Atividade Avaliativa 02 PPGBAA_Turma2025
Dielson Marcio Fonseca Maues
2025-12-03
================================================================== ### ANÁLISE MULTIVARIADA ### ==================================================================
1. Pacotes
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.6
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.2.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(vegan)## Carregando pacotes exigidos: permutelibrary(cluster)
library(FactoMineR)
library(factoextra)## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBalibrary(MASS)##
## Anexando pacote: 'MASS'
##
## O seguinte objeto é mascarado por 'package:dplyr':
##
## select2. Upload do arquivo via Web “dataset_bioinfo_bioestat.csv”
dataset_bb = read.csv("https://raw.githubusercontent.com/leocbc/ANALISE-MULTIVARIADA/refs/heads/main/dataset_bioinfo_bioestat.csv",
sep = ",", dec = ".", header = TRUE)
View(dataset_bb)3. Estruturas de Repetição e Funções no R
3.1. Usando ‘for’: trabalhando com média
mean_dataset_bb = NULL
for (i in 2:ncol(dataset_bb)) { # a partir da 2° coluna
mean_dataset_bb[i] = mean(dataset_bb[[i]])
}
mean_dataset_bb # média total das colunas## [1] NA 5.1360 74.5880 2986.0200 30.5000 6.2984 28.3940
## [8] 40.3840 70.7980 81.00803.1.1. Usando o pacote dplyr: trabalhando com média
library(dplyr)
dataset_bb %>%
summarise(across(where(is.numeric), mean, na.rm = TRUE)) # média por variável## Warning: There was 1 warning in `summarise()`.
## ℹ In argument: `across(where(is.numeric), mean, na.rm = TRUE)`.
## Caused by warning:
## ! The `...` argument of `across()` is deprecated as of dplyr 1.1.0.
## Supply arguments directly to `.fns` through an anonymous function instead.
##
## # Previously
## across(a:b, mean, na.rm = TRUE)
##
## # Now
## across(a:b, \(x) mean(x, na.rm = TRUE))3.2 Usando o ‘while’: trabalhando com média
n_contagem = 1
soma = 0
while (n_contagem <= 9) { # 9 equivale ao n°de colunas do dataset
soma = soma + mean(dataset_bb[[1]]) # Somando a média das variáveis até a ultima coluna.
n_contagem = n_contagem + 1
}
soma## [1] 229.53.2.1 Usando o pacote dplyr: trabalhando com média
library(dplyr)
soma = dataset_bb %>%
dplyr::select(where(is.numeric)) %>% # selecionando apenas números
summarise(across(everything(), mean)) %>% # somando a média das colunas
sum()
soma## [1] 3348.6263.3 Montagem de uma função para retornar Média e o Desvia Padrão de uma variável
mdp = function(variavel) {
media = mean(variavel)
desvio_pad = sd(variavel)
return(list(media = media, desvio_padrao = desvio_pad))
}
mdp # nome da nova função## function (variavel)
## {
## media = mean(variavel)
## desvio_pad = sd(variavel)
## return(list(media = media, desvio_padrao = desvio_pad))
## }mdp(dataset_bb$Biomassa_g) # variável exemplo## $media
## [1] 5.136
##
## $desvio_padrao
## [1] 2.0027374. Condicionais em R: ‘if’ e ‘else’
4.1 Classificando experimento como ‘Alto’, ‘Moderado’ ou ‘Baixo’, com base na media.
rend_media = mean(dataset_bb$Rendimento_Etanol_.)
rend_media## [1] 74.588if (rend_media < 50) {
cat("O experimento teve BAIXO rendimento na produção de bioetanol.\n")
}
if (rend_media >= 50 & rend_media <= 70) {
cat("O experimento teve MODERADO rendimento na produção de bioetanol.\n")
} else {
cat("O experimento teve ALTO rendimento na produção de bioetanol.\n")
}## O experimento teve ALTO rendimento na produção de bioetanol.4.2 Criando uma coluna com base nos valores de uma variável:
dataset_bb$Eficacia_Enzimatica = ifelse(
dataset_bb$Atividade_Enzimatica_UmL >= 70,
"ELEVADO",
"BAIXO"
)
dataset_bb5. Sumarização das Variáveis
summary(dataset_bb)## Experimento_ID Biomassa_g Rendimento_Etanol_. Expressao_Genica_FP
## Min. : 1.00 Min. :1.800 Min. :40.70 Min. : 120
## 1st Qu.:13.25 1st Qu.:3.368 1st Qu.:65.28 1st Qu.:1994
## Median :25.50 Median :5.395 Median :79.35 Median :3322
## Mean :25.50 Mean :5.136 Mean :74.59 Mean :2986
## 3rd Qu.:37.75 3rd Qu.:7.032 3rd Qu.:90.25 3rd Qu.:4430
## Max. :50.00 Max. :8.150 Max. :94.30 Max. :5000
## Temperatura_Reacao_C pH_Cultura Concentracao_Substrato_gL
## Min. :25.0 Min. :4.730 Min. : 9.03
## 1st Qu.:28.0 1st Qu.:5.420 1st Qu.:17.22
## Median :30.0 Median :6.240 Median :25.70
## Mean :30.5 Mean :6.298 Mean :28.39
## 3rd Qu.:33.0 3rd Qu.:7.277 3rd Qu.:38.89
## Max. :37.0 Max. :8.000 Max. :49.98
## Tempo_Fermentacao_h Atividade_Enzimatica_UmL Viabilidade_Celular_.
## Min. :12.30 Min. : 11.00 Min. :62.50
## 1st Qu.:23.40 1st Qu.: 50.23 1st Qu.:70.83
## Median :41.20 Median : 72.10 Median :82.65
## Mean :40.38 Mean : 70.80 Mean :81.01
## 3rd Qu.:57.25 3rd Qu.: 96.38 3rd Qu.:90.85
## Max. :71.70 Max. :119.50 Max. :98.20
## Eficacia_Enzimatica
## Length:50
## Class :character
## Mode :character
##
##
## 6. Análise de Correlação
cor_data = cor(dataset_bb[ ,2:10]) # Dá coluna 2 até a coluna 10 são númericas
cor_data## Biomassa_g Rendimento_Etanol_. Expressao_Genica_FP
## Biomassa_g 1.00000000 0.03255417 -0.035317751
## Rendimento_Etanol_. 0.03255417 1.00000000 0.297750675
## Expressao_Genica_FP -0.03531775 0.29775068 1.000000000
## Temperatura_Reacao_C 0.02037497 0.04332942 0.034116469
## pH_Cultura -0.14749029 0.02265867 0.005210462
## Concentracao_Substrato_gL 0.18499721 0.08242555 0.115137093
## Tempo_Fermentacao_h -0.05416871 0.12779681 0.001527177
## Atividade_Enzimatica_UmL -0.05716153 0.24861430 0.160794205
## Viabilidade_Celular_. 0.01764701 0.28681575 0.123145020
## Temperatura_Reacao_C pH_Cultura
## Biomassa_g 0.0203749671 -0.147490286
## Rendimento_Etanol_. 0.0433294180 0.022658669
## Expressao_Genica_FP 0.0341164689 0.005210462
## Temperatura_Reacao_C 1.0000000000 0.087559113
## pH_Cultura 0.0875591126 1.000000000
## Concentracao_Substrato_gL -0.2818214674 0.144933992
## Tempo_Fermentacao_h -0.0001047807 0.041278595
## Atividade_Enzimatica_UmL 0.1504107199 0.047651129
## Viabilidade_Celular_. -0.1799980241 0.082912740
## Concentracao_Substrato_gL Tempo_Fermentacao_h
## Biomassa_g 0.18499721 -0.0541687078
## Rendimento_Etanol_. 0.08242555 0.1277968121
## Expressao_Genica_FP 0.11513709 0.0015271768
## Temperatura_Reacao_C -0.28182147 -0.0001047807
## pH_Cultura 0.14493399 0.0412785947
## Concentracao_Substrato_gL 1.00000000 -0.1379666992
## Tempo_Fermentacao_h -0.13796670 1.0000000000
## Atividade_Enzimatica_UmL -0.16242476 0.1030906911
## Viabilidade_Celular_. 0.10518119 0.0201931453
## Atividade_Enzimatica_UmL Viabilidade_Celular_.
## Biomassa_g -0.05716153 0.01764701
## Rendimento_Etanol_. 0.24861430 0.28681575
## Expressao_Genica_FP 0.16079420 0.12314502
## Temperatura_Reacao_C 0.15041072 -0.17999802
## pH_Cultura 0.04765113 0.08291274
## Concentracao_Substrato_gL -0.16242476 0.10518119
## Tempo_Fermentacao_h 0.10309069 0.02019315
## Atividade_Enzimatica_UmL 1.00000000 -0.11555619
## Viabilidade_Celular_. -0.11555619 1.000000006.1 PLOT de correlação
library(corrplot)## corrplot 0.95 loadedcorrplot::corrplot(cor_data, method = "color", tl.cex = 0.8)
6.2 Distribuição das Variáveis
ggplot(stack(dataset_bb[,2:10]), aes(x = ind, y = values)) +
geom_boxplot() +
theme_minimal() +
labs(title = "Distribuição das Variáveis", x = "Variáveis", y = "Valores") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
7. Análise de Variância Multivariada (MANOVA)
group = factor(rep(c("A","B","C","D"), length.out = nrow(dataset_bb)))
group## [1] A B C D A B C D A B C D A B C D A B C D A B C D A B C D A B C D A B C D A B
## [39] C D A B C D A B C D A B
## Levels: A B C Dmanova_dataset_bb <- manova(as.matrix(dataset_bb[,2:10]) ~ group)
manova_dataset_bb## Call:
## manova(as.matrix(dataset_bb[, 2:10]) ~ group)
##
## Terms:
## group Residuals
## Biomassa_g 1 195
## Rendimento_Etanol_. 429 14159
## Expressao_Genica_FP 2593997 116803282
## Temperatura_Reacao_C 58 795
## pH_Cultura 0 51
## Concentracao_Substrato_gL 1121 6306
## Tempo_Fermentacao_h 2753 14342
## Atividade_Enzimatica_UmL 8769 39170
## Viabilidade_Celular_. 381 5782
## Deg. of Freedom 3 46
##
## Residual standard errors: 2.061527 17.54408 1593.487 4.156817 1.053757 11.70834 17.65734 29.18088 11.21153
## Estimated effects may be unbalancedsummary(manova_dataset_bb)## Df Pillai approx F num Df den Df Pr(>F)
## group 3 0.62499 1.1696 27 120 0.2776
## Residuals 467.1 Teste univariado
summary.aov(manova_dataset_bb)## Response Biomassa_g :
## Df Sum Sq Mean Sq F value Pr(>F)
## group 3 1.042 0.3472 0.0817 0.9697
## Residuals 46 195.495 4.2499
##
## Response Rendimento_Etanol_. :
## Df Sum Sq Mean Sq F value Pr(>F)
## group 3 429.1 143.04 0.4647 0.7083
## Residuals 46 14158.6 307.80
##
## Response Expressao_Genica_FP :
## Df Sum Sq Mean Sq F value Pr(>F)
## group 3 2593997 864666 0.3405 0.7961
## Residuals 46 116803282 2539202
##
## Response Temperatura_Reacao_C :
## Df Sum Sq Mean Sq F value Pr(>F)
## group 3 57.66 19.220 1.1123 0.3538
## Residuals 46 794.84 17.279
##
## Response pH_Cultura :
## Df Sum Sq Mean Sq F value Pr(>F)
## group 3 0.497 0.16582 0.1493 0.9296
## Residuals 46 51.079 1.11040
##
## Response Concentracao_Substrato_gL :
## Df Sum Sq Mean Sq F value Pr(>F)
## group 3 1120.6 373.53 2.7248 0.05494 .
## Residuals 46 6305.9 137.09
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Tempo_Fermentacao_h :
## Df Sum Sq Mean Sq F value Pr(>F)
## group 3 2752.8 917.61 2.9431 0.04277 *
## Residuals 46 14342.0 311.78
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Atividade_Enzimatica_UmL :
## Df Sum Sq Mean Sq F value Pr(>F)
## group 3 8769 2923.07 3.4327 0.02451 *
## Residuals 46 39170 851.52
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Viabilidade_Celular_. :
## Df Sum Sq Mean Sq F value Pr(>F)
## group 3 381.4 127.13 1.0114 0.3963
## Residuals 46 5782.1 125.708. Clusterização
8.1 Transformando os dados na escala de normalidade:
dataset_bb_scale = scale(dataset_bb[,1:10])
View(dataset_bb_scale)8.2 Matrizes de Distância
d_euclid = dist(dataset_bb_scale, method = "euclidean")
d_manhat = dist(dataset_bb_scale, method = "manhattan")
d_euclid # demonstrando apenas a distância euclidiana## 1 2 3 4 5 6 7 8
## 2 3.589837
## 3 4.112983 3.181403
## 4 4.890817 4.546811 3.597263
## 5 4.537532 4.931996 4.272828 2.246182
## 6 5.625143 3.867865 3.111980 4.376488 5.055426
## 7 2.861601 4.352569 3.375729 3.803540 3.515087 5.056541
## 8 6.161499 6.288984 5.836874 3.227393 4.163064 5.296150 5.459992
## 9 3.023846 4.346477 3.022346 4.195808 4.615988 5.288075 3.537654 5.910883
## 10 4.062334 3.479239 2.719928 2.903355 4.252948 4.232374 3.363571 4.606378
## 11 5.245504 3.923703 3.527707 3.920920 4.741872 2.849879 4.751061 4.512950
## 12 4.569356 3.488371 4.131692 4.252436 4.801056 2.850746 4.299361 4.451371
## 13 5.028132 4.949769 3.645433 3.780927 4.066465 4.978610 4.697951 5.447036
## 14 4.933589 4.472788 3.619375 2.469935 2.932672 5.211564 3.853880 4.926479
## 15 3.704032 3.490707 3.243427 3.739387 4.655974 4.569936 4.201123 5.434420
## 16 5.141756 4.703105 3.851030 3.581886 4.281398 3.458063 4.730701 3.872760
## 17 5.074151 5.673706 4.678953 3.002264 2.985260 5.182605 3.100986 4.149378
## 18 4.572220 3.447758 3.172416 5.066248 5.073148 3.762258 3.918162 6.420278
## 19 4.916373 4.700055 5.211760 3.228126 3.845180 4.828541 4.711512 3.395809
## 20 4.200076 3.911150 3.290506 4.011225 4.546614 4.210458 3.736757 4.974128
## 21 4.632394 4.918820 4.222803 2.780393 1.985821 4.347844 3.410475 3.580179
## 22 4.197537 4.131678 4.461422 4.060289 5.011505 5.857380 4.430078 5.092970
## 23 3.221846 3.896473 4.422858 4.939457 5.005676 5.278589 3.459590 5.773210
## 24 5.142236 3.620503 4.062954 3.020065 3.587762 4.200425 4.121325 4.833704
## 25 4.685763 4.143615 4.406792 5.057870 5.661179 5.148742 5.298911 5.737691
## 26 5.178330 5.101229 4.566196 3.673349 3.677109 4.850431 5.093417 4.829368
## 27 5.310322 4.900614 4.500280 4.798729 4.831433 4.110983 4.805771 4.912783
## 28 6.506059 4.939053 4.276992 3.739179 4.909573 3.796991 5.751136 5.052195
## 29 3.095323 5.123963 4.837290 4.073911 3.826779 6.361774 2.792620 5.267850
## 30 5.552608 4.557567 4.918197 4.600579 3.986729 4.193127 4.955415 5.159664
## 31 4.576260 3.237822 2.886864 4.654709 5.239958 3.381914 4.483391 6.123475
## 32 4.431839 3.660313 3.178411 4.517223 5.037016 3.972093 3.486608 6.024985
## 33 4.394759 4.031480 4.529893 3.597654 3.876445 5.673373 3.937249 5.492530
## 34 4.385830 4.965063 4.416518 3.846065 4.765905 5.049397 3.937981 3.914806
## 35 4.629641 3.982884 3.443706 4.426556 4.890527 4.113900 4.084166 5.521549
## 36 5.642757 4.815802 5.026018 4.420228 5.495496 5.831029 5.868083 5.464000
## 37 3.855622 4.530219 5.113573 4.792896 4.366986 5.420896 4.117036 5.097274
## 38 5.218888 4.022705 3.479666 4.433247 4.344469 4.143560 3.977755 6.449014
## 39 4.425950 2.998085 4.272119 4.802575 4.980368 4.293880 4.874150 5.911741
## 40 5.027003 3.900574 3.374823 4.009195 4.786398 4.086737 4.005062 5.862926
## 41 4.923952 3.351266 4.157329 4.368898 4.956028 4.832740 4.535039 5.984432
## 42 3.987466 5.299494 4.444721 4.889766 5.034509 6.260454 4.170591 6.155050
## 43 4.984712 5.714785 4.903945 4.456033 4.601952 5.311124 4.083776 5.181535
## 44 3.874192 3.780703 4.554759 5.375571 5.548631 4.977789 4.423613 6.368400
## 45 5.344404 5.735436 5.570511 4.163658 3.989789 5.339920 4.924056 4.502676
## 46 4.747977 3.560587 4.993896 5.091159 5.500082 5.403518 5.469744 6.176606
## 47 6.017007 5.601734 5.524332 4.659642 4.792933 6.331304 5.605402 5.473800
## 48 5.449721 5.203426 4.638667 4.812855 4.589723 5.850588 3.967006 6.756766
## 49 4.178405 5.534957 5.190142 5.778978 5.440197 6.070007 4.682080 6.372056
## 50 5.264288 4.701551 4.811917 5.163570 5.189680 5.545654 5.186159 6.878088
## 9 10 11 12 13 14 15 16
## 2
## 3
## 4
## 5
## 6
## 7
## 8
## 9
## 10 3.390857
## 11 4.842441 3.762837
## 12 5.342305 3.799996 3.604294
## 13 3.906269 3.460386 5.406461 5.323026
## 14 4.196240 3.082072 3.993504 5.370409 3.983817
## 15 2.723694 2.734316 4.262574 4.465939 4.019077 3.955619
## 16 4.453685 3.525643 2.622699 4.032023 4.112866 3.931111 3.489458
## 17 5.204481 3.973006 5.080029 4.434372 4.913011 3.941295 4.678068 4.276390
## 18 4.936435 3.783998 4.016695 3.819796 4.458813 4.604573 5.075515 4.635629
## 19 5.312522 4.275638 4.724722 3.220885 5.535642 4.881274 4.216252 4.543397
## 20 3.954845 2.229818 3.927676 3.848615 2.933356 3.793451 3.736703 3.240247
## 21 4.786172 4.011018 4.131579 3.792815 3.964532 3.502878 4.812784 3.674120
## 22 3.800538 2.679401 4.184847 5.062871 4.877251 3.337772 3.359874 4.264074
## 23 4.278821 3.964737 5.231464 3.558947 5.224626 5.336964 4.797981 5.688132
## 24 5.391639 3.501836 3.843720 3.495278 5.192981 3.257661 4.227769 4.424242
## 25 4.290610 3.350614 4.245738 4.948094 3.895432 4.456110 3.575933 3.421637
## 26 4.589355 4.222235 5.269168 4.873124 2.769789 4.339737 3.548425 3.460709
## 27 5.424439 4.128684 4.370926 3.725331 3.722240 5.032235 5.356715 3.811851
## 28 5.630790 4.157185 5.002747 4.018164 4.331726 5.063726 4.683171 4.842678
## 29 3.476464 3.956380 5.651029 5.110229 4.938956 4.165545 3.912472 5.154359
## 30 6.161279 4.980965 4.020403 3.835289 5.003182 4.511536 5.773774 4.295208
## 31 4.103680 3.117312 4.199295 3.582175 3.598931 4.692982 3.169275 3.821289
## 32 4.453191 3.040316 4.657259 3.238252 4.392859 4.732526 4.071312 4.808730
## 33 4.691657 3.238632 5.381246 4.547108 4.353997 3.448335 3.580257 4.974788
## 34 3.742313 3.232918 3.823815 4.040449 5.100556 4.304976 3.807394 3.847038
## 35 4.329435 2.754264 4.198130 3.814657 3.232189 4.162606 3.828146 3.581830
## 36 4.571823 4.376207 4.717865 5.411050 5.689642 4.535047 4.392011 5.423320
## 37 4.722302 4.584564 3.974483 4.376976 5.609419 4.336460 4.485414 3.985125
## 38 5.194624 3.992476 4.663678 4.254437 4.443633 3.982528 4.618972 4.774476
## 39 4.815011 4.214477 4.348948 3.376090 5.020380 4.903557 4.158746 4.869769
## 40 4.547110 3.197785 4.211507 3.887049 4.868927 4.000473 3.349720 4.323084
## 41 5.005415 3.561763 4.479185 3.938024 5.229937 4.102572 4.237698 5.221759
## 42 2.567121 4.218828 5.272207 5.925528 4.695896 4.323831 3.807486 4.949508
## 43 4.813253 4.209690 5.853801 4.351940 4.317586 5.295901 4.212248 4.587465
## 44 4.472951 4.085187 4.984614 3.893904 5.181807 5.335783 3.254194 4.530590
## 45 5.320129 5.207431 5.053526 4.565834 5.661633 4.991309 4.408078 4.257592
## 46 4.947963 4.155139 4.736274 4.554961 5.243041 4.676218 3.455082 4.639998
## 47 5.572277 4.544902 5.424357 5.783433 4.363274 3.974923 5.682378 5.318421
## 48 5.405261 4.492834 5.195652 5.652728 5.512128 3.551130 4.862573 5.133906
## 49 3.921354 5.252661 4.999766 5.708252 5.588386 5.232430 4.462411 4.546549
## 50 5.010756 4.718735 5.323845 5.506935 5.160348 4.525448 3.421252 4.537109
## 17 18 19 20 21 22 23 24
## 2
## 3
## 4
## 5
## 6
## 7
## 8
## 9
## 10
## 11
## 12
## 13
## 14
## 15
## 16
## 17
## 18 5.407866
## 19 3.725739 5.923081
## 20 4.511664 2.718346 5.091506
## 21 2.819798 4.151442 3.573744 3.665186
## 22 5.282922 4.924620 4.811904 3.442215 4.856727
## 23 5.176786 3.783550 4.363606 3.920313 4.198826 4.384680
## 24 3.596243 4.338120 3.179764 4.327792 3.414060 4.274924 4.467986
## 25 6.036134 4.173371 5.778192 2.357825 5.079377 3.059155 5.065660 5.266617
## 26 4.212762 5.429665 4.235608 3.954028 3.576800 5.186610 5.641185 4.598088
## 27 5.088995 2.937908 5.326593 2.339249 3.311404 5.140517 4.309678 4.907633
## 28 4.979692 5.195739 3.960930 4.722183 4.375029 5.789394 5.243397 3.744105
## 29 3.666226 5.442520 4.060530 4.411747 3.779146 3.804782 3.526936 4.473982
## 30 4.918959 3.383076 4.815842 3.992427 2.754894 5.462991 4.725643 3.676256
## 31 5.132788 3.041090 4.984311 2.668742 4.498533 4.515416 4.142400 4.097407
## 32 4.379808 2.847011 4.642013 3.066684 4.138194 4.652727 3.003863 3.551981
## 33 3.777224 4.819132 3.679096 3.916219 3.902122 3.658343 4.084130 2.690280
## 34 4.351373 4.937675 3.756538 3.684276 3.871780 2.979450 3.598159 4.269054
## 35 4.639427 2.612071 5.110238 1.326759 3.826349 3.935187 3.924254 4.112362
## 36 6.346665 5.919447 4.489290 5.254308 5.291332 3.517260 4.702298 4.441677
## 37 4.766626 4.521962 4.409698 4.060815 3.574966 3.708281 4.096693 4.215721
## 38 4.249929 3.012219 5.116760 3.766579 3.725093 5.252929 4.496872 2.971503
## 39 5.601193 3.731587 4.000889 4.045387 4.215847 4.367940 3.123594 3.425379
## 40 3.988999 4.139591 4.186163 3.930826 4.284313 4.349917 4.391300 2.626802
## 41 5.106137 3.869875 4.172550 4.059447 4.397611 3.785217 3.430012 2.468559
## 42 5.473296 5.245026 5.519398 4.272587 4.723981 3.544417 4.234668 5.422589
## 43 3.215910 5.314136 4.026881 4.100850 3.727607 5.462293 4.494135 4.604341
## 44 5.059252 4.417189 4.478879 3.862038 4.843587 4.346235 3.857114 4.282165
## 45 3.672799 6.228268 2.901344 5.415592 3.481468 5.417381 5.297334 4.007571
## 46 5.828039 4.877547 4.438483 4.184026 5.064254 3.479462 4.517886 3.832542
## 47 5.825658 4.739956 5.552075 3.916238 4.029231 4.074516 4.785966 4.676978
## 48 4.047152 4.569822 5.652887 4.581732 4.319573 4.837853 5.408127 3.517456
## 49 5.754708 5.240842 5.761604 4.616286 4.743050 4.512518 4.788091 5.794646
## 50 5.006297 5.413661 5.201925 4.799076 5.077781 4.904424 5.857674 4.161573
## 25 26 27 28 29 30 31 32
## 2
## 3
## 4
## 5
## 6
## 7
## 8
## 9
## 10
## 11
## 12
## 13
## 14
## 15
## 16
## 17
## 18
## 19
## 20
## 21
## 22
## 23
## 24
## 25
## 26 4.331668
## 27 3.761109 4.297679
## 28 5.756950 4.076334 4.764954
## 29 5.200486 4.626820 5.462693 5.900955
## 30 4.921527 4.657763 2.901611 4.959848 5.534638
## 31 3.366164 3.782593 3.549956 3.735577 4.990125 4.405201
## 32 4.646253 4.790795 3.828033 3.825729 4.324390 4.453221 2.225187
## 33 4.630776 3.858546 5.042701 4.407315 3.173116 4.688862 3.893379 3.473995
## 34 4.259223 4.966389 4.518763 4.957002 3.240399 5.093091 4.364596 3.989707
## 35 2.762140 3.840542 2.414606 4.284689 4.551623 3.817374 1.868934 2.389585
## 36 5.083430 5.659883 6.025030 4.699567 4.876877 5.794695 5.065716 5.160200
## 37 4.090659 4.863436 4.370788 6.252295 3.539588 3.637769 4.681307 4.749502
## 38 5.089870 4.434467 4.159274 4.091734 4.844759 3.529635 2.902692 2.463263
## 39 4.334385 4.613427 4.163374 4.079301 4.596891 3.599976 2.995012 3.163908
## 40 4.841628 4.430395 4.951673 3.630854 4.278576 4.751631 2.720927 2.305687
## 41 4.701244 5.165839 4.785399 3.993291 4.381934 4.179846 3.401405 2.761180
## 42 4.371449 4.945700 5.409063 6.039573 2.932232 5.854673 4.539039 4.636513
## 43 5.360107 3.372599 4.483507 4.364181 3.570228 5.247165 3.848202 3.447447
## 44 3.964869 4.314442 4.716418 5.224967 3.945746 4.914546 2.744185 3.152276
## 45 5.889549 3.687783 5.495298 4.840636 3.846082 4.757194 5.031686 5.056723
## 46 3.480951 4.404844 5.045845 5.039651 4.572138 4.664023 3.430385 4.193209
## 47 4.350609 4.960357 3.981552 5.200214 4.936200 4.008056 4.974436 4.957955
## 48 5.473543 5.179583 5.520280 5.817955 4.245035 4.681817 4.510872 4.017434
## 49 4.398315 5.079637 5.149412 6.809055 3.798875 5.260073 4.739242 5.173381
## 50 4.665647 3.810809 5.787404 5.390410 4.641054 5.260338 3.652227 4.482093
## 33 34 35 36 37 38 39 40
## 2
## 3
## 4
## 5
## 6
## 7
## 8
## 9
## 10
## 11
## 12
## 13
## 14
## 15
## 16
## 17
## 18
## 19
## 20
## 21
## 22
## 23
## 24
## 25
## 26
## 27
## 28
## 29
## 30
## 31
## 32
## 33
## 34 4.241314
## 35 3.662472 3.855547
## 36 4.565222 3.500883 5.206294
## 37 4.213551 3.381330 4.111397 4.878672
## 38 3.380908 5.045748 2.979433 5.622826 4.645014
## 39 3.589225 4.090383 3.482590 3.750599 3.657067 3.464615
## 40 2.966428 3.881128 3.229094 4.562328 4.540497 2.367668 3.377356
## 41 2.730603 3.926516 3.510690 3.477463 4.171930 2.973529 2.113679 2.483341
## 42 4.447123 3.132927 4.259476 3.983333 3.811997 5.073521 4.464743 4.475195
## 43 3.663454 4.071820 3.633855 6.040541 4.829364 4.086454 4.662640 3.580560
## 44 3.463646 4.059031 3.220350 5.235537 3.530952 3.826968 2.926234 3.060414
## 45 4.111774 3.992664 5.098032 5.169021 3.738467 4.783428 4.383594 4.058574
## 46 3.156140 4.243769 3.706166 3.900467 3.519546 4.254655 2.438008 3.545709
## 47 4.174438 4.435131 3.874514 4.206372 4.437483 4.698169 4.203795 5.170996
## 48 3.396516 4.968817 4.082772 5.909492 4.216813 2.645331 4.772331 2.993261
## 49 5.256570 3.749183 4.472429 5.239290 2.656499 5.269524 4.484791 4.973925
## 50 3.442943 5.195557 4.133757 5.592424 4.312874 3.595872 4.168392 3.054124
## 41 42 43 44 45 46 47 48
## 2
## 3
## 4
## 5
## 6
## 7
## 8
## 9
## 10
## 11
## 12
## 13
## 14
## 15
## 16
## 17
## 18
## 19
## 20
## 21
## 22
## 23
## 24
## 25
## 26
## 27
## 28
## 29
## 30
## 31
## 32
## 33
## 34
## 35
## 36
## 37
## 38
## 39
## 40
## 41
## 42 4.513992
## 43 4.752896 4.655758
## 44 3.505111 4.185369 3.521833
## 45 4.780597 4.774099 3.360487 4.064026
## 46 2.809236 4.339017 4.903737 2.509553 4.420840
## 47 3.938654 4.445734 5.524872 5.520964 5.625136 4.418340
## 48 3.785087 4.654084 4.579932 4.257333 4.685264 4.527962 5.022652
## 49 5.186409 2.512395 4.872027 3.735603 4.326708 4.302410 5.222381 4.805742
## 50 4.150162 4.590735 4.244862 2.899326 3.914256 3.047852 5.678573 3.224062
## 49
## 2
## 3
## 4
## 5
## 6
## 7
## 8
## 9
## 10
## 11
## 12
## 13
## 14
## 15
## 16
## 17
## 18
## 19
## 20
## 21
## 22
## 23
## 24
## 25
## 26
## 27
## 28
## 29
## 30
## 31
## 32
## 33
## 34
## 35
## 36
## 37
## 38
## 39
## 40
## 41
## 42
## 43
## 44
## 45
## 46
## 47
## 48
## 49
## 50 4.340498heatmap(as.matrix(d_euclid)) # Mapa de calor da distancia euclidiana do dataset
8.3 Métodos de associação e Gráficos
ward_d2 = hclust(d_euclid, method = "ward.D2")
average = hclust(d_euclid, method = "average")
complete = hclust(d_euclid, method = "complete")# Dendrogramas
plot(ward_d2, main="Distância Euclidiana - ward.D2", h = -1, xlab = "", ylab = "") 
plot(average, main="Distância Euclidiana - average", h = -1, xlab = "", ylab = "")
plot(complete, main="Distância Euclidiana - complete", h = -1, xlab = "", ylab = "")
# K-means
k3 = kmeans(d_euclid, centers = 3)
fviz_cluster(k3, data = d_euclid, main = "Clusterização K-means (k=3)")
9. Análise de Componentes Principais (PCA)
# PCA
pca_dataset_bb = PCA(dataset_bb[,1:10], scale.unit = TRUE, graph = FALSE)fviz_pca_biplot(pca_dataset_bb, repel = TRUE,
col.var = "black",
col.ind = "purple4",
title = "Biplot PCA - Biotechnology and Bioinformatics dataset") ## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## ℹ The deprecated feature was likely used in the ggpubr package.
## Please report the issue at <https://github.com/kassambara/ggpubr/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
fviz_pca_var(pca_dataset_bb,
repel = TRUE,
col.var = "purple4") +
ggtitle("PCA – Variáveis")## Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
## ℹ Please use tidy evaluation idioms with `aes()`.
## ℹ See also `vignette("ggplot2-in-packages")` for more information.
## ℹ The deprecated feature was likely used in the factoextra package.
## Please report the issue at <https://github.com/kassambara/factoextra/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
fviz_pca_biplot(
pca_dataset_bb,
repel = TRUE,
habillage = as.factor(dataset_bb$Eficacia_Enzimatica), # fator
addEllipses = TRUE, # adiciona elipses
ellipse.level = 0.95, palette = c("red", "green3"), col.var = "black", # nível de confiança
) +
ggtitle("Biplot PCA com Elipses por grupo")