ch5

library(dplyr)

## 
## 다음의 패키지를 부착합니다: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)

1. 변수명 바꾸기

Q1

mpg <- as.data.frame(ggplot2::mpg)
mpgnew <- mpg

Q2

rename(mpgnew, city = cty) -> mpgnew
rename(mpgnew, highway = hwy) -> mpgnew

Q3

head(mpgnew)

##   manufacturer model displ year cyl      trans drv city highway fl   class
## 1         audi    a4   1.8 1999   4   auto(l5)   f   18      29  p compact
## 2         audi    a4   1.8 1999   4 manual(m5)   f   21      29  p compact
## 3         audi    a4   2.0 2008   4 manual(m6)   f   20      31  p compact
## 4         audi    a4   2.0 2008   4   auto(av)   f   21      30  p compact
## 5         audi    a4   2.8 1999   6   auto(l5)   f   16      26  p compact
## 6         audi    a4   2.8 1999   6 manual(m5)   f   18      26  p compact

2. 교과서 123쪽 문제 수행하기

Q1

midwest <- as.data.frame(ggplot2::midwest)

head(midwest)
tail(midwest)
View(midwest)
dim(midwest)
str(midwest)
summary(midwest)

Q2

midwest <- rename(midwest, total = poptotal, asian = popasian)

Q3

midwest$percentage <- midwest$asian/midwest$total * 100
hist(midwest$percentage)

Q4

mean(midwest$percentage)

## [1] 0.4872462

midwest$abc <- ifelse(midwest$percentage > 0.4872462, "large", "small")

Q5

table(midwest$abc)

## 
## large small 
##   119   318

qplot(midwest$abc)

## Warning: `qplot()` was deprecated in ggplot2 3.4.0.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

3. 엑셀파일 불러들여 데이터 살펴보고 과제 수행하기

library(readxl)

Q1

setwd("C:/Users/최창정/Documents")
mlu_data <- readxl::read_excel("mlu.xlsx", sheet = 2)

mlu_data -> mlu_data2

Q2

unique_age <- unique(mlu_data2$age)
length(unique_age)

## [1] 3

3개의 요인이 있음

Q3

mlu_data2 <- rename(mlu_data2, utterances = utterances_mlu)
mlu_data2 <- rename(mlu_data2, words = words_mlu)
mlu_data2

## # A tibble: 35 × 8
##    File    age   utterances words DurationTime DurationSec Types_freq Token_freq
##    <chr>   <chr>      <dbl> <dbl> <chr>              <dbl>      <dbl>      <dbl>
##  1 13_A0P… A0           566  1290 "00:17:35"          1055        580       1346
##  2 21_A0P… A0           565  1602 "00:20:44"          1244        737       1606
##  3 27_A0P… A0           470   813 "00:12:07"           727        378        832
##  4 28_A0P… A0           371   976 "00:11:53"           713        419        979
##  5 29_A0P… A0           802  2239 "00:24:45"          1485        814       2253
##  6 2_A0P0… A0           563  1243 "00:12:06\""          NA        425       1263
##  7 30_A0P… A0           574  1705 "00:21:56"          1316        828       1712
##  8 31_A0P… A0           539  1110 "00:10:54"           654        426       1124
##  9 35_A0P… A0           705  1847 "00:20:46"          1246        622       1860
## 10 36_A0P… A0           752  2120 "00:29:22"          1762       1014       2599
## # ℹ 25 more rows

Q4

mlu_data2$mlu <- mlu_data2$words/mlu_data2$utterances

Q5

summary(mlu_data2$mlu)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.730   2.447   2.745   2.696   2.916   3.476

Q6

mlu_data2$grade <- ifelse(mlu_data2$mlu >=3.476, "A", ifelse(mlu_data2$mlu >=2.916, "B", ifelse(mlu_data2$mlu >= 2.745, "C", "D")))
head(mlu_data2$grade)

## [1] "D" "C" "D" "D" "C" "D"

Q8

qplot(mlu_data2$age,mlu_data2$mlu)