엑셀파일 불러들여 데이터 살펴보고 과제 수행하기
지난 시간에 엑셀파일을 불러들여오는 명령어를 배웠는데, 이번에는 주어진 엑셀파일(mlu.xls)를 그 명령어를 이용해서 불러들인 다음 오늘 배운 내용들을 수행해봅니다. 데이터는 엑셀파일의 두번째 sheet에 있으므로 명령어를 잘 활용하여 불러들이기 바랍니다.
Q1. 데이터를 불러들여 mlu_data로 지정한 다음 카피본을 만든다.
library(readxl)
mlu <- read_excel("mlu.xlsx")
mlu_data <- as.data.frame(mlu)
summary(mlu_data)
## File age utterances_mlu words_mlu
## Length:35 Length:35 Min. :323.0 Min. : 813
## Class :character Class :character 1st Qu.:561.0 1st Qu.:1368
## Mode :character Mode :character Median :621.0 Median :1716
## Mean :631.8 Mean :1710
## 3rd Qu.:716.0 3rd Qu.:2060
## Max. :890.0 Max. :2766
##
## DurationTime DurationSec Types_freq Token_freq
## Min. :1899-12-31 00:08:47 Min. : 527.0 Min. : 378.0 Min. : 832
## 1st Qu.:1899-12-31 00:15:17 1st Qu.: 940.5 1st Qu.: 567.5 1st Qu.:1446
## Median :1899-12-31 00:17:39 Median :1060.5 Median : 694.0 Median :1798
## Mean :1899-12-31 00:17:57 Mean :1088.1 Mean : 754.8 Mean :1778
## 3rd Qu.:1899-12-31 00:20:45 3rd Qu.:1245.5 3rd Qu.: 775.5 3rd Qu.:2134
## Max. :1899-12-31 00:29:22 Max. :1762.0 Max. :4014.0 Max. :2827
## NA's :1
Q2. age칼럼에는 몇개의 요인이 있는가?
class(mlu_data$age)
## [1] "character"
length(mlu_data$age)
## [1] 35
table(mlu_data$age)
##
## A0 A1 A2
## 12 11 12
Q3. utterances_mlu를 utterances로 words_mlu를 words로 이름을 바꾸라.
library("dplyr")
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
mlu_data <- dplyr::rename(mlu_data, utterances= utterances_mlu)
mlu_data <- dplyr::rename(mlu_data, words = words_mlu)
summary(mlu_data)
## File age utterances words
## Length:35 Length:35 Min. :323.0 Min. : 813
## Class :character Class :character 1st Qu.:561.0 1st Qu.:1368
## Mode :character Mode :character Median :621.0 Median :1716
## Mean :631.8 Mean :1710
## 3rd Qu.:716.0 3rd Qu.:2060
## Max. :890.0 Max. :2766
##
## DurationTime DurationSec Types_freq Token_freq
## Min. :1899-12-31 00:08:47 Min. : 527.0 Min. : 378.0 Min. : 832
## 1st Qu.:1899-12-31 00:15:17 1st Qu.: 940.5 1st Qu.: 567.5 1st Qu.:1446
## Median :1899-12-31 00:17:39 Median :1060.5 Median : 694.0 Median :1798
## Mean :1899-12-31 00:17:57 Mean :1088.1 Mean : 754.8 Mean :1778
## 3rd Qu.:1899-12-31 00:20:45 3rd Qu.:1245.5 3rd Qu.: 775.5 3rd Qu.:2134
## Max. :1899-12-31 00:29:22 Max. :1762.0 Max. :4014.0 Max. :2827
## NA's :1
Q4. 각 utterance에 평균 몇개의 단어가 들어있는지를 계산해서 mlu라는 파생변수를 생성하라
library("dplyr")
mlu_data$mlu <- (mlu_data$words/mlu_data$utterances)
Q5. summary 명령을 이용하여 mlu의 평균 및 quartile값을 파악하라.
library("dplyr")
summary(mlu_data$mlu)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.730 2.447 2.745 2.696 2.916 3.476
Q6. mlu값을 4개의 등급으로 나누어 가장 문장 길이가 긴 그룹을 A, 그다음 순서대로 B, C, D로 구분하여 grade칼럼을 생성하라.
Min. 1st Qu. Median Mean 3rd Qu. Max.
1.730 2.447 2.745 2.696 2.916 3.476
library("dplyr")
mlu_data$grade <- ifelse(mlu_data$mlu >= 2.916, "A",
ifelse(mlu_data$mlu >= 2.745, "B",
ifelse(mlu_data$mlu >= 2.447, "C","D")))
table(mlu_data$grade)
##
## A B C D
## 9 9 8 9
Q7. age와 mlu사이의 빈도분포를 table명령어를 이용하여 구하라.
summary(table(mlu_data$age, mlu_data$mlu))
## Number of cases in table: 35
## Number of factors: 2
## Test for independence of all factors:
## Chisq = 70, df = 68, p-value = 0.4102
## Chi-squared approximation may be incorrect
Q8. qplot을 이용하여 각 나이 그룹을 X축으로 하여 mlu값의 분포를 그래프로 그려라.
library("ggplot2")
table(mlu_data$age, mlu_data$mlu)
##
## 1.72978723404255 2.05936920222635 2.13109243697479 2.20781527531083
## A0 1 1 1 1
## A1 0 0 0 0
## A2 0 0 0 0
##
## 2.20955882352941 2.2791519434629 2.35725938009788 2.40298507462687
## A0 0 1 0 0
## A1 1 0 1 1
## A2 0 0 0 0
##
## 2.42857142857143 2.46551724137931 2.54157303370787 2.61985815602837
## A0 0 0 0 1
## A1 1 0 1 0
## A2 0 1 0 0
##
## 2.63072776280323 2.63979848866499 2.66183574879227 2.68727272727273
## A0 1 0 0 0
## A1 0 1 1 0
## A2 0 0 0 1
##
## 2.69240196078431 2.74540682414698 2.75541795665635 2.79177057356608
## A0 0 0 0 1
## A1 1 1 0 0
## A2 0 0 1 0
##
## 2.80441176470588 2.81474820143885 2.81914893617021 2.8353982300885
## A0 0 0 1 1
## A1 1 0 0 0
## A2 0 1 0 0
##
## 2.84929577464789 2.90047393364929 2.93213296398892 2.97038327526132
## A0 0 1 0 1
## A1 0 0 0 0
## A2 1 0 1 0
##
## 2.98074074074074 3.02551020408163 3.02862254025045 3.18450704225352
## A0 0 0 0 0
## A1 0 0 1 0
## A2 1 1 0 1
##
## 3.34057971014493 3.35387323943662 3.47609147609148
## A0 0 0 0
## A1 0 0 0
## A2 1 1 1
qplot(mlu_data$age, mlu_data$mlu)
