#2023.07.20
getwd()
## [1] "C:/data"
rm(list = ls())
setwd('c:/data')
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(caret)
## 필요한 패키지를 로딩중입니다: ggplot2
## 필요한 패키지를 로딩중입니다: lattice
# 단순선형회귀분석
# BM(건강한 자기 관리)
# HAPINESS(행복도)
# 건강한 자기 관리를 잘할수록 행복도 증가하는가??
df<-read.csv("Data1.csv")
glimpse(df)
## Rows: 1,925
## Columns: 26
## $ Q1 <int> 4, 4, 4, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, …
## $ Q2 <int> 4, 4, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 2, 2, …
## $ Q3 <int> 2, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 4, 4, 3, 2, 3, …
## $ Q4 <int> 3, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 4, 4, 2, 4, 4, 4, 2, 2, 4, …
## $ Q5 <int> 4, 4, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 4, 4, 4, 4, 3, 1, 2, …
## $ Q6 <int> 2, 3, 4, 4, 4, 4, 4, 4, 1, 2, 2, 2, 4, 4, 3, 5, 2, 2, 1, 4, …
## $ Q7 <int> 2, 2, 4, 4, 4, 4, 4, 4, 3, 4, 4, 4, 5, 4, 4, 5, 4, 3, 4, 4, …
## $ Q8 <int> 4, 4, 4, 4, 4, 4, 5, 5, 2, 2, 4, 4, 4, 4, 3, 5, 4, 2, 4, 4, …
## $ Q9 <int> 4, 4, 4, 4, 2, 4, 5, 5, 3, 4, 4, 4, 2, 2, 4, 5, 2, 4, 2, 4, …
## $ Q10 <int> 4, 4, 2, 4, 4, 4, 5, 5, 2, 4, 2, 4, 4, 4, 3, 4, 4, 3, 2, 3, …
## $ Q11 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 3, 4, 4, 4, 4, 5, 4, 3, 3, …
## $ Q12 <int> 4, 4, 4, 4, 4, 4, 5, 5, 3, 4, 4, 3, 4, 3, 3, 4, 5, 4, 4, 2, …
## $ Q13 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 4, 2, 4, 4, 4, 5, 4, 4, 4, …
## $ Q14 <int> 4, 4, 4, 4, 4, 4, 5, 5, 5, 4, 4, 4, 3, 4, 5, 4, 5, 4, 4, 4, …
## $ Q15 <int> 4, 4, 3, 4, 4, 4, 4, 2, 3, 4, 4, 3, 1, 4, 4, 4, 5, 4, 4, 4, …
## $ Q16 <int> 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, 4, 4, 4, 5, 4, 5, 4, 4, 4, …
## $ Q17 <int> 4, 3, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 3, 2, 4, 5, 4, 4, 3, 4, …
## $ Q18 <int> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, …
## $ Q19 <int> 4, 2, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 1, 4, 4, 4, 5, 4, 2, 3, …
## $ Q20 <int> 4, 1, 3, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 2, 4, 5, 5, 4, 2, 4, …
## $ Gender1 <int> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, …
## $ EDU1 <int> 1, 1, 2, 1, 2, 1, 1, 1, 4, 3, 2, 1, 1, 3, 3, 2, 1, 1, 1, 4, …
## $ BF <dbl> 3.4, 4.0, 3.6, 4.2, 4.0, 4.0, 3.6, 3.6, 3.6, 3.2, 4.0, 3.2, …
## $ BM <dbl> 3.2, 3.4, 3.6, 4.0, 3.6, 4.0, 4.6, 4.6, 2.2, 3.2, 3.2, 3.6, …
## $ Happiness <dbl> 4.0, 4.0, 3.8, 4.0, 4.0, 4.0, 4.8, 4.4, 3.8, 4.0, 4.0, 3.4, …
## $ Peace <dbl> 4.0, 2.8, 3.8, 4.0, 4.0, 4.0, 3.8, 2.4, 4.0, 3.2, 4.0, 3.9, …
# 회귀분석은 동간척도 이상어어야 함
# 독립변수 범주형이라도 회구분석이 가능하다.=더미변수
# 종속변수가 이전데이터(0,1)경우 로자스틱 회구분석이라 함
bs.out2<-lm(Happiness~BM,data=df)
summary(bs.out2)
##
## Call:
## lm(formula = Happiness ~ BM, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1591 -0.4577 0.0418 0.4409 1.9386
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.06599 0.05777 35.77 <2e-16 ***
## BM 0.49771 0.01878 26.50 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6404 on 1923 degrees of freedom
## Multiple R-squared: 0.2675, Adjusted R-squared: 0.2671
## F-statistic: 702.2 on 1 and 1923 DF, p-value: < 2.2e-16
# 건강한 자기 관리가 '1'증가할 경우 행복은 0.498증가함
# 더빈왓슨 경청
# 더빈왓슨 통계량은 0~4사이값을 갖을 수 있음.
# 0에 가까울수록 -> 양의 상관관계
# 4에 가까울수록->음의 상관관계
# 2에 가까울수록 -> 오차항의 자기 상관이 없음
#오차항 : 모집단을 알 수 없음. 실제 관측값과 모회귀선의 차이
#잔차항 : 표본을 통해 표본 회귀선을 만들고 그때 관측값 차이를
#잔차라고 하고, 잔차를 통해서 오차항의 가정조건 성립을 확인하게 된다.
#이를 잔차 분석이라고 한다.
#hAPPINESS=2.06+0.497*BM, 모델링이라 할 수 있음
library(car)
## 필요한 패키지를 로딩중입니다: carData
##
## 다음의 패키지를 부착합니다: 'car'
## The following object is masked from 'package:dplyr':
##
## recode
sreq.res1<-residuals(bs.out2)
durbinWatsonTest(sreq.res1)
## [1] 1.787942
par(mfrow=c(2,2))
plot(bs.out2)
#전자의 등분산성을 입증하기 위해서는 산점도에서
#예측값(fitted value)의 변화에 관계없이 전차(residuals)가
#분포하는 모습이 일정하여야 한다
#정규성 경정(normality )
#shapiro-wilk test(사피로 월크 검정)
shapiro.test(sreq.res1)
##
## Shapiro-Wilk normality test
##
## data: sreq.res1
## W = 0.99439, p-value = 1.148e-06
#귀무가설 : 정규분포이다.
#대립갑설 : 정규분포 아니다.
#유의확률(p-value)< 유의수준(0.05) 이므로 귀무가설 기각.
#따라서 정규분포가 아니다.
#happiness 정규성 검정을 한다.
#아라비아 숫자로 표현 하려면,
options(scipen = 999)
shapiro.test(sreq.res1)
##
## Shapiro-Wilk normality test
##
## data: sreq.res1
## W = 0.99439, p-value = 0.000001148
#위의 전차분석 결과 등분산성과 정규성을 안촉하지 못함.
#정규성을 안측하지 못하는 경우 박스콕스 변수 변환을 적용할 수 있다.
bs.out3<-lm(Happiness~BM+BF,data = df)
summary(bs.out3)
##
## Call:
## lm(formula = Happiness ~ BM + BF, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.23134 -0.40553 0.02014 0.41352 1.86210
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.60995 0.06412 25.11 <0.0000000000000002 ***
## BM 0.29054 0.02331 12.47 <0.0000000000000002 ***
## BF 0.33817 0.02435 13.89 <0.0000000000000002 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6106 on 1922 degrees of freedom
## Multiple R-squared: 0.3343, Adjusted R-squared: 0.3336
## F-statistic: 482.6 on 2 and 1922 DF, p-value: < 0.00000000000000022
library(car)
vif(bs.out3)
## BM BF
## 1.693504 1.693504
#vif 값이 모두 10보다 작으므로 두 변수는 서로 상관이 높지 않댜옹
library(caret)
idx<-createDataPartition(df$Happiness,p=0.8,list = FALSE)
train<-df[idx,]
test<-df[-idx,]
library(dplyr)
glimpse(train)
## Rows: 1,541
## Columns: 26
## $ Q1 <int> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, 5, …
## $ Q2 <int> 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 2, 3, 2, 5, …
## $ Q3 <int> 2, 4, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 4, 4, 3, 2, 3, 2, 5, …
## $ Q4 <int> 3, 4, 4, 4, 4, 4, 4, 2, 4, 4, 4, 2, 4, 4, 4, 2, 2, 4, 1, 5, …
## $ Q5 <int> 4, 4, 2, 4, 4, 4, 2, 4, 4, 2, 4, 4, 4, 4, 4, 3, 1, 2, 1, 5, …
## $ Q6 <int> 2, 3, 4, 4, 4, 4, 1, 2, 2, 2, 4, 4, 3, 5, 2, 2, 1, 2, 1, 5, …
## $ Q7 <int> 2, 2, 4, 4, 4, 4, 3, 4, 4, 4, 5, 4, 4, 5, 4, 3, 4, 4, 2, 5, …
## $ Q8 <int> 4, 4, 4, 4, 5, 5, 2, 2, 4, 4, 4, 4, 3, 5, 4, 2, 4, 4, 4, 5, …
## $ Q9 <int> 4, 4, 4, 2, 5, 5, 3, 4, 4, 4, 2, 2, 4, 5, 2, 4, 2, 4, 4, 5, …
## $ Q10 <int> 4, 4, 2, 4, 5, 5, 2, 4, 2, 4, 4, 4, 3, 4, 4, 3, 2, 3, 3, 5, …
## $ Q11 <int> 4, 4, 4, 4, 5, 5, 4, 4, 4, 3, 4, 4, 4, 4, 5, 4, 3, 4, 3, 5, …
## $ Q12 <int> 4, 4, 4, 4, 5, 5, 3, 4, 4, 3, 4, 3, 3, 4, 5, 4, 4, 3, 4, 5, …
## $ Q13 <int> 4, 4, 4, 4, 5, 5, 4, 4, 4, 4, 2, 4, 4, 4, 5, 4, 4, 3, 2, 5, …
## $ Q14 <int> 4, 4, 4, 4, 5, 5, 5, 4, 4, 4, 3, 4, 5, 4, 5, 4, 4, 4, 4, 5, …
## $ Q15 <int> 4, 4, 3, 4, 4, 2, 3, 4, 4, 3, 1, 4, 4, 4, 5, 4, 4, 3, 3, 4, …
## $ Q16 <int> 4, 4, 4, 4, 5, 2, 4, 4, 4, 4, 4, 4, 5, 4, 5, 4, 4, 4, 4, 4, …
## $ Q17 <int> 4, 3, 4, 4, 2, 2, 4, 4, 4, 4, 3, 2, 4, 5, 4, 4, 3, 2, 4, 4, …
## $ Q18 <int> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, 4, 4, …
## $ Q19 <int> 4, 2, 4, 4, 4, 2, 4, 2, 4, 4, 1, 4, 4, 4, 5, 4, 2, 3, 3, 4, …
## $ Q20 <int> 4, 1, 3, 4, 4, 2, 4, 2, 4, 4, 4, 2, 4, 5, 5, 4, 2, 3, 3, 5, …
## $ Gender1 <int> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, …
## $ EDU1 <int> 1, 1, 2, 2, 1, 1, 4, 3, 2, 1, 1, 3, 3, 2, 1, 1, 1, 3, 2, 1, …
## $ BF <dbl> 3.4, 4.0, 3.6, 4.0, 3.6, 3.6, 3.6, 3.2, 4.0, 3.2, 4.0, 3.2, …
## $ BM <dbl> 3.2, 3.4, 3.6, 3.6, 4.6, 4.6, 2.2, 3.2, 3.2, 3.6, 3.8, 3.6, …
## $ Happiness <dbl> 4.0, 4.0, 3.8, 4.0, 4.8, 4.4, 3.8, 4.0, 4.0, 3.4, 2.8, 3.8, …
## $ Peace <dbl> 4.0, 2.8, 3.8, 4.0, 3.8, 2.4, 4.0, 3.2, 4.0, 3.9, 3.2, 3.2, …
#linear regrssion model1
fit<-lm(Happiness~BM+BF+Peace, data = train)
summary(fit)
##
## Call:
## lm(formula = Happiness ~ BM + BF + Peace, data = train)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.89485 -0.33053 0.00184 0.34587 2.18890
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.51632 0.08649 5.970 0.00000000295 ***
## BM 0.22029 0.02369 9.298 < 0.0000000000000002 ***
## BF 0.25288 0.02458 10.289 < 0.0000000000000002 ***
## Peace 0.44082 0.02328 18.935 < 0.0000000000000002 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5493 on 1537 degrees of freedom
## Multiple R-squared: 0.4608, Adjusted R-squared: 0.4597
## F-statistic: 437.8 on 3 and 1537 DF, p-value: < 0.00000000000000022
#
predict(fit,newdata = test)
## 4 6 20 26 29 34 38 40
## 4.222858 4.172282 3.787181 3.738026 4.229376 3.731508 4.121706 3.731458
## 42 44 48 67 71 72 73 84
## 3.819623 2.344300 1.972285 3.932440 4.128225 4.172282 3.813204 4.865986
## 88 89 92 100 101 102 105 109
## 3.446187 4.040110 3.315435 3.938908 4.084117 3.641972 4.040060 3.793799
## 110 117 122 123 134 148 151 152
## 3.705584 4.203353 4.954101 3.441139 4.405656 3.263439 3.819623 2.652803
## 167 170 173 175 179 180 184 203
## 3.680982 3.599285 3.951995 4.222858 4.260397 3.692548 3.863755 3.591645
## 204 208 215 221 226 227 230 231
## 3.756110 2.551701 3.938958 3.705534 4.020555 4.121706 3.333420 3.661427
## 233 234 237 249 254 257 258 259
## 3.276425 2.445452 3.313965 3.377477 3.813179 4.172282 3.566893 3.320433
## 260 263 268 269 270 271 281 297
## 3.573362 3.806785 3.599285 3.496862 4.392670 3.837757 3.850843 3.384195
## 302 304 306 307 309 314 317 322
## 4.128225 3.674513 3.951995 3.881864 3.402179 3.787231 4.064662 3.384045
## 325 332 335 336 337 342 353 362
## 3.434621 3.956993 3.667945 4.216340 2.432415 3.654909 3.996052 3.579830
## 365 367 375 379 396 401 405 407
## 2.961455 3.856040 3.264909 3.503381 1.619626 3.277846 2.344300 4.007618
## 425 426 447 449 453 455 464 474
## 4.084117 3.553757 3.655058 3.743123 3.289462 3.932490 4.172282 3.604482
## 476 480 496 497 498 519 522 524
## 3.945377 3.756185 3.516367 3.207765 3.996052 4.998158 4.172282 3.932540
## 536 547 549 553 554 562 572 576
## 2.986007 3.441089 3.327051 2.445402 2.350818 4.090636 3.220702 3.258241
## 593 598 605 613 616 617 622 625
## 3.736655 3.454026 4.733663 3.586298 3.780862 4.121706 3.522836 3.340038
## 627 629 635 638 639 655 658 660
## 3.661427 4.027073 3.340038 3.101566 4.020555 3.269907 2.778557 2.533716
## 662 667 670 671 676 682 688 692
## 2.665839 2.483091 2.438934 2.659321 4.040060 3.573362 3.441239 3.824969
## 699 701 704 710 711 719 721 723
## 3.100195 4.399188 4.071280 3.908037 3.813304 3.875446 2.483041 2.621831
## 735 741 746 753 761 776 777 790
## 3.630456 4.493721 3.762678 3.654959 4.229376 2.212128 2.205609 2.910879
## 792 800 804 810 813 816 823 837
## 4.172382 3.964931 3.062656 4.128225 3.674613 2.350818 3.491765 3.062631
## 842 844 848 852 857 869 878 888
## 3.617419 3.628935 2.476473 2.754004 2.672357 3.252022 3.976497 4.040010
## 897 899 901 903 906 909 910 912
## 2.287256 2.533567 3.598064 3.402130 3.845745 3.529354 3.150821 4.310973
## 918 953 958 959 961 964 971 980
## 3.736804 2.829232 3.610901 4.247560 3.119800 3.674463 3.454026 3.951895
## 982 986 988 991 995 998 1009 1015
## 2.709946 3.359493 3.157239 3.983165 3.622567 3.258391 3.390563 3.183163
## 1029 1049 1063 1067 1080 1091 1092 1110
## 4.077649 4.172282 3.692597 3.371108 3.617519 3.283043 3.674613 3.718571
## 1111 1122 1128 1130 1133 1134 1135 1138
## 3.057459 2.532246 2.773559 3.724989 3.384195 2.659371 3.100096 3.296030
## 1145 1147 1149 1155 1160 1171 1177 1197
## 3.390563 3.295980 3.214284 3.377527 3.951945 3.667945 3.712152 3.125969
## 1206 1210 1213 1214 1215 1220 1227 1234
## 3.113132 3.535773 2.974491 3.384145 3.434721 3.467162 3.093677 3.586249
## 1236 1237 1244 1247 1249 1250 1251 1252
## 3.125969 4.040110 3.258291 3.276425 3.421634 3.371059 2.967923 3.075593
## 1254 1255 1268 1271 1272 1281 1283 1287
## 4.216390 3.289462 4.172282 2.873240 4.172282 4.108770 3.119750 3.888432
## 1301 1302 1305 1312 1321 1322 1333 1342
## 3.661477 3.529404 4.266916 3.150721 4.172282 2.753954 3.850743 3.284364
## 1349 1352 1353 1357 1359 1364 1366 1377
## 3.509849 3.756110 3.225949 3.459273 4.291568 3.824870 3.441189 3.542191
## 1383 1387 1393 1398 1402 1410 1415 1416
## 4.027073 3.183113 3.730236 3.919453 3.699066 3.333569 4.077649 3.756160
## 1422 1427 1431 1432 1434 1435 1436 1437
## 3.132637 3.516367 3.679661 3.478728 3.592817 3.353024 4.254029 3.535773
## 1442 1447 1448 1449 1452 1454 1458 1460
## 3.769097 2.344300 2.344300 4.040110 4.134743 3.176645 3.125969 3.258291
## 1468 1470 1477 1481 1482 1484 1485 1488
## 4.121906 3.573362 3.907788 3.749741 3.850843 2.798111 3.327051 3.447558
## 1492 1493 1496 1499 1506 1511 1513 1516
## 3.591446 3.837856 3.283043 3.894901 3.062556 3.201347 2.974391 3.296030
## 1520 1522 1526 1527 1528 1533 1537 1540
## 3.976497 2.993946 3.176744 2.709897 3.769147 3.238836 3.163658 4.348762
## 1547 1549 1550 1552 1553 1565 1566 1567
## 3.139155 3.661576 3.610951 3.692597 3.170176 3.233689 3.547488 4.051825
## 1568 1569 1574 1587 1593 1594 1600 1602
## 4.040159 4.247460 3.926021 4.134643 3.315385 2.167970 4.077749 3.555277
## 1603 1606 1612 1619 1620 1627 1629 1634
## 3.736705 3.057409 3.390563 3.844325 3.756210 3.844375 3.025017 3.163758
## 1637 1644 1646 1647 1658 1660 1672 1674
## 3.163758 3.813204 2.923865 4.342144 3.068975 3.068975 2.956207 3.100195
## 1675 1679 1680 1685 1695 1697 1699 1707
## 3.454076 3.723718 4.910043 3.101516 3.384095 3.681081 3.295831 3.824820
## 1710 1714 1715 1724 1729 1730 1739 1741
## 3.163658 3.982966 4.059565 2.690442 3.214284 4.077599 4.518473 3.396932
## 1743 1745 1750 1753 1755 1760 1763 1769
## 3.868877 3.170176 3.850843 4.683138 4.348512 2.956207 3.245354 3.100096
## 1776 1779 1781 1782 1792 1796 1802 1806
## 3.560425 2.949839 4.430259 3.447608 3.031485 3.295980 3.863830 4.178800
## 1812 1817 1819 1822 1847 1849 1856 1858
## 3.692747 2.236780 3.738026 2.742538 2.810998 4.632562 3.201297 3.302349
## 1864 1878 1883 1888 1893 1900 1901 1921
## 3.498134 3.093677 4.707640 3.661527 3.126119 3.945377 4.386151 2.293724
lm_p<-predict(fit,newdata = test)
round(predict(fit, newdata = test),1)
## 4 6 20 26 29 34 38 40 42 44 48 67 71 72 73 84
## 4.2 4.2 3.8 3.7 4.2 3.7 4.1 3.7 3.8 2.3 2.0 3.9 4.1 4.2 3.8 4.9
## 88 89 92 100 101 102 105 109 110 117 122 123 134 148 151 152
## 3.4 4.0 3.3 3.9 4.1 3.6 4.0 3.8 3.7 4.2 5.0 3.4 4.4 3.3 3.8 2.7
## 167 170 173 175 179 180 184 203 204 208 215 221 226 227 230 231
## 3.7 3.6 4.0 4.2 4.3 3.7 3.9 3.6 3.8 2.6 3.9 3.7 4.0 4.1 3.3 3.7
## 233 234 237 249 254 257 258 259 260 263 268 269 270 271 281 297
## 3.3 2.4 3.3 3.4 3.8 4.2 3.6 3.3 3.6 3.8 3.6 3.5 4.4 3.8 3.9 3.4
## 302 304 306 307 309 314 317 322 325 332 335 336 337 342 353 362
## 4.1 3.7 4.0 3.9 3.4 3.8 4.1 3.4 3.4 4.0 3.7 4.2 2.4 3.7 4.0 3.6
## 365 367 375 379 396 401 405 407 425 426 447 449 453 455 464 474
## 3.0 3.9 3.3 3.5 1.6 3.3 2.3 4.0 4.1 3.6 3.7 3.7 3.3 3.9 4.2 3.6
## 476 480 496 497 498 519 522 524 536 547 549 553 554 562 572 576
## 3.9 3.8 3.5 3.2 4.0 5.0 4.2 3.9 3.0 3.4 3.3 2.4 2.4 4.1 3.2 3.3
## 593 598 605 613 616 617 622 625 627 629 635 638 639 655 658 660
## 3.7 3.5 4.7 3.6 3.8 4.1 3.5 3.3 3.7 4.0 3.3 3.1 4.0 3.3 2.8 2.5
## 662 667 670 671 676 682 688 692 699 701 704 710 711 719 721 723
## 2.7 2.5 2.4 2.7 4.0 3.6 3.4 3.8 3.1 4.4 4.1 3.9 3.8 3.9 2.5 2.6
## 735 741 746 753 761 776 777 790 792 800 804 810 813 816 823 837
## 3.6 4.5 3.8 3.7 4.2 2.2 2.2 2.9 4.2 4.0 3.1 4.1 3.7 2.4 3.5 3.1
## 842 844 848 852 857 869 878 888 897 899 901 903 906 909 910 912
## 3.6 3.6 2.5 2.8 2.7 3.3 4.0 4.0 2.3 2.5 3.6 3.4 3.8 3.5 3.2 4.3
## 918 953 958 959 961 964 971 980 982 986 988 991 995 998 1009 1015
## 3.7 2.8 3.6 4.2 3.1 3.7 3.5 4.0 2.7 3.4 3.2 4.0 3.6 3.3 3.4 3.2
## 1029 1049 1063 1067 1080 1091 1092 1110 1111 1122 1128 1130 1133 1134 1135 1138
## 4.1 4.2 3.7 3.4 3.6 3.3 3.7 3.7 3.1 2.5 2.8 3.7 3.4 2.7 3.1 3.3
## 1145 1147 1149 1155 1160 1171 1177 1197 1206 1210 1213 1214 1215 1220 1227 1234
## 3.4 3.3 3.2 3.4 4.0 3.7 3.7 3.1 3.1 3.5 3.0 3.4 3.4 3.5 3.1 3.6
## 1236 1237 1244 1247 1249 1250 1251 1252 1254 1255 1268 1271 1272 1281 1283 1287
## 3.1 4.0 3.3 3.3 3.4 3.4 3.0 3.1 4.2 3.3 4.2 2.9 4.2 4.1 3.1 3.9
## 1301 1302 1305 1312 1321 1322 1333 1342 1349 1352 1353 1357 1359 1364 1366 1377
## 3.7 3.5 4.3 3.2 4.2 2.8 3.9 3.3 3.5 3.8 3.2 3.5 4.3 3.8 3.4 3.5
## 1383 1387 1393 1398 1402 1410 1415 1416 1422 1427 1431 1432 1434 1435 1436 1437
## 4.0 3.2 3.7 3.9 3.7 3.3 4.1 3.8 3.1 3.5 3.7 3.5 3.6 3.4 4.3 3.5
## 1442 1447 1448 1449 1452 1454 1458 1460 1468 1470 1477 1481 1482 1484 1485 1488
## 3.8 2.3 2.3 4.0 4.1 3.2 3.1 3.3 4.1 3.6 3.9 3.7 3.9 2.8 3.3 3.4
## 1492 1493 1496 1499 1506 1511 1513 1516 1520 1522 1526 1527 1528 1533 1537 1540
## 3.6 3.8 3.3 3.9 3.1 3.2 3.0 3.3 4.0 3.0 3.2 2.7 3.8 3.2 3.2 4.3
## 1547 1549 1550 1552 1553 1565 1566 1567 1568 1569 1574 1587 1593 1594 1600 1602
## 3.1 3.7 3.6 3.7 3.2 3.2 3.5 4.1 4.0 4.2 3.9 4.1 3.3 2.2 4.1 3.6
## 1603 1606 1612 1619 1620 1627 1629 1634 1637 1644 1646 1647 1658 1660 1672 1674
## 3.7 3.1 3.4 3.8 3.8 3.8 3.0 3.2 3.2 3.8 2.9 4.3 3.1 3.1 3.0 3.1
## 1675 1679 1680 1685 1695 1697 1699 1707 1710 1714 1715 1724 1729 1730 1739 1741
## 3.5 3.7 4.9 3.1 3.4 3.7 3.3 3.8 3.2 4.0 4.1 2.7 3.2 4.1 4.5 3.4
## 1743 1745 1750 1753 1755 1760 1763 1769 1776 1779 1781 1782 1792 1796 1802 1806
## 3.9 3.2 3.9 4.7 4.3 3.0 3.2 3.1 3.6 2.9 4.4 3.4 3.0 3.3 3.9 4.2
## 1812 1817 1819 1822 1847 1849 1856 1858 1864 1878 1883 1888 1893 1900 1901 1921
## 3.7 2.2 3.7 2.7 2.8 4.6 3.2 3.3 3.5 3.1 4.7 3.7 3.1 3.9 4.4 2.3
test$Happiness1<-round(predict(fit,newdata = test),1)
View(test)
#MSE
mean((test$Happiness-test$Happiness1)^2)
## [1] 0.280625
mean((test$Happiness-test$Happiness2)^2)
## [1] NaN
#linear regrssion mode
fit1<-lm(Happiness~BM+BF, data = train)
summary(fit1)
##
## Call:
## lm(formula = Happiness ~ BM + BF, data = train)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.22802 -0.40371 0.01684 0.42408 1.86981
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.60196 0.07189 22.28 <0.0000000000000002 ***
## BM 0.29812 0.02590 11.51 <0.0000000000000002 ***
## BF 0.33285 0.02688 12.38 <0.0000000000000002 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6099 on 1538 degrees of freedom
## Multiple R-squared: 0.335, Adjusted R-squared: 0.3341
## F-statistic: 387.4 on 2 and 1538 DF, p-value: < 0.00000000000000022
predict(fit, newdata = test)
## 4 6 20 26 29 34 38 40
## 4.222858 4.172282 3.787181 3.738026 4.229376 3.731508 4.121706 3.731458
## 42 44 48 67 71 72 73 84
## 3.819623 2.344300 1.972285 3.932440 4.128225 4.172282 3.813204 4.865986
## 88 89 92 100 101 102 105 109
## 3.446187 4.040110 3.315435 3.938908 4.084117 3.641972 4.040060 3.793799
## 110 117 122 123 134 148 151 152
## 3.705584 4.203353 4.954101 3.441139 4.405656 3.263439 3.819623 2.652803
## 167 170 173 175 179 180 184 203
## 3.680982 3.599285 3.951995 4.222858 4.260397 3.692548 3.863755 3.591645
## 204 208 215 221 226 227 230 231
## 3.756110 2.551701 3.938958 3.705534 4.020555 4.121706 3.333420 3.661427
## 233 234 237 249 254 257 258 259
## 3.276425 2.445452 3.313965 3.377477 3.813179 4.172282 3.566893 3.320433
## 260 263 268 269 270 271 281 297
## 3.573362 3.806785 3.599285 3.496862 4.392670 3.837757 3.850843 3.384195
## 302 304 306 307 309 314 317 322
## 4.128225 3.674513 3.951995 3.881864 3.402179 3.787231 4.064662 3.384045
## 325 332 335 336 337 342 353 362
## 3.434621 3.956993 3.667945 4.216340 2.432415 3.654909 3.996052 3.579830
## 365 367 375 379 396 401 405 407
## 2.961455 3.856040 3.264909 3.503381 1.619626 3.277846 2.344300 4.007618
## 425 426 447 449 453 455 464 474
## 4.084117 3.553757 3.655058 3.743123 3.289462 3.932490 4.172282 3.604482
## 476 480 496 497 498 519 522 524
## 3.945377 3.756185 3.516367 3.207765 3.996052 4.998158 4.172282 3.932540
## 536 547 549 553 554 562 572 576
## 2.986007 3.441089 3.327051 2.445402 2.350818 4.090636 3.220702 3.258241
## 593 598 605 613 616 617 622 625
## 3.736655 3.454026 4.733663 3.586298 3.780862 4.121706 3.522836 3.340038
## 627 629 635 638 639 655 658 660
## 3.661427 4.027073 3.340038 3.101566 4.020555 3.269907 2.778557 2.533716
## 662 667 670 671 676 682 688 692
## 2.665839 2.483091 2.438934 2.659321 4.040060 3.573362 3.441239 3.824969
## 699 701 704 710 711 719 721 723
## 3.100195 4.399188 4.071280 3.908037 3.813304 3.875446 2.483041 2.621831
## 735 741 746 753 761 776 777 790
## 3.630456 4.493721 3.762678 3.654959 4.229376 2.212128 2.205609 2.910879
## 792 800 804 810 813 816 823 837
## 4.172382 3.964931 3.062656 4.128225 3.674613 2.350818 3.491765 3.062631
## 842 844 848 852 857 869 878 888
## 3.617419 3.628935 2.476473 2.754004 2.672357 3.252022 3.976497 4.040010
## 897 899 901 903 906 909 910 912
## 2.287256 2.533567 3.598064 3.402130 3.845745 3.529354 3.150821 4.310973
## 918 953 958 959 961 964 971 980
## 3.736804 2.829232 3.610901 4.247560 3.119800 3.674463 3.454026 3.951895
## 982 986 988 991 995 998 1009 1015
## 2.709946 3.359493 3.157239 3.983165 3.622567 3.258391 3.390563 3.183163
## 1029 1049 1063 1067 1080 1091 1092 1110
## 4.077649 4.172282 3.692597 3.371108 3.617519 3.283043 3.674613 3.718571
## 1111 1122 1128 1130 1133 1134 1135 1138
## 3.057459 2.532246 2.773559 3.724989 3.384195 2.659371 3.100096 3.296030
## 1145 1147 1149 1155 1160 1171 1177 1197
## 3.390563 3.295980 3.214284 3.377527 3.951945 3.667945 3.712152 3.125969
## 1206 1210 1213 1214 1215 1220 1227 1234
## 3.113132 3.535773 2.974491 3.384145 3.434721 3.467162 3.093677 3.586249
## 1236 1237 1244 1247 1249 1250 1251 1252
## 3.125969 4.040110 3.258291 3.276425 3.421634 3.371059 2.967923 3.075593
## 1254 1255 1268 1271 1272 1281 1283 1287
## 4.216390 3.289462 4.172282 2.873240 4.172282 4.108770 3.119750 3.888432
## 1301 1302 1305 1312 1321 1322 1333 1342
## 3.661477 3.529404 4.266916 3.150721 4.172282 2.753954 3.850743 3.284364
## 1349 1352 1353 1357 1359 1364 1366 1377
## 3.509849 3.756110 3.225949 3.459273 4.291568 3.824870 3.441189 3.542191
## 1383 1387 1393 1398 1402 1410 1415 1416
## 4.027073 3.183113 3.730236 3.919453 3.699066 3.333569 4.077649 3.756160
## 1422 1427 1431 1432 1434 1435 1436 1437
## 3.132637 3.516367 3.679661 3.478728 3.592817 3.353024 4.254029 3.535773
## 1442 1447 1448 1449 1452 1454 1458 1460
## 3.769097 2.344300 2.344300 4.040110 4.134743 3.176645 3.125969 3.258291
## 1468 1470 1477 1481 1482 1484 1485 1488
## 4.121906 3.573362 3.907788 3.749741 3.850843 2.798111 3.327051 3.447558
## 1492 1493 1496 1499 1506 1511 1513 1516
## 3.591446 3.837856 3.283043 3.894901 3.062556 3.201347 2.974391 3.296030
## 1520 1522 1526 1527 1528 1533 1537 1540
## 3.976497 2.993946 3.176744 2.709897 3.769147 3.238836 3.163658 4.348762
## 1547 1549 1550 1552 1553 1565 1566 1567
## 3.139155 3.661576 3.610951 3.692597 3.170176 3.233689 3.547488 4.051825
## 1568 1569 1574 1587 1593 1594 1600 1602
## 4.040159 4.247460 3.926021 4.134643 3.315385 2.167970 4.077749 3.555277
## 1603 1606 1612 1619 1620 1627 1629 1634
## 3.736705 3.057409 3.390563 3.844325 3.756210 3.844375 3.025017 3.163758
## 1637 1644 1646 1647 1658 1660 1672 1674
## 3.163758 3.813204 2.923865 4.342144 3.068975 3.068975 2.956207 3.100195
## 1675 1679 1680 1685 1695 1697 1699 1707
## 3.454076 3.723718 4.910043 3.101516 3.384095 3.681081 3.295831 3.824820
## 1710 1714 1715 1724 1729 1730 1739 1741
## 3.163658 3.982966 4.059565 2.690442 3.214284 4.077599 4.518473 3.396932
## 1743 1745 1750 1753 1755 1760 1763 1769
## 3.868877 3.170176 3.850843 4.683138 4.348512 2.956207 3.245354 3.100096
## 1776 1779 1781 1782 1792 1796 1802 1806
## 3.560425 2.949839 4.430259 3.447608 3.031485 3.295980 3.863830 4.178800
## 1812 1817 1819 1822 1847 1849 1856 1858
## 3.692747 2.236780 3.738026 2.742538 2.810998 4.632562 3.201297 3.302349
## 1864 1878 1883 1888 1893 1900 1901 1921
## 3.498134 3.093677 4.707640 3.661527 3.126119 3.945377 4.386151 2.293724
lm_p<-predict(fit1, newdata = test)
round(predict(fit,newdata=test),1)
## 4 6 20 26 29 34 38 40 42 44 48 67 71 72 73 84
## 4.2 4.2 3.8 3.7 4.2 3.7 4.1 3.7 3.8 2.3 2.0 3.9 4.1 4.2 3.8 4.9
## 88 89 92 100 101 102 105 109 110 117 122 123 134 148 151 152
## 3.4 4.0 3.3 3.9 4.1 3.6 4.0 3.8 3.7 4.2 5.0 3.4 4.4 3.3 3.8 2.7
## 167 170 173 175 179 180 184 203 204 208 215 221 226 227 230 231
## 3.7 3.6 4.0 4.2 4.3 3.7 3.9 3.6 3.8 2.6 3.9 3.7 4.0 4.1 3.3 3.7
## 233 234 237 249 254 257 258 259 260 263 268 269 270 271 281 297
## 3.3 2.4 3.3 3.4 3.8 4.2 3.6 3.3 3.6 3.8 3.6 3.5 4.4 3.8 3.9 3.4
## 302 304 306 307 309 314 317 322 325 332 335 336 337 342 353 362
## 4.1 3.7 4.0 3.9 3.4 3.8 4.1 3.4 3.4 4.0 3.7 4.2 2.4 3.7 4.0 3.6
## 365 367 375 379 396 401 405 407 425 426 447 449 453 455 464 474
## 3.0 3.9 3.3 3.5 1.6 3.3 2.3 4.0 4.1 3.6 3.7 3.7 3.3 3.9 4.2 3.6
## 476 480 496 497 498 519 522 524 536 547 549 553 554 562 572 576
## 3.9 3.8 3.5 3.2 4.0 5.0 4.2 3.9 3.0 3.4 3.3 2.4 2.4 4.1 3.2 3.3
## 593 598 605 613 616 617 622 625 627 629 635 638 639 655 658 660
## 3.7 3.5 4.7 3.6 3.8 4.1 3.5 3.3 3.7 4.0 3.3 3.1 4.0 3.3 2.8 2.5
## 662 667 670 671 676 682 688 692 699 701 704 710 711 719 721 723
## 2.7 2.5 2.4 2.7 4.0 3.6 3.4 3.8 3.1 4.4 4.1 3.9 3.8 3.9 2.5 2.6
## 735 741 746 753 761 776 777 790 792 800 804 810 813 816 823 837
## 3.6 4.5 3.8 3.7 4.2 2.2 2.2 2.9 4.2 4.0 3.1 4.1 3.7 2.4 3.5 3.1
## 842 844 848 852 857 869 878 888 897 899 901 903 906 909 910 912
## 3.6 3.6 2.5 2.8 2.7 3.3 4.0 4.0 2.3 2.5 3.6 3.4 3.8 3.5 3.2 4.3
## 918 953 958 959 961 964 971 980 982 986 988 991 995 998 1009 1015
## 3.7 2.8 3.6 4.2 3.1 3.7 3.5 4.0 2.7 3.4 3.2 4.0 3.6 3.3 3.4 3.2
## 1029 1049 1063 1067 1080 1091 1092 1110 1111 1122 1128 1130 1133 1134 1135 1138
## 4.1 4.2 3.7 3.4 3.6 3.3 3.7 3.7 3.1 2.5 2.8 3.7 3.4 2.7 3.1 3.3
## 1145 1147 1149 1155 1160 1171 1177 1197 1206 1210 1213 1214 1215 1220 1227 1234
## 3.4 3.3 3.2 3.4 4.0 3.7 3.7 3.1 3.1 3.5 3.0 3.4 3.4 3.5 3.1 3.6
## 1236 1237 1244 1247 1249 1250 1251 1252 1254 1255 1268 1271 1272 1281 1283 1287
## 3.1 4.0 3.3 3.3 3.4 3.4 3.0 3.1 4.2 3.3 4.2 2.9 4.2 4.1 3.1 3.9
## 1301 1302 1305 1312 1321 1322 1333 1342 1349 1352 1353 1357 1359 1364 1366 1377
## 3.7 3.5 4.3 3.2 4.2 2.8 3.9 3.3 3.5 3.8 3.2 3.5 4.3 3.8 3.4 3.5
## 1383 1387 1393 1398 1402 1410 1415 1416 1422 1427 1431 1432 1434 1435 1436 1437
## 4.0 3.2 3.7 3.9 3.7 3.3 4.1 3.8 3.1 3.5 3.7 3.5 3.6 3.4 4.3 3.5
## 1442 1447 1448 1449 1452 1454 1458 1460 1468 1470 1477 1481 1482 1484 1485 1488
## 3.8 2.3 2.3 4.0 4.1 3.2 3.1 3.3 4.1 3.6 3.9 3.7 3.9 2.8 3.3 3.4
## 1492 1493 1496 1499 1506 1511 1513 1516 1520 1522 1526 1527 1528 1533 1537 1540
## 3.6 3.8 3.3 3.9 3.1 3.2 3.0 3.3 4.0 3.0 3.2 2.7 3.8 3.2 3.2 4.3
## 1547 1549 1550 1552 1553 1565 1566 1567 1568 1569 1574 1587 1593 1594 1600 1602
## 3.1 3.7 3.6 3.7 3.2 3.2 3.5 4.1 4.0 4.2 3.9 4.1 3.3 2.2 4.1 3.6
## 1603 1606 1612 1619 1620 1627 1629 1634 1637 1644 1646 1647 1658 1660 1672 1674
## 3.7 3.1 3.4 3.8 3.8 3.8 3.0 3.2 3.2 3.8 2.9 4.3 3.1 3.1 3.0 3.1
## 1675 1679 1680 1685 1695 1697 1699 1707 1710 1714 1715 1724 1729 1730 1739 1741
## 3.5 3.7 4.9 3.1 3.4 3.7 3.3 3.8 3.2 4.0 4.1 2.7 3.2 4.1 4.5 3.4
## 1743 1745 1750 1753 1755 1760 1763 1769 1776 1779 1781 1782 1792 1796 1802 1806
## 3.9 3.2 3.9 4.7 4.3 3.0 3.2 3.1 3.6 2.9 4.4 3.4 3.0 3.3 3.9 4.2
## 1812 1817 1819 1822 1847 1849 1856 1858 1864 1878 1883 1888 1893 1900 1901 1921
## 3.7 2.2 3.7 2.7 2.8 4.6 3.2 3.3 3.5 3.1 4.7 3.7 3.1 3.9 4.4 2.3
test$Happiness2<-round(predict(fit1,newdata = test),1)
#linear regrssion model
glimpse(iris)
## Rows: 150
## Columns: 5
## $ Sepal.Length <dbl> 5.1, 4.9, 4.7, 4.6, 5.0, 5.4, 4.6, 5.0, 4.4, 4.9, 5.4, 4.…
## $ Sepal.Width <dbl> 3.5, 3.0, 3.2, 3.1, 3.6, 3.9, 3.4, 3.4, 2.9, 3.1, 3.7, 3.…
## $ Petal.Length <dbl> 1.4, 1.4, 1.3, 1.5, 1.4, 1.7, 1.4, 1.5, 1.4, 1.5, 1.5, 1.…
## $ Petal.Width <dbl> 0.2, 0.2, 0.2, 0.2, 0.2, 0.4, 0.3, 0.2, 0.2, 0.1, 0.2, 0.…
## $ Species <fct> setosa, setosa, setosa, setosa, setosa, setosa, setosa, s…
#알아서 더미변수로 바꿔준다
#단계적 변수 선택
x1<-c(7,1,11,11,7,11,3,1,2,21,1,11,10)
x2<-c(26,29,56,31,52,55,71,31,54,47,40,66,68)
x3<-c(6,15,8,8,6,9,17,22,18,4,23,9,8)
x4<-c(60,52,30,47,33,22,6,44,22,26,34,12,12)
y<-c(78.5,74.3,104.3,87.6,95.9,109.2,102.7,72.5,93.1,115.9,83.8,113.3,109.4)
df<-data.frame(x1,x2,x3,x4,y)
step(lm(y~1,df),scope = list(lower=~1,upper=~x1+x2+x3+x4),direction = "forward")
## Start: AIC=71.44
## y ~ 1
##
## Df Sum of Sq RSS AIC
## + x2 1 1809.43 906.34 59.178
## + x4 1 1759.55 956.21 59.874
## + x1 1 1450.08 1265.69 63.519
## + x3 1 776.36 1939.40 69.067
## <none> 2715.76 71.444
##
## Step: AIC=59.18
## y ~ x2
##
## Df Sum of Sq RSS AIC
## + x1 1 848.43 57.90 25.420
## + x3 1 490.89 415.44 51.037
## <none> 906.34 59.178
## + x4 1 12.99 893.34 60.990
##
## Step: AIC=25.42
## y ~ x2 + x1
##
## Df Sum of Sq RSS AIC
## + x4 1 13.9620 43.942 23.833
## + x3 1 9.7939 48.111 25.011
## <none> 57.904 25.420
##
## Step: AIC=23.83
## y ~ x2 + x1 + x4
##
## Df Sum of Sq RSS AIC
## <none> 43.942 23.833
## + x3 1 0.10561 43.837 25.802
##
## Call:
## lm(formula = y ~ x2 + x1 + x4, data = df)
##
## Coefficients:
## (Intercept) x2 x1 x4
## 72.0911 0.4130 1.4692 -0.2444
library(ISLR)
library(dplyr)
data("attitude")
glimpse(attitude)
## Rows: 30
## Columns: 7
## $ rating <dbl> 43, 63, 71, 61, 81, 43, 58, 71, 72, 67, 64, 67, 69, 68, 77,…
## $ complaints <dbl> 51, 64, 70, 63, 78, 55, 67, 75, 82, 61, 53, 60, 62, 83, 77,…
## $ privileges <dbl> 30, 51, 68, 45, 56, 49, 42, 50, 72, 45, 53, 47, 57, 83, 54,…
## $ learning <dbl> 39, 54, 69, 47, 66, 44, 56, 55, 67, 47, 58, 39, 42, 45, 72,…
## $ raises <dbl> 61, 63, 76, 54, 71, 54, 66, 70, 71, 62, 58, 59, 55, 59, 79,…
## $ critical <dbl> 92, 73, 86, 84, 83, 49, 68, 66, 83, 80, 67, 74, 63, 77, 77,…
## $ advance <dbl> 45, 47, 48, 35, 47, 34, 35, 41, 31, 41, 34, 41, 25, 35, 46,…
step(lm(rating~., data=attitude),directions="backward")
## Start: AIC=123.36
## rating ~ complaints + privileges + learning + raises + critical +
## advance
##
## Df Sum of Sq RSS AIC
## - critical 1 3.41 1152.4 121.45
## - raises 1 6.80 1155.8 121.54
## - privileges 1 14.47 1163.5 121.74
## - advance 1 74.11 1223.1 123.24
## <none> 1149.0 123.36
## - learning 1 180.50 1329.5 125.74
## - complaints 1 724.80 1873.8 136.04
##
## Step: AIC=121.45
## rating ~ complaints + privileges + learning + raises + advance
##
## Df Sum of Sq RSS AIC
## - raises 1 10.61 1163.0 119.73
## - privileges 1 14.16 1166.6 119.82
## - advance 1 71.27 1223.7 121.25
## <none> 1152.4 121.45
## - learning 1 177.74 1330.1 123.75
## - complaints 1 724.70 1877.1 134.09
##
## Step: AIC=119.73
## rating ~ complaints + privileges + learning + advance
##
## Df Sum of Sq RSS AIC
## - privileges 1 16.10 1179.1 118.14
## - advance 1 61.60 1224.6 119.28
## <none> 1163.0 119.73
## - learning 1 197.03 1360.0 122.42
## - complaints 1 1165.94 2328.9 138.56
##
## Step: AIC=118.14
## rating ~ complaints + learning + advance
##
## Df Sum of Sq RSS AIC
## - advance 1 75.54 1254.7 118.00
## <none> 1179.1 118.14
## - learning 1 186.12 1365.2 120.54
## - complaints 1 1259.91 2439.0 137.94
##
## Step: AIC=118
## rating ~ complaints + learning
##
## Df Sum of Sq RSS AIC
## <none> 1254.7 118.00
## - learning 1 114.73 1369.4 118.63
## - complaints 1 1370.91 2625.6 138.16
##
## Call:
## lm(formula = rating ~ complaints + learning, data = attitude)
##
## Coefficients:
## (Intercept) complaints learning
## 9.8709 0.6435 0.2112
step(lm(rating~.,data=attitude), direction="forward")
## Start: AIC=123.36
## rating ~ complaints + privileges + learning + raises + critical +
## advance
##
## Call:
## lm(formula = rating ~ complaints + privileges + learning + raises +
## critical + advance, data = attitude)
##
## Coefficients:
## (Intercept) complaints privileges learning raises critical
## 10.78708 0.61319 -0.07305 0.32033 0.08173 0.03838
## advance
## -0.21706
step(lm(rating~.,data=attitude), direction="both")
## Start: AIC=123.36
## rating ~ complaints + privileges + learning + raises + critical +
## advance
##
## Df Sum of Sq RSS AIC
## - critical 1 3.41 1152.4 121.45
## - raises 1 6.80 1155.8 121.54
## - privileges 1 14.47 1163.5 121.74
## - advance 1 74.11 1223.1 123.24
## <none> 1149.0 123.36
## - learning 1 180.50 1329.5 125.74
## - complaints 1 724.80 1873.8 136.04
##
## Step: AIC=121.45
## rating ~ complaints + privileges + learning + raises + advance
##
## Df Sum of Sq RSS AIC
## - raises 1 10.61 1163.0 119.73
## - privileges 1 14.16 1166.6 119.82
## - advance 1 71.27 1223.7 121.25
## <none> 1152.4 121.45
## + critical 1 3.41 1149.0 123.36
## - learning 1 177.74 1330.1 123.75
## - complaints 1 724.70 1877.1 134.09
##
## Step: AIC=119.73
## rating ~ complaints + privileges + learning + advance
##
## Df Sum of Sq RSS AIC
## - privileges 1 16.10 1179.1 118.14
## - advance 1 61.60 1224.6 119.28
## <none> 1163.0 119.73
## + raises 1 10.61 1152.4 121.45
## + critical 1 7.21 1155.8 121.54
## - learning 1 197.03 1360.0 122.42
## - complaints 1 1165.94 2328.9 138.56
##
## Step: AIC=118.14
## rating ~ complaints + learning + advance
##
## Df Sum of Sq RSS AIC
## - advance 1 75.54 1254.7 118.00
## <none> 1179.1 118.14
## + privileges 1 16.10 1163.0 119.73
## + raises 1 12.54 1166.6 119.82
## + critical 1 7.18 1171.9 119.96
## - learning 1 186.12 1365.2 120.54
## - complaints 1 1259.91 2439.0 137.94
##
## Step: AIC=118
## rating ~ complaints + learning
##
## Df Sum of Sq RSS AIC
## <none> 1254.7 118.00
## + advance 1 75.54 1179.1 118.14
## - learning 1 114.73 1369.4 118.63
## + privileges 1 30.03 1224.6 119.28
## + raises 1 1.19 1253.5 119.97
## + critical 1 0.00 1254.7 120.00
## - complaints 1 1370.91 2625.6 138.16
##
## Call:
## lm(formula = rating ~ complaints + learning, data = attitude)
##
## Coefficients:
## (Intercept) complaints learning
## 9.8709 0.6435 0.2112
df<-read.csv("Data1.csv")
table(df$Gender1)
##
## 0 1
## 1136 789
#남자:1, 여자:0
lmfit<-lm(Happiness~Gender1,data=df)
summary(lmfit)
##
## Call:
## lm(formula = Happiness ~ Gender1, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1659 -0.5199 0.0801 0.4801 1.4801
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.56593 0.02219 160.711 <0.0000000000000002 ***
## Gender1 -0.04603 0.03466 -1.328 0.184
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7479 on 1923 degrees of freedom
## Multiple R-squared: 0.0009166, Adjusted R-squared: 0.0003971
## F-statistic: 1.764 on 1 and 1923 DF, p-value: 0.1843
df<-read.csv("Data1.csv")
table(df$Gender1)
##
## 0 1
## 1136 789
#남자:1, 여자:0
glimpse(df)
## Rows: 1,925
## Columns: 26
## $ Q1 <int> 4, 4, 4, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, …
## $ Q2 <int> 4, 4, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 2, 2, …
## $ Q3 <int> 2, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 4, 4, 3, 2, 3, …
## $ Q4 <int> 3, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 4, 4, 2, 4, 4, 4, 2, 2, 4, …
## $ Q5 <int> 4, 4, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 4, 4, 4, 4, 3, 1, 2, …
## $ Q6 <int> 2, 3, 4, 4, 4, 4, 4, 4, 1, 2, 2, 2, 4, 4, 3, 5, 2, 2, 1, 4, …
## $ Q7 <int> 2, 2, 4, 4, 4, 4, 4, 4, 3, 4, 4, 4, 5, 4, 4, 5, 4, 3, 4, 4, …
## $ Q8 <int> 4, 4, 4, 4, 4, 4, 5, 5, 2, 2, 4, 4, 4, 4, 3, 5, 4, 2, 4, 4, …
## $ Q9 <int> 4, 4, 4, 4, 2, 4, 5, 5, 3, 4, 4, 4, 2, 2, 4, 5, 2, 4, 2, 4, …
## $ Q10 <int> 4, 4, 2, 4, 4, 4, 5, 5, 2, 4, 2, 4, 4, 4, 3, 4, 4, 3, 2, 3, …
## $ Q11 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 3, 4, 4, 4, 4, 5, 4, 3, 3, …
## $ Q12 <int> 4, 4, 4, 4, 4, 4, 5, 5, 3, 4, 4, 3, 4, 3, 3, 4, 5, 4, 4, 2, …
## $ Q13 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 4, 2, 4, 4, 4, 5, 4, 4, 4, …
## $ Q14 <int> 4, 4, 4, 4, 4, 4, 5, 5, 5, 4, 4, 4, 3, 4, 5, 4, 5, 4, 4, 4, …
## $ Q15 <int> 4, 4, 3, 4, 4, 4, 4, 2, 3, 4, 4, 3, 1, 4, 4, 4, 5, 4, 4, 4, …
## $ Q16 <int> 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, 4, 4, 4, 5, 4, 5, 4, 4, 4, …
## $ Q17 <int> 4, 3, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 3, 2, 4, 5, 4, 4, 3, 4, …
## $ Q18 <int> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, …
## $ Q19 <int> 4, 2, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 1, 4, 4, 4, 5, 4, 2, 3, …
## $ Q20 <int> 4, 1, 3, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 2, 4, 5, 5, 4, 2, 4, …
## $ Gender1 <int> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, …
## $ EDU1 <int> 1, 1, 2, 1, 2, 1, 1, 1, 4, 3, 2, 1, 1, 3, 3, 2, 1, 1, 1, 4, …
## $ BF <dbl> 3.4, 4.0, 3.6, 4.2, 4.0, 4.0, 3.6, 3.6, 3.6, 3.2, 4.0, 3.2, …
## $ BM <dbl> 3.2, 3.4, 3.6, 4.0, 3.6, 4.0, 4.6, 4.6, 2.2, 3.2, 3.2, 3.6, …
## $ Happiness <dbl> 4.0, 4.0, 3.8, 4.0, 4.0, 4.0, 4.8, 4.4, 3.8, 4.0, 4.0, 3.4, …
## $ Peace <dbl> 4.0, 2.8, 3.8, 4.0, 4.0, 4.0, 3.8, 2.4, 4.0, 3.2, 4.0, 3.9, …
df$EDU1<-factor(df$EDU1)
lmfit1<-lm(Happiness~EDU1,data=df)
summary(lmfit)
##
## Call:
## lm(formula = Happiness ~ Gender1, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1659 -0.5199 0.0801 0.4801 1.4801
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.56593 0.02219 160.711 <0.0000000000000002 ***
## Gender1 -0.04603 0.03466 -1.328 0.184
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7479 on 1923 degrees of freedom
## Multiple R-squared: 0.0009166, Adjusted R-squared: 0.0003971
## F-statistic: 1.764 on 1 and 1923 DF, p-value: 0.1843
table(df$EDU1)
##
## 1 2 3 4
## 233 472 1022 198
#1중졸, 2 고졸, 3대졸, 4대학원졸
bs.out2<-lm(Happiness~BM,data = df)
summary(bs.out2)
##
## Call:
## lm(formula = Happiness ~ BM, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1591 -0.4577 0.0418 0.4409 1.9386
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.06599 0.05777 35.77 <0.0000000000000002 ***
## BM 0.49771 0.01878 26.50 <0.0000000000000002 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6404 on 1923 degrees of freedom
## Multiple R-squared: 0.2675, Adjusted R-squared: 0.2671
## F-statistic: 702.2 on 1 and 1923 DF, p-value: < 0.00000000000000022
#건강한 자기관리가 '1' 증가할 경우 행복은 0.498증가함
#현짱 화장실
install.packages('datasets')
## Warning: 패키지 'datasets'가 사용중이므로 설치되지 않을 것입니다
library(datasets)
data('USArrests')
head(USArrests)
## Murder Assault UrbanPop Rape
## Alabama 13.2 236 58 21.2
## Alaska 10.0 263 48 44.5
## Arizona 8.1 294 80 31.0
## Arkansas 8.8 190 50 19.5
## California 9.0 276 91 40.6
## Colorado 7.9 204 78 38.7
fit<-prcomp(USArrests,scale=TRUE)
summary(fit)
## Importance of components:
## PC1 PC2 PC3 PC4
## Standard deviation 1.5749 0.9949 0.59713 0.41645
## Proportion of Variance 0.6201 0.2474 0.08914 0.04336
## Cumulative Proportion 0.6201 0.8675 0.95664 1.00000
Nile
## Time Series:
## Start = 1871
## End = 1970
## Frequency = 1
## [1] 1120 1160 963 1210 1160 1160 813 1230 1370 1140 995 935 1110 994 1020
## [16] 960 1180 799 958 1140 1100 1210 1150 1250 1260 1220 1030 1100 774 840
## [31] 874 694 940 833 701 916 692 1020 1050 969 831 726 456 824 702
## [46] 1120 1100 832 764 821 768 845 864 862 698 845 744 796 1040 759
## [61] 781 865 845 944 984 897 822 1010 771 676 649 846 812 742 801
## [76] 1040 860 874 848 890 744 749 838 1050 918 986 797 923 975 815
## [91] 1020 906 901 1170 912 746 919 718 714 740
plot(Nile)
Nile.diff1<-diff(Nile,differences = 1)
plot(Nile.diff1)
Nile.diff2<-diff(Nile,differences = 2)
plot(Nile.diff2)
