  Median :  22188   Median :74.25   Median :16.798   Median : 3.8142  
##  Mean   :  60973   Mean   :73.97   Mean   :18.273   Mean   : 4.4473  
##  3rd Qu.:  47541   3rd Qu.:77.20   3rd Qu.:20.550   3rd Qu.: 4.9493  
##  Max.   :3291995   Max.   :88.90   Max.   :48.079   Max.   :20.7913  
##  poppovertyknown   percpovertyknown percbelowpoverty percchildbelowpovert
##  Min.   :   1696   Min.   :80.90    Min.   : 2.180   Min.   : 1.919      
##  1st Qu.:  18364   1st Qu.:96.89    1st Qu.: 9.199   1st Qu.:11.624      
##  Median :  33788   Median :98.17    Median :11.822   Median :15.270      
##  Mean   :  93642   Mean   :97.11    Mean   :12.511   Mean   :16.447      
##  3rd Qu.:  72840   3rd Qu.:98.60    3rd Qu.:15.133   3rd Qu.:20.352      
##  Max.   :5023523   Max.   :99.86    Max.   :48.691   Max.   :64.308      
##  percadultpoverty percelderlypoverty    inmetro         category        
##  Min.   : 1.938   Min.   : 3.547     Min.   :0.0000   Length:437        
##  1st Qu.: 7.668   1st Qu.: 8.912     1st Qu.:0.0000   Class :character  
##  Median :10.008   Median :10.869     Median :0.0000   Mode  :character  
##  Mean   :10.919   Mean   :11.389     Mean   :0.3432                     
##  3rd Qu.:13.182   3rd Qu.:13.412     3rd Qu.:1.0000                     
##  Max.   :43.312   Max.   :31.162     Max.   :1.0000
midwest.new <- midwest #데이터 ν”„λ ˆμž„ 사본 μ œμž‘ ν›„ ν–‰ 이름 μž¬μ„€μ • 
midwest.new  <- rename(midwest.new, total = poptotal, asian = popasian) 
midwest.new$prop_asian <- (midwest.new$asian/midwest.new$total)*100 #νŒŒμƒλ³€μˆ˜ μ œμž‘
hist(midwest.new$prop_asian) #νžˆμŠ€ν† κ·Έλž¨ μ œμž‘

mean(midwest.new$prop_asian) # 평균 κ΅¬ν•˜κΈ° 
## [1] 0.4872462
midwest.new$mean_asian <- ifelse(midwest.new$prop_asian > mean(midwest.new$prop_asian), "large", "small") # 쑰건문 ν™œμš© νŒŒμƒλ³€μˆ˜ μ œμž‘ 
table(midwest.new$mean_asian) # λΉˆλ„ν‘œ μ œμž‘
## 
## large small 
##   119   318
qplot(midwest.new$mean_asian) # λ§‰λŒ€κ·Έλž˜ν”„ μ œμž‘

Q3. mlu 데이터 λΆ„μ„ν•˜κΈ°

install.packages("readxl")
library(readxl)

setwd("C:\\Users\\user\\Desktop\\R μ‹€μŠ΅μš©")
mlu_data <- read_excel("mlu.xlsx")
mlu_data.ori <- mlu_data #1. μΉ΄ν”Όλ³Έ μ œμž‘  

table(mlu_data$age) #2. age 칼럼의 μš”μΈ 개수 μ•Œμ•„λ³΄κΈ°  
## 
## A0 A1 A2 
## 12 11 12
mlu_data <- rename(mlu_data, utterances = utterances_mlu, words = words_mlu) #3. 칼럼 이름 λ°”κΎΈκΈ°  

mlu_data$mlu <- mlu_data$words/mlu_data$utterances #4. νŒŒμƒλ³€μˆ˜ λ§Œλ“€κΈ°  

summary(mlu_data$mlu) #5.mlu 칼럼의 평균 및 quartile κ°’ κ΅¬ν•˜κΈ°  
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.730   2.447   2.745   2.696   2.916   3.476
mlu_data$grade <- ifelse(mlu_data$mlu < 2.447, "D", 
                         ifelse(mlu_data$mlu < 2.745, "C", 
                                ifelse(mlu_data$mlu < 2.916, "B", "A"))) #6-1. quartile 값을 κΈ°μ€€μœΌλ‘œ ifelseλ₯Ό μ‚¬μš©ν•΄μ„œ grade νŒŒμƒ λ³€μˆ˜ λ§Œλ“€κΈ°   

mlu_data$grade2 <- ntile(mlu_data$mlu, 4) #6-2. λ‹€λ₯Έ λ°©μ‹μœΌλ‘œ dplyr νŒ¨ν‚€μ§€μ— μžˆλŠ” ntile ν•¨μˆ˜λ₯Ό μ΄μš©ν•΄μ„œ 4λ“±λΆ„μœΌλ‘œ grouping ν›„ grade2 νŒŒμƒ λ³€μˆ˜ λ§Œλ“€κΈ°  

qplot(data = mlu_data, x = age, y = mlu) #8. age와 mluμ‚¬μ΄μ˜ 관계λ₯Ό κ·Έλž˜ν”„λ‘œ 그렀보기

7주차 과제

Q1. p133 ν˜Όμžμ„œ 해보기

1-1.

mpg %>% filter(displ <= 4) -> mpg_lower4 #λ°°κΈ°λŸ‰μ΄ 4 μ΄ν•˜μΈ μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©)
mpg[mpg$displ <= 4,] -> mpg_lower4 #λ°°κΈ°λŸ‰μ΄ 4 μ΄ν•˜μΈ μ—΄ μΆ”μΆœ (filterν•¨μˆ˜ μ‚¬μš©X)
mean(mpg_lower4$hwy)
## [1] 25.96319
mpg %>% filter(displ >= 5) -> mpg_upper5 #λ°°κΈ°λŸ‰μ΄ 5 이상인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©)
mpg[mpg$displ >= 5,] -> mpg_upper5 #λ°°κΈ°λŸ‰μ΄ 5 이상인 μ—΄ μΆ”μΆœ (filterν•¨μˆ˜ μ‚¬μš©X)
mean(mpg_upper5$hwy)
## [1] 18.07895
ifelse(mpg$displ <= 4, "lower4", ifelse(mpg$displ >= 5, "upper5", NA)) -> mpg$grade
# λ°°κΈ°λŸ‰μ΄ 5 이상인 μžλ™μ°¨λ³΄λ‹€ 4 이상인 μžλ™μ°¨μ˜ μ—°λΉ„κ°€ ν‰κ· μ μœΌλ‘œ 더 λ†’λ‹€.

1-2.(νŒŒμƒλ³€μˆ˜μ™€ tapplyν•¨μˆ˜λ₯Ό μ΄μš©ν•΄μ„œ 평균 κ΅¬ν•˜κΈ°)

ifelse(mpg$displ <= 4, "lower4", ifelse(mpg$displ >= 5, "upper5", NA)) -> mpg$grade
tapply(mpg$hwy, mpg$grade, mean)
##   lower4   upper5 
## 25.96319 18.07895
# λ°°κΈ°λŸ‰μ΄ 5 이상인 μžλ™μ°¨λ³΄λ‹€ 4 이상인 μžλ™μ°¨μ˜ μ—°λΉ„κ°€ ν‰κ· μ μœΌλ‘œ 더 λ†’λ‹€.

2-1.

mpg %>% filter(manufacturer == "audi") -> mpg_audi #μ œμ‘°μ‚¬κ°€ audi인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©)
mpg[mpg$manufacturer == "audi",] -> mpg_audi #μ œμ‘°μ‚¬κ°€ audi인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©X)
mean(mpg_audi$cty)
## [1] 17.61111
mpg %>% filter(manufacturer == "toyota") -> mpg_toyota #μ œμ‘°μ‚¬κ°€ honda인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©)
mpg[mpg$manufacturer == "toyota",] -> mpg_toyota #μ œμ‘°μ‚¬κ°€ honda인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©X)
mean(mpg_toyota$cty)
## [1] 18.52941
# μ œμ‘°νšŒμ‚¬κ°€ audi인 μžλ™μ°¨λ³΄λ‹€ toyota인 μžλ™μ°¨μ˜ λ„μ‹œ μ—°λΉ„κ°€ ν‰κ· μ μœΌλ‘œ 더 λ†’λ‹€.

2-2.(tapplyν•¨μˆ˜λ₯Ό μ΄μš©ν•΄μ„œ 평균 κ΅¬ν•˜κΈ°)

tapply(mpg$cty, mpg$manufacturer, mean)
##       audi  chevrolet      dodge       ford      honda    hyundai       jeep 
##   17.61111   15.00000   13.13514   14.00000   24.44444   18.64286   13.50000 
## land rover    lincoln    mercury     nissan    pontiac     subaru     toyota 
##   11.50000   11.33333   13.25000   18.07692   17.00000   19.28571   18.52941 
## volkswagen 
##   20.92593
# μ œμ‘°νšŒμ‚¬κ°€ audi인 μžλ™μ°¨λ³΄λ‹€ toyota인 μžλ™μ°¨μ˜ λ„μ‹œ μ—°λΉ„κ°€ ν‰κ· μ μœΌλ‘œ 더 λ†’λ‹€.
mpg %>% filter(manufacturer %in% c("chevrolet", "ford", "honda")) -> mpg_ma #μ œμ‘°μ‚¬κ°€ chevorlet, ford, honda인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©)
mpg[mpg$manufacturer %in% c("chevrolet", "ford", "honda"),] -> mpg_ma #μ œμ‘°μ‚¬κ°€ chevorlet, ford, honda인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©X)
mean(mpg_ma$hwy)
## [1] 22.50943

Q2. p138 ν˜Όμžμ„œ 해보기

mpg %>% select(class, cty) -> mpg_cc #class, cty ν–‰ μΆ”μΆœ(selectν•¨μˆ˜ μ‚¬μš©)
mpg[,c("class","cty")] -> mpg_cc #class, cty ν–‰ μΆ”μΆœ(selectν•¨μˆ˜ μ‚¬μš©X)
head(mpg_cc)
## # A tibble: 6 x 2
##   class     cty
##   <chr>   <int>
## 1 compact    18
## 2 compact    21
## 3 compact    20
## 4 compact    21
## 5 compact    16
## 6 compact    18

2-1.

mpg_cc %>% filter(class == "suv") -> mpg_suv #μžλ™μ°¨ μ’…λ₯˜κ°€ suv인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©) 
mpg_cc[mpg$class == "suv",] -> mpg_suv #μžλ™μ°¨ μ’…λ₯˜κ°€ suv인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©X)
mpg %>% select(class, cty) %>% filter(class == "suv") -> mpg_suv #class, cty ν–‰κ³Ό μžλ™μ°¨ μ’…λ₯˜κ°€ suv인 μ—΄ μΆ”μΆœ(select,filterν•¨μˆ˜ μ‚¬μš©) 
mpg[mpg$class == "suv",c("class","cty")] -> mpg_suv #class, cty ν–‰κ³Ό μžλ™μ°¨ μ’…λ₯˜κ°€ suv인 μ—΄ μΆ”μΆœ(select,filterν•¨μˆ˜ μ‚¬μš©X) 
mean(mpg_suv$cty)
## [1] 13.5
mpg_cc %>% filter(class == "compact") -> mpg_compact #μžλ™μ°¨ μ’…λ₯˜κ°€ suv인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©) 
mpg_cc[mpg$class == "compact",] -> mpg_compact #μžλ™μ°¨ μ’…λ₯˜κ°€ suv인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©X)
mpg %>% select(class, cty) %>% filter(class == "compact") -> mpg_compact #class, cty ν–‰κ³Ό μžλ™μ°¨ μ’…λ₯˜κ°€ suv인 μ—΄ μΆ”μΆœ(select,filterν•¨μˆ˜ μ‚¬μš©) 
mpg[mpg$class == "compact",c("class","cty")] -> mpg_compact #class, cty ν–‰κ³Ό μžλ™μ°¨ μ’…λ₯˜κ°€ suv인 μ—΄ μΆ”μΆœ(select,filterν•¨μˆ˜ μ‚¬μš©X) 
mean(mpg_compact$cty)
## [1] 20.12766
#μžλ™μ°¨ μ’…λ₯˜κ°€ suv인 μžλ™μ°¨λ³΄λ‹€ compact인 μžλ™μ°¨μ˜ λ„μ‹œμ—°λΉ„κ°€ 더 λ†’λ‹€

2-2. (tapplyν•¨μˆ˜λ₯Ό μ΄μš©ν•΄μ„œ 평균 κ΅¬ν•˜κΈ°)

tapply(mpg$cty, mpg$class, mean)
##    2seater    compact    midsize    minivan     pickup subcompact        suv 
##   15.40000   20.12766   18.75610   15.81818   13.00000   20.37143   13.50000
#μžλ™μ°¨ μ’…λ₯˜κ°€ suv인 μžλ™μ°¨λ³΄λ‹€ compact인 μžλ™μ°¨μ˜ λ„μ‹œμ—°λΉ„κ°€ 더 λ†’λ‹€

Q3. p141 ν˜Όμžμ„œ 해보기

mpg %>% filter(manufacturer == "audi") -> mpg_audi #μ œμ‘°μ‚¬κ°€ audi인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©)
mpg_audi %>% arrange(desc(hwy)) %>% head(5) #ordering ν›„ μ—°λΉ„κ°€ 1~5μœ„ μ•ˆμ— λ“œλŠ” μžλ™μ°¨ 좜λ ₯
## # A tibble: 5 x 12
##   manufacturer model displ  year   cyl trans drv     cty   hwy fl    class grade
##   <chr>        <chr> <dbl> <int> <int> <chr> <chr> <int> <int> <chr> <chr> <chr>
## 1 audi         a4      2    2008     4 manu~ f        20    31 p     comp~ lowe~
## 2 audi         a4      2    2008     4 auto~ f        21    30 p     comp~ lowe~
## 3 audi         a4      1.8  1999     4 auto~ f        18    29 p     comp~ lowe~
## 4 audi         a4      1.8  1999     4 manu~ f        21    29 p     comp~ lowe~
## 5 audi         a4 q~   2    2008     4 manu~ 4        20    28 p     comp~ lowe~
mpg[mpg$manufacturer == "audi",] -> mpg_audi #μ œμ‘°μ‚¬κ°€ audi인 μ—΄ μΆ”μΆœ(filterν•¨μˆ˜ μ‚¬μš©X)
head(mpg_audi[order(-mpg_audi$hwy),],5) #μ œμ‘°μ‚¬κ°€ audi인 μ—΄ μΆ”μΆœ(arrangeν•¨μˆ˜ μ‚¬μš©X)
## # A tibble: 5 x 12
##   manufacturer model displ  year   cyl trans drv     cty   hwy fl    class grade
##   <chr>        <chr> <dbl> <int> <int> <chr> <chr> <int> <int> <chr> <chr> <chr>
## 1 audi         a4      2    2008     4 manu~ f        20    31 p     comp~ lowe~
## 2 audi         a4      2    2008     4 auto~ f        21    30 p     comp~ lowe~
## 3 audi         a4      1.8  1999     4 auto~ f        18    29 p     comp~ lowe~
## 4 audi         a4      1.8  1999     4 manu~ f        21    29 p     comp~ lowe~
## 5 audi         a4 q~   2    2008     4 manu~ 4        20    28 p     comp~ lowe~

Q4. p144 ν˜Όμžμ„œ 해보기

mpg.new2 <- mpg
mpg.new2 %>% mutate(total = cty + hwy) -> mpg.new2 #cty와 hwy값을 ν•©μΉœ νŒŒμƒλ³€μˆ˜ 생성
mpg.new2 %>% mutate(mean = total/2) -> mpg.new2 #cty와 hwyκ°’μ˜ 평균값을 κ΅¬ν•œ νŒŒμƒλ³€μˆ˜ 생성
mpg.new2 %>% arrange(desc(mean)) %>% head(3)  #ordering ν›„ 평균 μ—°λΉ„κ°€ 1~3μœ„ μ•ˆμ— λ“œλŠ” μžλ™μ°¨ 좜λ ₯
## # A tibble: 3 x 14
##   manufacturer model displ  year   cyl trans drv     cty   hwy fl    class grade
##   <chr>        <chr> <dbl> <int> <int> <chr> <chr> <int> <int> <chr> <chr> <chr>
## 1 volkswagen   new ~   1.9  1999     4 manu~ f        35    44 d     subc~ lowe~
## 2 volkswagen   jetta   1.9  1999     4 manu~ f        33    44 d     comp~ lowe~
## 3 volkswagen   new ~   1.9  1999     4 auto~ f        29    41 d     subc~ lowe~
## # ... with 2 more variables: total <int>, mean <dbl>
mpg %>% mutate(mean = (cty + hwy)/2) %>% arrange(desc(mean)) %>% head(3)
## # A tibble: 3 x 13
##   manufacturer model displ  year   cyl trans drv     cty   hwy fl    class grade
##   <chr>        <chr> <dbl> <int> <int> <chr> <chr> <int> <int> <chr> <chr> <chr>
## 1 volkswagen   new ~   1.9  1999     4 manu~ f        35    44 d     subc~ lowe~
## 2 volkswagen   jetta   1.9  1999     4 manu~ f        33    44 d     comp~ lowe~
## 3 volkswagen   new ~   1.9  1999     4 auto~ f        29    41 d     subc~ lowe~
## # ... with 1 more variable: mean <dbl>

Q5. p150 ν˜Όμžμ„œ 해보기

mpg %>% group_by(class) %>% summarise(mean_cty = mean(cty)) #class별 λ„μ‹œ μ—°λΉ„μ˜ 평균 κ΅¬ν•˜κΈ°(group_by, summariseμ‚¬μš©)
## `summarise()` ungrouping output (override with `.groups` argument)
## # A tibble: 7 x 2
##   class      mean_cty
##   <chr>         <dbl>
## 1 2seater        15.4
## 2 compact        20.1
## 3 midsize        18.8
## 4 minivan        15.8
## 5 pickup         13  
## 6 subcompact     20.4
## 7 suv            13.5
tapply(mpg$cty, mpg$class, mean) #class별 λ„μ‹œ μ—°λΉ„μ˜ 평균 κ΅¬ν•˜κΈ°(group_by, summariseμ‚¬μš©X)
##    2seater    compact    midsize    minivan     pickup subcompact        suv 
##   15.40000   20.12766   18.75610   15.81818   13.00000   20.37143   13.50000
mpg %>% group_by(class) %>% 
  summarise(mean_cty = mean(cty)) %>% 
  arrange(desc(mean_cty)) #class별 λ„μ‹œ μ—°λΉ„μ˜ 평균을 κ΅¬ν•œ ν›„ μ •λ ¬ν•˜κΈ°
## `summarise()` ungrouping output (override with `.groups` argument)
## # A tibble: 7 x 2
##   class      mean_cty
##   <chr>         <dbl>
## 1 subcompact     20.4
## 2 compact        20.1
## 3 midsize        18.8
## 4 minivan        15.8
## 5 2seater        15.4
## 6 suv            13.5
## 7 pickup         13
mpg %>% group_by(class) %>% 
  summarise(mean_cty = mean(cty)) %>% 
  arrange(desc(mean_cty)) %>% 
  head(3) #class별 λ„μ‹œ μ—°λΉ„μ˜ 평균을 κ΅¬ν•œ ν›„ μ •λ ¬ ν›„ 1~3μœ„ 좜λ ₯ 
## `summarise()` ungrouping output (override with `.groups` argument)
## # A tibble: 3 x 2
##   class      mean_cty
##   <chr>         <dbl>
## 1 subcompact     20.4
## 2 compact        20.1
## 3 midsize        18.8
mpg %>% filter(class == "compact") %>% group_by(manufacturer) %>% summarise(compact_n = n()) %>% arrange(desc(compact_n))
## `summarise()` ungrouping output (override with `.groups` argument)
## # A tibble: 5 x 2
##   manufacturer compact_n
##   <chr>            <int>
## 1 audi                15
## 2 volkswagen          14
## 3 toyota              12
## 4 subaru               4
## 5 nissan               2

Q6. mlu 데이터 λΆ„μ„ν•˜κΈ°

mlu_data2 <- mlu_data.ori  #1. μΉ΄ν”Όλ³Έ μ œμž‘  
dim(mlu_data2 %>% filter(utterances_mlu <= 500)) #2. 주어진 λ…ΉμŒ μ‹œκ°„ 쀑 500λ¬Έμž₯ μ΄ν•˜λ‘œ λ°œν™”ν•œ μ–‘μœ‘μžλŠ” 5λͺ…이닀. 
## [1] 5 8
mlu_data2 %>% select(-DurationTime, -DurationSec) -> mlu_data2 #3. 뢄석에 ν•„μš”μ—†λŠ” DurationTime, DurationSec column 제거
mlu_data2 %>% mutate(mlu = words_mlu/utterances_mlu) %>% #4-1. mlu νŒŒμƒλ³€μˆ˜ μΆ”κ°€
  group_by(age) %>% summarise(mean_mlu = mean(mlu)) #4-2. λ‚˜μ΄λ³„ mlu 평균 κ΅¬ν•˜κΈ° 
## `summarise()` ungrouping output (override with `.groups` argument)
## # A tibble: 3 x 2
##   age   mean_mlu
##   <chr>    <dbl>
## 1 A0        2.50
## 2 A1        2.59
## 3 A2        2.99
mlu_data2 %>% mutate(TTR = Token_freq/Types_freq) %>% #5-1. TTR νŒŒμƒλ³€μˆ˜ μΆ”κ°€
  group_by(age) %>% summarise(mean_TTR = mean(TTR)) #5-2. λ‚˜μ΄λ³„ TTR 평균 κ΅¬ν•˜κΈ°
## `summarise()` ungrouping output (override with `.groups` argument)
## # A tibble: 3 x 2
##   age   mean_TTR
##   <chr>    <dbl>
## 1 A0        2.41
## 2 A1        2.74
## 3 A2        2.66

9주차 과제

Q1. p156 ν˜Όμžμ„œ 해보기

fuel <- data.frame(fl = c("c", "d", "e", "p", "r"), 
                   price_fl = c(2.35, 2.38, 2.11, 2.76, 2.22), 
                   stringsAsFactors = F)

#1
mpg.new3 <- mpg #μΉ΄ν”Όλ³Έ μ œμž‘
mpg.fuel <- left_join(mpg.new3, fuel, by = "fl") #데이터 μΆ”κ°€

#2
mpg.fuel %>% select(model, fl, price_fl) %>% head(5) 
## # A tibble: 5 x 3
##   model fl    price_fl
##   <chr> <chr>    <dbl>
## 1 a4    p         2.76
## 2 a4    p         2.76
## 3 a4    p         2.76
## 4 a4    p         2.76
## 5 a4    p         2.76

Q2. p160 뢄석 도전

#1
midwest.new2 <- midwest #μΉ΄ν”Όλ³Έ μ œμž‘
midwest.new2 <- midwest.new2 %>% mutate(prop_popchild = (poptotal-popadults)/poptotal*100) 

#2
midwest.new2 %>% arrange(desc(prop_popchild)) %>% select(county, prop_popchild) %>% head(5)
##      county prop_popchild
## 1  ISABELLA      51.50117
## 2 MENOMINEE      50.59126
## 3    ATHENS      49.32073
## 4   MECOSTA      49.05918
## 5    MONROE      47.35818
#3
midwest.new2 <- midwest.new2 %>% 
  mutate(grade_popchild = ifelse(prop_popchild >= 40, "large", 
                                 ifelse(prop_popchild >= 30, "middle", "small")))
midwest.new2 %>% 
  group_by(grade_popchild) %>% 
  summarise(n_county = n())
## `summarise()` ungrouping output (override with `.groups` argument)
## # A tibble: 3 x 2
##   grade_popchild n_county
##   <chr>             <int>
## 1 large                32
## 2 middle              396
## 3 small                 9
#4
midwest.new2 <- midwest.new2 %>% mutate(prop_popasian = popasian/poptotal*100) 
midwest.new2 %>% select(state, county, prop_popasian) %>% arrange(prop_popasian) %>% head(10) 
##    state    county prop_popasian
## 1     WI MENOMINEE    0.00000000
## 2     IN    BENTON    0.01059210
## 3     IN   CARROLL    0.01594981
## 4     OH    VINTON    0.02703190
## 5     WI      IRON    0.03250447
## 6     IL     SCOTT    0.05315379
## 7     IN      CLAY    0.06071645
## 8     MI    OSCODA    0.06375925
## 9     OH     PERRY    0.06654625
## 10    IL     PIATT    0.07074865

Q3. p170 ν˜Όμžμ„œ 해보기

mpg <- as.data.frame(ggplot2::mpg)
mpg.new4 <- mpg
mpg.new4[c(65, 124, 131, 153, 212), "hwy"] <- NA

#1
table(is.na(mpg.new4$drv))
## 
## FALSE 
##   234
table(is.na(mpg.new4$hwy))
## 
## FALSE  TRUE 
##   229     5
#2
mpg.new4 %>% filter(!is.na(hwy)) %>% group_by(drv) %>% summarise(mean_hwy = mean(hwy))
## `summarise()` ungrouping output (override with `.groups` argument)
## # A tibble: 3 x 2
##   drv   mean_hwy
##   <chr>    <dbl>
## 1 4         19.2
## 2 f         28.2
## 3 r         21

Q4. p178 ν˜Όμžμ„œ 해보기

#1
mpg <- as.data.frame(ggplot2::mpg)
mpg[c(10, 14, 58, 93), "drv"] <- "k"
mpg[c(29, 43, 129, 203), "cty"] <- c(3, 4, 39, 42)
ifelse(mpg$drv %in% "k", NA, mpg$drv) -> mpg$drv #μ΄μƒμΉ˜λ₯Ό NA둜 λ³€ν™˜
table(is.na(mpg$drv)) #μ΄μƒμΉ˜κ°€ NA둜 λ³€ν™˜λ˜μ—ˆλŠ” 지 확인
## 
## FALSE  TRUE 
##   230     4
#2
str(mpg)
## 'data.frame':    234 obs. of  11 variables:
##  $ manufacturer: chr  "audi" "audi" "audi" "audi" ...
##  $ model       : chr  "a4" "a4" "a4" "a4" ...
##  $ displ       : num  1.8 1.8 2 2 2.8 2.8 3.1 1.8 1.8 2 ...
##  $ year        : int  1999 1999 2008 2008 1999 1999 2008 1999 1999 2008 ...
##  $ cyl         : int  4 4 4 4 6 6 6 4 4 4 ...
##  $ trans       : chr  "auto(l5)" "manual(m5)" "manual(m6)" "auto(av)" ...
##  $ drv         : chr  "f" "f" "f" "f" ...
##  $ cty         : num  18 21 20 21 16 18 18 18 16 20 ...
##  $ hwy         : int  29 29 31 30 26 26 27 26 25 28 ...
##  $ fl          : chr  "p" "p" "p" "p" ...
##  $ class       : chr  "compact" "compact" "compact" "compact" ...
as.numeric(mpg$cty) -> mpg$cty
boxplot(mpg$cty)$stat

##      [,1]
## [1,]    9
## [2,]   14
## [3,]   17
## [4,]   19
## [5,]   26
ifelse(mpg$cty < 9 | mpg$cty > 26, NA, mpg$cty) -> mpg$cty 
boxplot(mpg$cty)

#3
mpg %>% filter(!is.na(drv), !is.na(cty)) %>% group_by(drv) %>% summarise(mean_cty = mean(cty))
## `summarise()` ungrouping output (override with `.groups` argument)
## # A tibble: 3 x 2
##   drv   mean_cty
##   <chr>    <dbl>
## 1 4         14.2
## 2 f         19.5
## 3 r         14.0

Q5. p188 ν˜Όμžμ„œ 해보기

#1
mpg <- as.data.frame(ggplot2::mpg)
qplot(data = mpg, x = cty, y = hwy) + geom_point()

#2
qplot(data = midwest, x = poptotal, y = popasian) + geom_point() + xlim(0, 500000) + ylim(0, 10000)
## Warning: Removed 15 rows containing missing values (geom_point).

## Warning: Removed 15 rows containing missing values (geom_point).

Q6. p193 ν˜Όμžμ„œ 해보기

#1
mpg %>% filter(class == "suv") %>%  group_by(manufacturer) %>% summarise(mean_cty = mean(cty)) %>% arrange(desc(mean_cty)) %>% head(5) -> mpg_upper5
## `summarise()` ungrouping output (override with `.groups` argument)
ggplot(data = mpg_upper5, aes(x = reorder(manufacturer, -mean_cty), y = mean_cty)) + geom_col()

#2
ggplot(data = mpg, aes(x = class)) + geom_bar()

Q7. p195 ν˜Όμžμ„œ 해보기

#1
ggplot(data = economics, aes(x = date, y = psavert)) + geom_line()

Q8. p198 ν˜Όμžμ„œ 해보기

mpg %>% filter(class == c("subcompact", "compact", "suv")) -> mpg.scs
ggplot(data = mpg.scs, aes(x = class, y = cty)) + geom_boxplot()

11주차 과제

ν•œκ΅­ 볡지 νŒ¨λ„ 데이터 뢄석 μ€€λΉ„ν•˜κΈ°

install.packages("foreign")
library(foreign)
library(dplyr)
library(ggplot2)
library(readxl)
setwd("C:\\Users\\user\\Desktop\\R μ‹€μŠ΅μš©")
raw_welfare <- read.spss(file = "Koweps_hpc10_2015_beta1.sav", to.data.frame = T)
## Warning in read.spss(file = "Koweps_hpc10_2015_beta1.sav", to.data.frame = T):
## Koweps_hpc10_2015_beta1.sav: Compression bias (0) is not the usual value of 100
welfare <- raw_welfare

dim(welfare)
## [1] 16664   957
welfare <- rename(welfare, 
                  sex = h10_g3, #성별
                  birth = h10_g4, #νƒœμ–΄λ‚œ 연도 
                  marriage = h10_g10, #혼인 μƒνƒœ
                  religion = h10_g11, #쒅ꡐ
                  income = p1002_8aq1, #μ›”κΈ‰
                  code_job = h10_eco9, #직업 μ½”λ“œ
                  code_region = h10_reg7) #지역 μ½”λ“œ

성별에 λ”°λ₯Έ μ›”κΈ‰ 차이

#성별 λ³€μˆ˜ κ²€ν† 
class(welfare$sex) 
## [1] "numeric"
table(welfare$sex)
## 
##    1    2 
## 7578 9086
ifelse(welfare$sex == 1, "male", "female") -> welfare$sex
qplot(welfare$sex)

#μ›”κΈ‰ λ³€μˆ˜ κ²€ν† 
class(welfare$income)
## [1] "numeric"
summary(welfare$income)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##     0.0   122.0   192.5   241.6   316.6  2400.0   12030
qplot(welfare$income) + xlim(0, 1000)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 12051 rows containing non-finite values (stat_bin).
## Warning: Removed 2 rows containing missing values (geom_bar).

#결츑치 μ œκ±°ν•˜κΈ° 
ifelse(welfare$income %in% c(0, 9999), NA, welfare$income) -> welfare$income
table(is.na(welfare$income))
## 
## FALSE  TRUE 
##  4620 12044
#성별에 λ”°λ₯Έ μ›”κΈ‰ 차이 λΆ„μ„ν•˜κΈ° 
welfare %>% filter(!is.na(income)) %>% group_by(sex) %>% summarise(mean_income = mean(income)) -> sex_income
## `summarise()` ungrouping output (override with `.groups` argument)
sex_income
## # A tibble: 2 x 2
##   sex    mean_income
##   <chr>        <dbl>
## 1 female        163.
## 2 male          312.
ggplot(data = sex_income, aes(x = sex, y = mean_income)) + geom_col()

λ‚˜μ΄ 및 μ—°λ ΉλŒ€μ— λ”°λ₯Έ μ›”κΈ‰ 차이

#λ‚˜μ΄ λ³€μˆ˜ κ²€ν† 
class(welfare$birth) 
## [1] "numeric"
summary(welfare$birth)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1907    1946    1966    1968    1988    2014
qplot(welfare$birth)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

welfare$age <- 2015 - welfare$birth + 1 #λ‚˜μ΄ νŒŒμƒλ³€μˆ˜ λ§Œλ“€κΈ°
summary(welfare$age)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    2.00   28.00   50.00   48.43   70.00  109.00
qplot(welfare$age)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

#λ‚˜μ΄μ— λ”°λ₯Έ μ›”κΈ‰ 차이 λΆ„μ„ν•˜κΈ° 
welfare %>% filter(!is.na(income)) %>% group_by(age) %>% summarise(mean_income = mean(income)) -> age_income
## `summarise()` ungrouping output (override with `.groups` argument)
age_income
## # A tibble: 69 x 2
##      age mean_income
##    <dbl>       <dbl>
##  1    20        121.
##  2    21        106.
##  3    22        130.
##  4    23        142.
##  5    24        134.
##  6    25        145.
##  7    26        158.
##  8    27        188.
##  9    28        205.
## 10    29        189.
## # ... with 59 more rows
ggplot(data = age_income, aes(x = age, y = mean_income)) + geom_line()

#μ—°λ ΉλŒ€μ— λ”°λ₯Έ μ›”κΈ‰ 차이 λΆ„μ„ν•˜κΈ° 
welfare$ageg <- ifelse(welfare$age < 30, "young", 
                       ifelse(welfare$age <= 59, "middle", "old")) #μ—°λ ΉλŒ€ νŒŒμƒλ³€μˆ˜ λ§Œλ“€κΈ°
table(welfare$ageg)
## 
## middle    old  young 
##   6049   6281   4334
qplot(welfare$ageg)

welfare %>% filter(!is.na(income)) %>% group_by(ageg) %>% summarise(mean_income = mean(income)) -> ageg_income
## `summarise()` ungrouping output (override with `.groups` argument)
ageg_income
## # A tibble: 3 x 2
##   ageg   mean_income
##   <chr>        <dbl>
## 1 middle        282.
## 2 old           125.
## 3 young         164.
ggplot(data = ageg_income, aes(x = ageg, y = mean_income)) + geom_col() + scale_x_discrete(limit = c("young", "middle", "old"))

성별 및 μ—°λ ΉλŒ€, λ‚˜μ΄μ— λ”°λ₯Έ μ›”κΈ‰ 차이

# 성별 및 μ—°λ ΉλŒ€μ— λ”°λ₯Έ μ›”κΈ‰ 차이
welfare %>% filter(!is.na(income)) %>% group_by(ageg, sex) %>% summarise(mean_income = mean(income)) -> sex_income
## `summarise()` regrouping output by 'ageg' (override with `.groups` argument)
sex_income
## # A tibble: 6 x 3
## # Groups:   ageg [3]
##   ageg   sex    mean_income
##   <chr>  <chr>        <dbl>
## 1 middle female       188. 
## 2 middle male         353. 
## 3 old    female        81.5
## 4 old    male         174. 
## 5 young  female       160. 
## 6 young  male         171.
ggplot(data = sex_income, aes(x = ageg, y = mean_income, fill = sex)) + geom_col(position = "dodge") + scale_x_discrete(limit = c("young", "middle", "old"))

# 성별 및 λ‚˜μ΄μ— λ”°λ₯Έ μ›”κΈ‰ 차이
welfare %>% filter(!is.na(income)) %>% group_by(age, sex) %>% summarise(mean_income = mean(income)) -> sex_age
## `summarise()` regrouping output by 'age' (override with `.groups` argument)
sex_income
## # A tibble: 6 x 3
## # Groups:   ageg [3]
##   ageg   sex    mean_income
##   <chr>  <chr>        <dbl>
## 1 middle female       188. 
## 2 middle male         353. 
## 3 old    female        81.5
## 4 old    male         174. 
## 5 young  female       160. 
## 6 young  male         171.
ggplot(data = sex_age, aes(x = age, y = mean_income, col = sex)) + geom_line()

직업별 μ›”κΈ‰ 차이

class(welfare$code_job)
## [1] "numeric"
table(welfare$code_job)
## 
##  111  120  131  132  133  134  135  139  141  149  151  152  153  159  211  212 
##    2   16   10   11    9    3    7   10   35   20   26   18   15   16    8    4 
##  213  221  222  223  224  231  232  233  234  235  236  237  239  241  242  243 
##    3   17   31   12    4   41    5    3    6   48   14    2   29   12    4   63 
##  244  245  246  247  248  251  252  253  254  259  261  271  272  273  274  281 
##    4   33   59   77   38   14  111   24   67  109    4   15   11    4   36   17 
##  283  284  285  286  289  311  312  313  314  320  330  391  392  399  411  412 
##    8   10   26   16    5  140  260  220   84   75   15    4   13   87   47   12 
##  421  422  423  429  431  432  441  442  510  521  522  530  611  612  613  620 
##  124   71    5   14   20   33  154  197  192  353    5  106 1320   11   40    2 
##  630  710  721  722  730  741  742  743  751  752  753  761  762  771  772  773 
##   20   29   30   22   16   27    3   34   34    5   49   69   27   11   61   86 
##  774  780  791  792  799  811  812  819  821  822  823  831  832  841  842  843 
##    7   17    5   21   45   16    1    6    9    9   23    5   17   32   10    4 
##  851  852  853  854  855  861  862  863  864  871  873  874  875  876  881  882 
##   19   13    7   33    9    3   14   17   31    2  257   34   37    2    2    3 
##  891  892  899  910  921  922  930  941  942  951  952  953  991  992  999 1011 
##    8   19   16  102   31   74  289  325   99  125  122   73   45   12  141    2 
## 1012 
##   17
library(readxl)

#데이터 μ „μ²˜λ¦¬
setwd("C:\\Users\\user\\Desktop\\R μ‹€μŠ΅μš©")
list_job <- read_excel("Koweps_Codebook.xlsx", col_names = T, sheet = 2)
head(list_job)
## # A tibble: 6 x 2
##   code_job job                                
##      <dbl> <chr>                              
## 1      111 μ˜νšŒμ˜μ› κ³ μœ„κ³΅λ¬΄μ› 및 κ³΅κ³΅λ‹¨μ²΄μž„μ›
## 2      112 κΈ°μ—…κ³ μœ„μž„μ›                       
## 3      120 ν–‰μ • 및 κ²½μ˜μ§€μ› κ΄€λ¦¬μž            
## 4      131 연ꡬ ꡐ윑 및 법λ₯  κ΄€λ ¨ κ΄€λ¦¬μž      
## 5      132 λ³΄ν—˜ 및 금육 κ΄€λ¦¬μž                
## 6      133 보건 및 μ‚¬νšŒλ³΅μ§€ κ΄€λ ¨ κ΄€λ¦¬μž
dim(list_job)
## [1] 149   2
welfare <- left_join(welfare, list_job, id = "code_job")
## Joining, by = "code_job"
welfare %>% filter(!is.na(code_job)) %>% select(code_job, job) %>% head(10)
##    code_job                                job
## 1       942                   경비원 및 κ²€ν‘œμ›
## 2       762                             전기곡
## 3       530 λ°©λ¬Έ 노점 및 톡신 판맀 κ΄€λ ¨ μ’…μ‚¬μž
## 4       999        기타 μ„œλΉ„μŠ€κ΄€λ ¨ λ‹¨μˆœ 쒅사원
## 5       312                    κ²½μ˜κ΄€λ ¨ 사무원
## 6       254             문리 기술 및 예λŠ₯ 강사
## 7       510                        μ˜μ—… μ’…μ‚¬μž
## 8       530 λ°©λ¬Έ 노점 및 톡신 판맀 κ΄€λ ¨ μ’…μ‚¬μž
## 9       286   슀포츠 및 λ ˆν¬λ ˆμ΄μ…˜ κ΄€λ ¨ μ „λ¬Έκ°€
## 10      521                   맀μž₯ 판맀 μ’…μ‚¬μž
#직업별 μƒμœ„ 10μœ„, ν•˜μœ„ 10μœ„μ˜ μ›”κΈ‰ 평균 κ΅¬ν•˜κΈ° 
job_income <- welfare %>% filter(!is.na(job) & !is.na(income)) %>% group_by(job) %>% summarise(mean_income = mean(income)) %>% arrange(desc(mean_income))
## `summarise()` ungrouping output (override with `.groups` argument)
top10 <- job_income %>% head(10)
bottom10 <- job_income %>% tail(10)
ggplot(data = top10, aes(x = reorder(job, mean_income), y = mean_income)) + geom_col() + coord_flip()

ggplot(data = bottom10, aes(x = reorder(job, -mean_income), y = mean_income)) + geom_col() + coord_flip() + ylim(0, 850)

성별 직업 λΉˆλ„

male_job <- welfare %>% filter(!is.na(job) & sex == "male") %>% group_by(job) %>% summarise(n = n()) %>% arrange(desc(n))
## `summarise()` ungrouping output (override with `.groups` argument)
male_top10 <- male_job %>% head(10)

female_job <- welfare %>% filter(!is.na(job) & sex == "female") %>% group_by(job) %>% summarise(n = n()) %>% arrange(desc(n))
## `summarise()` ungrouping output (override with `.groups` argument)
female_top10 <- female_job %>% head(10)

ggplot(data = male_top10, aes(x = reorder(job, n), y = n)) + geom_col() + coord_flip()

ggplot(data = female_top10, aes(x = reorder(job, n), y = n)) + geom_col() + coord_flip()

쒅ꡐ μœ λ¬΄μ— λ”°λ₯Έ 이혼율

class(welfare$religion)
## [1] "numeric"
table(welfare$religion)
## 
##    1    2 
## 8047 8617
class(welfare$marriage)
## [1] "numeric"
table(welfare$marriage)
## 
##    0    1    2    3    4    5    6 
## 2861 8431 2117  712   84 2433   26
#데이터 μ „μ²˜λ¦¬
welfare$religion <- ifelse(welfare$religion == 1, "yes", "no")
qplot(welfare$religion)

welfare$group_marriage <- ifelse(welfare$marriage == 1, "marriage", 
                                ifelse(welfare$marriage == 3, "divorce", NA))
table(welfare$group_marriage)
## 
##  divorce marriage 
##      712     8431
qplot(welfare$group_marriage)

religion_marriage <- welfare %>% filter(!is.na(group_marriage)) %>% group_by(religion, group_marriage) %>% summarise(n = n()) %>% mutate(tot_group = sum(n)) %>% mutate(pct = round(n/tot_group*100, 1))
## `summarise()` regrouping output by 'religion' (override with `.groups` argument)
divorce <- religion_marriage %>% filter(group_marriage == "divorce") %>% select(religion, pct) 

#κ·Έλž˜ν”„ 그리기 
ggplot(data = divorce, aes(x = religion, y = pct)) + geom_col()

#μ—°λ ΉλŒ€λ³„ 이혼율 뢄석
ageg_marriage <- welfare %>% filter(!is.na(group_marriage)) %>% group_by(ageg, group_marriage) %>% summarise(n = n()) %>% mutate(tot_group = sum(n)) %>% mutate(pct = round(n/tot_group*100, 1))
## `summarise()` regrouping output by 'ageg' (override with `.groups` argument)
ageg_divorce <- ageg_marriage %>% filter(group_marriage == "divorce") %>% select(ageg, pct)
ggplot(data = ageg_divorce, aes(x = ageg, y = pct)) + geom_col()

#μ—°λ ΉλŒ€ 및 쒅ꡐ μœ λ¬΄μ— λ”°λ₯Έ 이혼율 뢄석
ageg_religion_marriage <- welfare %>% filter(!is.na(group_marriage)) %>% group_by(ageg, religion, group_marriage) %>% summarise(n = n()) %>% mutate(tot_group = sum(n)) %>% mutate(pct = round(n/tot_group*100, 1))
## `summarise()` regrouping output by 'ageg', 'religion' (override with `.groups` argument)
ageg_religion_divorce <- ageg_religion_marriage %>% filter(group_marriage == "divorce") %>% select(ageg, religion, pct)
ggplot(data = ageg_religion_divorce, aes(x = ageg, y = pct, fill = religion)) + geom_col(position = "dodge")

지역별 μ—°λ ΉλŒ€ λΉ„μœ¨

class(welfare$code_region)
## [1] "numeric"
table(welfare$code_region)
## 
##    1    2    3    4    5    6    7 
## 2486 3711 2785 2036 1467 1257 2922
#데이터 μ „μ²˜λ¦¬
list_region <- data.frame(code_region = c(1:7), 
                          region = c("μ„œμšΈ", "μˆ˜λ„κΆŒ(인천/κ²½κΈ°)", "λΆ€μ‚°/경남/μšΈμ‚°", "λŒ€κ΅¬/경뢁", "λŒ€μ „/좩남", "강원/좩뢁", "κ΄‘μ£Ό/전남/전뢁/μ œμ£Όλ„"))
welfare <- left_join(welfare, list_region, by = "code_region")

region_ageg <- welfare %>% group_by(region, ageg) %>% summarise(n = n()) %>% mutate(tot_group = sum(n)) %>% mutate(pct = round(n/tot_group*100, 2))
## `summarise()` regrouping output by 'region' (override with `.groups` argument)
#κ·Έλž˜ν”„ 그리기
ggplot(data = region_ageg, aes(x = region, y = pct, fill = ageg)) + geom_col() + coord_flip()

#λ…Έλ…„μΈ΅ λΉ„μœ¨μ΄ 높은 순으둜 μ •λ ¬ν•˜κΈ°
list_order_old <- region_ageg %>% filter(ageg == "old") %>% arrange(pct) 
order <- list_order_old$region
ggplot(data = region_ageg, aes(x = region, y = pct, fill = ageg)) + geom_col() + coord_flip() + scale_x_discrete(limits = order)

#μ—°λ ΉλŒ€ 순으둜 λ§‰λŒ€ 색깔 λ‚˜μ—΄ν•˜κΈ°
region_ageg$ageg <- factor(region_ageg$ageg, level = c("old", "middle", "young"))
ggplot(data = region_ageg, aes(x = region, y = pct, fill = ageg)) + geom_col() + coord_flip() + scale_x_discrete(limits = order)

Vowel and coda duration as a function of speaking rate

setwd("C:\\Users\\user\\Desktop\\R μ‹€μŠ΅μš©")
coda <- read.delim(file = "all_data.txt") 
V_speed <- coda %>% filter(phoneme == c("AE1", "EH1", "IH1")) %>% group_by(voice, speed) %>% summarise(mean_duration = mean(duration)) 
## `summarise()` regrouping output by 'voice' (override with `.groups` argument)
coda_speed <- coda %>% filter(phoneme == c("K", "G")) %>% group_by(voice, speed) %>% summarise(mean_duration = mean(duration)) 
## `summarise()` regrouping output by 'voice' (override with `.groups` argument)
ggplot(data = V_speed, aes(x = speed, y = mean_duration, fill = voice)) + geom_col(position = "dodge") #λͺ¨μŒμ˜ 길이

ggplot(data = coda_speed, aes(x = speed, y = mean_duration, fill = voice)) + geom_col(position = "dodge") #coda의 길이

Vowel and coda duration as a function of sentence position

V_pos <- coda %>% filter(phoneme == c("AE1", "EH1", "IH1")) %>% group_by(position, voice) %>% summarise(mean_duration = mean(duration)) 
## `summarise()` regrouping output by 'position' (override with `.groups` argument)
coda_pos <- coda %>% filter(phoneme == c("K", "G")) %>% group_by(position, voice) %>% summarise(mean_duration = mean(duration)) 
## `summarise()` regrouping output by 'position' (override with `.groups` argument)
ggplot(data = V_pos, aes(x = position, y = mean_duration, fill = voice)) + geom_col(position = "dodge") #λͺ¨μŒμ˜ 길이

ggplot(data = coda_pos, aes(x = position, y = mean_duration, fill = voice)) + geom_col(position = "dodge") #coda의 길이

Vowel and coda duration as a function of vowel height

V_height <- coda %>% filter(phoneme == c("AE1", "EH1", "IH1")) %>% group_by(height, voice) %>% summarise(mean_duration = mean(duration)) 
## `summarise()` regrouping output by 'height' (override with `.groups` argument)
coda_height <- coda %>% filter(phoneme == c("K", "G")) %>% group_by(height, voice) %>% summarise(mean_duration = mean(duration)) 
## `summarise()` regrouping output by 'height' (override with `.groups` argument)
ggplot(data = V_height, aes(x = height, y = mean_duration, fill = voice)) + geom_col(position = "dodge") #λͺ¨μŒμ˜ 길이

ggplot(data = coda_height, aes(x = height, y = mean_duration, fill = voice)) + geom_col(position = "dodge") #coda의 길이

V-to-C ratio under varying speaking rate in CVC words ending in [-voice] and [+voice] stops

V_speed <- coda %>% filter(phoneme == c("AE1", "EH1", "IH1")) %>% group_by(voice, speed) %>% summarise(V_mean_duration = mean(duration))
## `summarise()` regrouping output by 'voice' (override with `.groups` argument)
coda_speed <- coda %>% filter(phoneme == c("K", "G")) %>% group_by(voice, speed) %>% summarise(coda_mean_duration = mean(duration))
## `summarise()` regrouping output by 'voice' (override with `.groups` argument)
VC_ratio <- left_join(V_speed, coda_speed, by = c("voice", "speed"))
VC_ratio <- VC_ratio %>% mutate(VC_ratio = V_mean_duration/coda_mean_duration) 
ggplot(data = VC_ratio, aes(x = voice, y = VC_ratio, fill = speed)) + geom_col(position = "dodge")

## 12주차 과제

install.packages("stringr")
install.packages("wordcloud")
library(KoNLP)
## Checking user defined dictionary!
library(stringr)
library(dplyr)
library(wordcloud)
## Loading required package: RColorBrewer
library(RColorBrewer)

ꡭ정원 νŠΈμœ— ν…μŠ€νŠΈ λ§ˆμ΄λ‹

#데이터 μ •μ œν•˜κΈ°
setwd("C:\\Users\\user\\Desktop\\R μ‹€μŠ΅μš©")
twitter <- read.csv("twitter.csv", header = T, stringsAsFactors = F, fileEncoding = "UTF-8")
twitter <- rename(twitter, no = 번호, id = 계정이름, date = μž‘μ„±μΌ, tw = λ‚΄μš©)
twitter$tw <- str_replace_all(twitter$tw, "\\W", " ")

#κ°€μž₯ 많이 μ‚¬μš©λœ 단어 μ•Œμ•„λ³΄κΈ° 
nouns <- extractNoun(twitter$tw)
wordcount <- table(unlist(nouns)) 
df_word <- as.data.frame(wordcount, stringsAsFactors = F)
df_word <- rename(df_word, word = Var1, freq = Freq)
df_word <- filter(df_word, nchar(word) >= 2)
top_20 <- df_word %>% arrange(desc(freq)) %>% head(20)

#단어 λΉˆλ„ κ·Έλž˜ν”„ λ§Œλ“€κΈ°
order <- arrange(top_20, freq)$word
ggplot(data = top_20, aes(x = word, y = freq)) + ylim(0, 2500) + geom_col() + coord_flip() + scale_x_discrete(limit = order) + geom_text(aes(label = freq), hjust = -0.3)

#wordcloud λ§Œλ“€κΈ°
pal <- brewer.pal(8, "Dark2")
set.seed(1234)
wordcloud(words = df_word$word,
          freq = df_word$freq, 
          min.freq = 10, 
          max.words = 200, 
          random.order = F, 
          rot.per = .1, 
          scale = c(6, 0.2), 
          colors = pal)

pal <- brewer.pal(9, "Blues")[5:9]
set.seed(1234)
wordcloud(words = df_word$word,
          freq = df_word$freq, 
          min.freq = 10, 
          max.words = 200, 
          random.order = F, 
          rot.per = .1, 
          scale = c(6, 0.2), 
          colors = pal)