Visualização de Dados (Ex. 12)
Aline Chagas
2025-05-18
Exercício 12 - Visualização de Dados - R
Questões de 1 a 5 foram feitas com o R tradicional e as questões de 6 a 10 utilizaram o Plotly.
Questão 1
MRT_1F <-c(517.1468515630205, 85.13094142168089, 30.333207896694553, 12.694776264558937, 3.3041601673945418, 1.1823111717498882, 1.1892293502386786)
MRT_3F <-c(156.68929936163462, 11.540837783562276, 0.4512835621696538, 0.4509797929766453, 0.4502068233039181, 0.4496185276300172, 0.4543157082191288)
MRT_5F <-c(83.90319666471157, 0.3068151086494968, 0.30522314133037304, 0.3072588968084928, 0.30655265997285697, 0.3055812715727718, 0.3053297166713006)
MRT_10F <-c(29.55430642951759, 0.19832832665772515, 0.1971923924717474, 0.19796648905716516, 0.19615594370806338, 0.2034569237883263, 0.19617420889447737)
MRT_15F <-c(11.317736530583566, 0.167364215666193, 0.16172168266811013, 0.16701085329580515, 0.1598052657153692, 0.1645934043532696, 0.16216563797118075)
MRT_sem_F <-c(11.93430909937736, 0.6095414637034009, 0.6060645101029295, 0.612167181646899, 0.6146761002685637, 0.6096747087200697, 0.6125810476877268)
clock <- c(0.1, 0.5, 1, 1.5, 2, 2.5, 3)
plot(clock ,MRT_1F, type="o",pch=4,
cex=2, col="black",
xlab= "Time between Things requests (s)",
ylab= "Response Time (s)",
cex.lab=1.0, cex.axis=1,
cex.main=2,
xlim = c(0,3),
ylim = c(0,600)
)
lines(x= clock,y = MRT_3F, type ="o", pch=0, col = "yellow")
lines(x= clock,y = MRT_5F, type ="o",pch=1, col = "red")
lines(x= clock,y = MRT_10F, type ="o",pch=2, col = "blue")
lines(x= clock,y = MRT_15F, type ="o",pch=5, col = "purple")
lines(x= clock,y = MRT_sem_F, type ="o", pch=6, col = "green")
legend("topright",
col= c("black","yellow","red","blue","purple","green"),
legend = c("1 Fog","3 Fogs","5 Fogs","10 Fogs","15 Fogs","w/o Fog"),
pch = c(4, 0, 1, 2, 5, 6),
lty = 1,
bty = "n",
x.intersp =0.5, y.intersp = 0.5)
#grafico em barras
par(mfrow = c(2, 3))
cores <- c("#E6E6E6", "#666666") # cinza claro e cinza escuro
barplot(rbind(MRT_sem_F, MRT_1F), beside = TRUE, col = cores, log = "y",
names.arg = clock, xlab = "Time between Things requests",
ylab = "Response time (s)", main = "1 Fog", ylim=c(0.1,600))
legend("topright", legend = c("w/o Fog", "1 Fog"), x.intersp =0.5, y.intersp = 0.5, fill = cores)
barplot(rbind(MRT_sem_F, MRT_3F), beside = TRUE, col = cores, log = "y",
names.arg = clock, xlab = "Time between Things requests",
ylab = "Response time (s)", main = "3 Fog")
legend("topright", legend = c("w/o Fog", "3 Fog"), x.intersp =0.5, y.intersp = 0.5, fill = cores)
barplot(rbind(MRT_sem_F, MRT_5F), beside = TRUE, col = cores, log = "y",
names.arg = clock, xlab = "Time between Things requests",
ylab = "Response time (s)", main = "5 Fog")
legend("topright", legend = c("w/o Fog", "5 Fog"), x.intersp =0.5, y.intersp = 0.5, fill = cores)
barplot(rbind(MRT_sem_F, MRT_10F), beside = TRUE, col = cores, log = "y",
names.arg = clock, xlab = "Time between Things requests",
ylab = "Response time (s)", main = "10 Fog")
legend("topright", legend = c("w/o Fog", "10 Fog"), x.intersp =0.5, y.intersp = 0.5,fill = cores)
barplot(rbind(MRT_sem_F, MRT_15F), beside = TRUE, col = cores, log = "y",
names.arg = clock, xlab = "Time between Things requests",
ylab = "Response time (s)", main = "15 Fog")
legend("topright", legend = c("w/o Fog", "15 Fog"), x.intersp =0.5, y.intersp = 0.5, fill = cores)
Questão 2
# Dados da tabela (valores em porcentagem)
MealPrice <- c("$10–19", "$20–29", "$30–39", "$40–49")
Qual.Rating <- c("Good", "Very Good", "Excellent")
Good <- c(53.8, 33.9,2.6, 0)
VeryGood <- c(43.6, 54.2, 60.5, 21.4)
Excellent <-c(2.6, 11.9, 36.8, 78.6)
# Criando a matriz de dados (linhas = qualidade, colunas = faixa de preço)
dados <- rbind(Good, VeryGood, Excellent)
# Nomeando as colunas (faixas de preço)
colnames(dados) <- MealPrice
# Transpor para empilhar por faixa de preço
dados_t <- t(dados)
# Cores
cores <- c("orange", "skyblue", "seagreen")
# Gráfico
barplot(dados, beside = FALSE, col = cores,
main = "Meal Price Range Quality Distribution",
xlab = "Meal Price",
ylab = "Quality Rating",
legend.text = TRUE,
args.legend = list(title = "Quality", x = "topright"))
Questão 3
# Dataset airquality já disponível no R
data("airquality")
# Filtrar apenas o mês de maio
maio <- subset(airquality, Month == 5)
# Converter temperatura de Fahrenheit para Celsius
temp_celsius <- (maio$Temp - 32) / 1.8
# Histograma com curva de densidade
hist(temp_celsius, breaks = 10, col = "lightblue", prob = TRUE,
main = "Histograma das Temperaturas em Maio (°C)",
xlab = "Temperatura (°C)",
ylab = "Densidade")
# Adicionar curva de densidade
lines(density(temp_celsius, na.rm = TRUE), col = "darkblue", lwd = 2)
Questão 4
# Carregar dados
sales <- read.table("https://training-course-material.com/images/8/8f/Sales.txt", header = TRUE)
str(sales)## 'data.frame': 6 obs. of 2 variables:
## $ COUNTRY: chr "US" "UK" "France" "Poland" ...
## $ SALES : int 340 290 510 820 120 780#proporções
pct <- round(sales$SALES/sum(sales$SALES)*100)
Ibis <- paste(sales$COUNTRY,pct)
Ibis <- paste(Ibis,"%",sep=" ")
# Criar gráfico de pizza
pie(pct,labels = Ibis, main= "Vendas no mundo", col = rainbow(6))
legend("topleft", legend = c(sales$COUNTRY), fill = rainbow(6))
Questão 5
# Questão 5
InsectSprays## count spray
## 1 10 A
## 2 7 A
## 3 20 A
## 4 14 A
## 5 14 A
## 6 12 A
## 7 10 A
## 8 23 A
## 9 17 A
## 10 20 A
## 11 14 A
## 12 13 A
## 13 11 B
## 14 17 B
## 15 21 B
## 16 11 B
## 17 16 B
## 18 14 B
## 19 17 B
## 20 17 B
## 21 19 B
## 22 21 B
## 23 7 B
## 24 13 B
## 25 0 C
## 26 1 C
## 27 7 C
## 28 2 C
## 29 3 C
## 30 1 C
## 31 2 C
## 32 1 C
## 33 3 C
## 34 0 C
## 35 1 C
## 36 4 C
## 37 3 D
## 38 5 D
## 39 12 D
## 40 6 D
## 41 4 D
## 42 3 D
## 43 5 D
## 44 5 D
## 45 5 D
## 46 5 D
## 47 2 D
## 48 4 D
## 49 3 E
## 50 5 E
## 51 3 E
## 52 5 E
## 53 3 E
## 54 6 E
## 55 1 E
## 56 1 E
## 57 3 E
## 58 2 E
## 59 6 E
## 60 4 E
## 61 11 F
## 62 9 F
## 63 15 F
## 64 22 F
## 65 15 F
## 66 16 F
## 67 13 F
## 68 10 F
## 69 26 F
## 70 26 F
## 71 24 F
## 72 13 Fstr(InsectSprays)## 'data.frame': 72 obs. of 2 variables:
## $ count: num 10 7 20 14 14 12 10 23 17 20 ...
## $ spray: Factor w/ 6 levels "A","B","C","D",..: 1 1 1 1 1 1 1 1 1 1 ...head(InsectSprays)## count spray
## 1 10 A
## 2 7 A
## 3 20 A
## 4 14 A
## 5 14 A
## 6 12 Aboxplot(count ~ spray, data=InsectSprays,
xlab = "Type of spray",
ylab = "Insect count",
main = "InsectSprays data",
outline=FALSE)
Questão 6
#diretório
setwd( "A:/UFRPE/RCAD/monitoringCloudData")
Data0.1 <- read.csv("monitoringCloudData_0.1.csv")
Data0.5 <- read.csv("monitoringCloudData_0.5.csv")
Data1.0 <- read.csv("monitoringCloudData_1.csv")
DataN <- read.csv("monitoringCloudData_NONE.csv")
head(Data0.1)## currentTime totalCpuUsage... totalMemory availableMemory
## 1 2020-01-28 19:05:24.696535 0 3.62GB 3.16GB
## 2 2020-01-28 19:06:24.960884 0 3.62GB 3.16GB
## 3 2020-01-28 19:07:25.178265 0 3.62GB 3.16GB
## 4 2020-01-28 19:08:25.422138 0 3.62GB 3.16GB
## 5 2020-01-28 19:09:25.684460 0 3.62GB 3.17GB
## 6 2020-01-28 19:10:25.946943 0 3.62GB 3.16GB
## usedMemory percentageMemory... totalSwap freeSwap usedSwap percentageSwap...
## 1 247.09MB 12.5 0.00B 0.00B 0.00B 0
## 2 247.34MB 12.5 0.00B 0.00B 0.00B 0
## 3 247.29MB 12.5 0.00B 0.00B 0.00B 0
## 4 247.02MB 12.5 0.00B 0.00B 0.00B 0
## 5 245.26MB 12.5 0.00B 0.00B 0.00B 0
## 6 247.49MB 12.5 0.00B 0.00B 0.00B 0
## totalPartition usedPartition freePartition percentagePartition...
## 1 9.78GB 5.33GB 3.94GB 57.5
## 2 9.78GB 5.33GB 3.94GB 57.5
## 3 9.78GB 5.33GB 3.94GB 57.5
## 4 9.78GB 5.33GB 3.94GB 57.5
## 5 9.78GB 5.33GB 3.94GB 57.5
## 6 9.78GB 5.33GB 3.94GB 57.5
## total_IO_read total_IO_write
## 1 291.32MB 6.74MB
## 2 291.32MB 7.05MB
## 3 291.32MB 7.25MB
## 4 291.32MB 7.47MB
## 5 291.32MB 7.71MB
## 6 291.32MB 7.96MBhead(Data0.5)## currentTime totalCpuUsage... totalMemory availableMemory
## 1 2020-01-28 15:14:55.878829 0.0 3.62GB 3.15GB
## 2 2020-01-28 15:15:56.127157 0.0 3.62GB 3.15GB
## 3 2020-01-28 15:16:56.385147 9.1 3.62GB 3.15GB
## 4 2020-01-28 15:17:56.647501 0.0 3.62GB 3.15GB
## 5 2020-01-28 15:18:56.910265 0.0 3.62GB 3.15GB
## 6 2020-01-28 15:19:57.172668 0.0 3.62GB 3.14GB
## usedMemory percentageMemory... totalSwap freeSwap usedSwap percentageSwap...
## 1 257.46MB 12.8 0.00B 0.00B 0.00B 0
## 2 261.70MB 12.9 0.00B 0.00B 0.00B 0
## 3 265.79MB 13.0 0.00B 0.00B 0.00B 0
## 4 266.47MB 13.1 0.00B 0.00B 0.00B 0
## 5 266.17MB 13.0 0.00B 0.00B 0.00B 0
## 6 269.06MB 13.1 0.00B 0.00B 0.00B 0
## totalPartition usedPartition freePartition percentagePartition...
## 1 9.78GB 5.34GB 3.93GB 57.6
## 2 9.78GB 5.34GB 3.93GB 57.6
## 3 9.78GB 5.34GB 3.93GB 57.6
## 4 9.78GB 5.34GB 3.93GB 57.6
## 5 9.78GB 5.34GB 3.93GB 57.6
## 6 9.78GB 5.34GB 3.93GB 57.6
## total_IO_read total_IO_write
## 1 292.50MB 15.57MB
## 2 292.50MB 15.79MB
## 3 292.50MB 16.07MB
## 4 292.50MB 16.38MB
## 5 292.50MB 16.46MB
## 6 292.50MB 16.70MBhead(Data1.0)## currentTime totalCpuUsage... totalMemory availableMemory
## 1 2020-01-28 21:16:18.220357 0 3.62GB 3.17GB
## 2 2020-01-28 21:17:18.482927 0 3.62GB 3.17GB
## 3 2020-01-28 21:18:18.700329 0 3.62GB 3.17GB
## 4 2020-01-28 21:19:18.963742 0 3.62GB 3.17GB
## 5 2020-01-28 21:20:19.212354 0 3.62GB 3.17GB
## 6 2020-01-28 21:21:19.474764 0 3.62GB 3.17GB
## usedMemory percentageMemory... totalSwap freeSwap usedSwap percentageSwap...
## 1 243.19MB 12.4 0.00B 0.00B 0.00B 0
## 2 242.52MB 12.4 0.00B 0.00B 0.00B 0
## 3 241.74MB 12.4 0.00B 0.00B 0.00B 0
## 4 241.23MB 12.4 0.00B 0.00B 0.00B 0
## 5 243.61MB 12.4 0.00B 0.00B 0.00B 0
## 6 242.70MB 12.4 0.00B 0.00B 0.00B 0
## totalPartition usedPartition freePartition percentagePartition...
## 1 9.78GB 5.39GB 3.88GB 58.1
## 2 9.78GB 5.39GB 3.88GB 58.1
## 3 9.78GB 5.39GB 3.88GB 58.1
## 4 9.78GB 5.39GB 3.88GB 58.1
## 5 9.78GB 5.39GB 3.88GB 58.1
## 6 9.78GB 5.39GB 3.88GB 58.1
## total_IO_read total_IO_write
## 1 292.33MB 14.85MB
## 2 292.33MB 15.06MB
## 3 292.33MB 15.31MB
## 4 292.33MB 15.51MB
## 5 292.33MB 15.73MB
## 6 292.33MB 15.96MBhead(DataN)## currentTime totalCpuUsage... totalMemory availableMemory
## 1 2020-01-28 15:37:52.452600 0.0 3.62GB 3.35GB
## 2 2020-01-28 15:38:52.718592 9.1 3.62GB 3.35GB
## 3 2020-01-28 15:39:52.981509 0.0 3.62GB 3.35GB
## 4 2020-01-28 15:40:53.245219 0.0 3.62GB 3.35GB
## 5 2020-01-28 15:41:53.509300 0.0 3.62GB 3.35GB
## 6 2020-01-28 15:42:53.773309 0.0 3.62GB 3.35GB
## usedMemory percentageMemory... totalSwap freeSwap usedSwap percentageSwap...
## 1 102.94MB 7.4 0.00B 0.00B 0.00B 0
## 2 103.36MB 7.4 0.00B 0.00B 0.00B 0
## 3 100.23MB 7.3 0.00B 0.00B 0.00B 0
## 4 100.19MB 7.3 0.00B 0.00B 0.00B 0
## 5 100.12MB 7.3 0.00B 0.00B 0.00B 0
## 6 100.01MB 7.3 0.00B 0.00B 0.00B 0
## totalPartition usedPartition freePartition percentagePartition...
## 1 9.78GB 5.28GB 3.98GB 57
## 2 9.78GB 5.28GB 3.98GB 57
## 3 9.78GB 5.28GB 3.98GB 57
## 4 9.78GB 5.28GB 3.98GB 57
## 5 9.78GB 5.28GB 3.98GB 57
## 6 9.78GB 5.28GB 3.98GB 57
## total_IO_read total_IO_write
## 1 84.64MB 1.65MB
## 2 84.65MB 2.10MB
## 3 84.65MB 2.26MB
## 4 84.71MB 2.77MB
## 5 84.71MB 2.85MB
## 6 84.71MB 2.96MB# é necessário ajustar a coluna “currentTime” para que o tempo fique contínuo
#e a coluna “usedMemory” para que todas as informações fiquem megabytes.
# Converter para data-hora
Data0.1$currentTime <- as.POSIXct(Data0.1$currentTime)
Data0.5$currentTime <- as.POSIXct(Data0.5$currentTime)
Data1.0$currentTime <- as.POSIXct(Data1.0$currentTime)
DataN$currentTime <- as.POSIXct(DataN$currentTime)
head(Data0.1$currentTime)## [1] "2020-01-28 19:05:24 -03" "2020-01-28 19:06:24 -03"
## [3] "2020-01-28 19:07:25 -03" "2020-01-28 19:08:25 -03"
## [5] "2020-01-28 19:09:25 -03" "2020-01-28 19:10:25 -03"head(Data0.5)## currentTime totalCpuUsage... totalMemory availableMemory usedMemory
## 1 2020-01-28 0.0 3.62GB 3.15GB 257.46MB
## 2 2020-01-28 0.0 3.62GB 3.15GB 261.70MB
## 3 2020-01-28 9.1 3.62GB 3.15GB 265.79MB
## 4 2020-01-28 0.0 3.62GB 3.15GB 266.47MB
## 5 2020-01-28 0.0 3.62GB 3.15GB 266.17MB
## 6 2020-01-28 0.0 3.62GB 3.14GB 269.06MB
## percentageMemory... totalSwap freeSwap usedSwap percentageSwap...
## 1 12.8 0.00B 0.00B 0.00B 0
## 2 12.9 0.00B 0.00B 0.00B 0
## 3 13.0 0.00B 0.00B 0.00B 0
## 4 13.1 0.00B 0.00B 0.00B 0
## 5 13.0 0.00B 0.00B 0.00B 0
## 6 13.1 0.00B 0.00B 0.00B 0
## totalPartition usedPartition freePartition percentagePartition...
## 1 9.78GB 5.34GB 3.93GB 57.6
## 2 9.78GB 5.34GB 3.93GB 57.6
## 3 9.78GB 5.34GB 3.93GB 57.6
## 4 9.78GB 5.34GB 3.93GB 57.6
## 5 9.78GB 5.34GB 3.93GB 57.6
## 6 9.78GB 5.34GB 3.93GB 57.6
## total_IO_read total_IO_write
## 1 292.50MB 15.57MB
## 2 292.50MB 15.79MB
## 3 292.50MB 16.07MB
## 4 292.50MB 16.38MB
## 5 292.50MB 16.46MB
## 6 292.50MB 16.70MBhead(Data1.0)## currentTime totalCpuUsage... totalMemory availableMemory usedMemory
## 1 2020-01-28 21:16:18 0 3.62GB 3.17GB 243.19MB
## 2 2020-01-28 21:17:18 0 3.62GB 3.17GB 242.52MB
## 3 2020-01-28 21:18:18 0 3.62GB 3.17GB 241.74MB
## 4 2020-01-28 21:19:18 0 3.62GB 3.17GB 241.23MB
## 5 2020-01-28 21:20:19 0 3.62GB 3.17GB 243.61MB
## 6 2020-01-28 21:21:19 0 3.62GB 3.17GB 242.70MB
## percentageMemory... totalSwap freeSwap usedSwap percentageSwap...
## 1 12.4 0.00B 0.00B 0.00B 0
## 2 12.4 0.00B 0.00B 0.00B 0
## 3 12.4 0.00B 0.00B 0.00B 0
## 4 12.4 0.00B 0.00B 0.00B 0
## 5 12.4 0.00B 0.00B 0.00B 0
## 6 12.4 0.00B 0.00B 0.00B 0
## totalPartition usedPartition freePartition percentagePartition...
## 1 9.78GB 5.39GB 3.88GB 58.1
## 2 9.78GB 5.39GB 3.88GB 58.1
## 3 9.78GB 5.39GB 3.88GB 58.1
## 4 9.78GB 5.39GB 3.88GB 58.1
## 5 9.78GB 5.39GB 3.88GB 58.1
## 6 9.78GB 5.39GB 3.88GB 58.1
## total_IO_read total_IO_write
## 1 292.33MB 14.85MB
## 2 292.33MB 15.06MB
## 3 292.33MB 15.31MB
## 4 292.33MB 15.51MB
## 5 292.33MB 15.73MB
## 6 292.33MB 15.96MBhead(DataN)## currentTime totalCpuUsage... totalMemory availableMemory usedMemory
## 1 2020-01-28 15:37:52 0.0 3.62GB 3.35GB 102.94MB
## 2 2020-01-28 15:38:52 9.1 3.62GB 3.35GB 103.36MB
## 3 2020-01-28 15:39:52 0.0 3.62GB 3.35GB 100.23MB
## 4 2020-01-28 15:40:53 0.0 3.62GB 3.35GB 100.19MB
## 5 2020-01-28 15:41:53 0.0 3.62GB 3.35GB 100.12MB
## 6 2020-01-28 15:42:53 0.0 3.62GB 3.35GB 100.01MB
## percentageMemory... totalSwap freeSwap usedSwap percentageSwap...
## 1 7.4 0.00B 0.00B 0.00B 0
## 2 7.4 0.00B 0.00B 0.00B 0
## 3 7.3 0.00B 0.00B 0.00B 0
## 4 7.3 0.00B 0.00B 0.00B 0
## 5 7.3 0.00B 0.00B 0.00B 0
## 6 7.3 0.00B 0.00B 0.00B 0
## totalPartition usedPartition freePartition percentagePartition...
## 1 9.78GB 5.28GB 3.98GB 57
## 2 9.78GB 5.28GB 3.98GB 57
## 3 9.78GB 5.28GB 3.98GB 57
## 4 9.78GB 5.28GB 3.98GB 57
## 5 9.78GB 5.28GB 3.98GB 57
## 6 9.78GB 5.28GB 3.98GB 57
## total_IO_read total_IO_write
## 1 84.64MB 1.65MB
## 2 84.65MB 2.10MB
## 3 84.65MB 2.26MB
## 4 84.71MB 2.77MB
## 5 84.71MB 2.85MB
## 6 84.71MB 2.96MBconvert_to_mb <- function(x) {
x <- gsub(" ", "", x) # remove espaços
num <- as.numeric(sub("[A-Za-z]+", "", x))
unit <- toupper(gsub("[0-9.]", "", x))
ifelse(unit == "GB", num * 1024, num)
}
# Função para converter qualquer unidade (TB, GB, MB) para MB
convert_to_mb <- function(x) {
x <- gsub(" ", "", x) # remove espaços
num <- as.numeric(sub("[A-Za-z]+", "", x))
unit <- toupper(gsub("[0-9.]", "", x))
converted <- ifelse(unit == "TB", num * 1e6,
ifelse(unit == "GB", num * 1024,
ifelse(unit == "MB", num, NA)))
return(converted)
}
Data0.1$usedMemory_MB <- convert_to_mb(Data0.1$usedMemory)
Data0.5$usedMemory_MB <- convert_to_mb(Data0.5$usedMemory)
Data1.0$usedMemory_MB <- convert_to_mb(Data1.0$usedMemory)
DataN$usedMemory_MB <- convert_to_mb(DataN$usedMemory)
# Converter para POSIXct
Data0.1$currentTime <- as.POSIXct(Data0.1$currentTime)
Data0.5$currentTime <- as.POSIXct(Data0.5$currentTime)
Data1.0$currentTime <- as.POSIXct(Data1.0$currentTime)
DataN$currentTime <- as.POSIXct(DataN$currentTime)
# Calcular tempo decorrido em horas (a partir da primeira observação)
Data0.1$time_hr <- as.numeric(difftime(Data0.1$currentTime, Data0.1$currentTime[1], units = "hours"))
Data0.5$time_hr <- as.numeric(difftime(Data0.5$currentTime, Data0.5$currentTime[1], units = "hours"))
Data1.0$time_hr <- as.numeric(difftime(Data1.0$currentTime, Data1.0$currentTime[1], units = "hours"))
DataN$time_hr <- as.numeric(difftime(DataN$currentTime, DataN$currentTime[1], units = "hours"))
# Definir layout: 2 linhas, 2 colunas
layout(matrix(1:4, nrow = 2, ncol = 2))
# Gráfico 1
plot(Data0.1$time_hr, Data0.1$usedMemory_MB, type = "l", col = "blue",
xlab = "Time (hour)", ylab = "Used Memory (MB)",
main = "Memory Analysis (Workload of 0.1)")
# Gráfico 2
plot(Data0.5$time_hr, Data0.5$usedMemory_MB, type = "l", col = "green",
xlab = "Time (hour)", ylab = "Used Memory (MB)",
main = "Memory Analysis (Workload of 0.5)")
# Gráfico 3
plot(Data1.0$time_hr, Data1.0$usedMemory_MB, type = "l", col = "red",
xlab = "Time (hour)", ylab = "Used Memory (MB)",
main = "Memory Analysis (Workload of 1.0)")
# Gráfico 4
plot(DataN$time_hr, DataN$usedMemory_MB, type = "l", col = "purple",
xlab = "Time (hour)", ylab = "Used Memory (MB)",
main = "Memory Analysis (None Workload)")
Questão 7
library(dplyr)## Warning: package 'dplyr' was built under R version 4.2.3##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(plotly)## Warning: package 'plotly' was built under R version 4.2.3## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 4.2.3##
## Attaching package: 'plotly'## The following object is masked from 'package:ggplot2':
##
## last_plot## The following object is masked from 'package:stats':
##
## filter## The following object is masked from 'package:graphics':
##
## layout# diretório
setwd( "A:/UFRPE/RCAD")
netflix <- read.csv("netflix_titles.csv")
head(netflix)## show_id type title director
## 1 s1 TV Show 3%
## 2 s2 Movie 7:19 Jorge Michel Grau
## 3 s3 Movie 23:59 Gilbert Chan
## 4 s4 Movie 9 Shane Acker
## 5 s5 Movie 21 Robert Luketic
## 6 s6 TV Show 46 Serdar Akar
## cast
## 1 João Miguel, Bianca Comparato, Michel Gomes, Rodolfo Valente, Vaneza Oliveira, Rafael Lozano, Viviane Porto, Mel Fronckowiak, Sergio Mamberti, Zezé Motta, Celso Frateschi
## 2 Demián Bichir, Héctor Bonilla, Oscar Serrano, Azalia Ortiz, Octavio Michel, Carmen Beato
## 3 Tedd Chan, Stella Chung, Henley Hii, Lawrence Koh, Tommy Kuan, Josh Lai, Mark Lee, Susan Leong, Benjamin Lim
## 4 Elijah Wood, John C. Reilly, Jennifer Connelly, Christopher Plummer, Crispin Glover, Martin Landau, Fred Tatasciore, Alan Oppenheimer, Tom Kane
## 5 Jim Sturgess, Kevin Spacey, Kate Bosworth, Aaron Yoo, Liza Lapira, Jacob Pitts, Laurence Fishburne, Jack McGee, Josh Gad, Sam Golzari, Helen Carey, Jack Gilpin
## 6 Erdal Beşikçioğlu, Yasemin Allen, Melis Birkan, Saygın Soysal, Berkan Şal, Metin Belgin, Ayça Eren, Selin Uludoğan, Özay Fecht, Suna Yıldızoğlu
## country date_added release_year rating duration
## 1 Brazil August 14, 2020 2020 TV-MA 4 Seasons
## 2 Mexico December 23, 2016 2016 TV-MA 93 min
## 3 Singapore December 20, 2018 2011 R 78 min
## 4 United States November 16, 2017 2009 PG-13 80 min
## 5 United States January 1, 2020 2008 PG-13 123 min
## 6 Turkey July 1, 2017 2016 TV-MA 1 Season
## listed_in
## 1 International TV Shows, TV Dramas, TV Sci-Fi & Fantasy
## 2 Dramas, International Movies
## 3 Horror Movies, International Movies
## 4 Action & Adventure, Independent Movies, Sci-Fi & Fantasy
## 5 Dramas
## 6 International TV Shows, TV Dramas, TV Mysteries
## description
## 1 In a future where the elite inhabit an island paradise far from the crowded slums, you get one chance to join the 3% saved from squalor.
## 2 After a devastating earthquake hits Mexico City, trapped survivors from all walks of life wait to be rescued while trying desperately to stay alive.
## 3 When an army recruit is found dead, his fellow soldiers are forced to confront a terrifying secret that's haunting their jungle island training camp.
## 4 In a postapocalyptic world, rag-doll robots hide in fear from dangerous machines out to exterminate them, until a brave newcomer joins the group.
## 5 A brilliant group of students become card-counting experts with the intent of swindling millions out of Las Vegas casinos by playing blackjack.
## 6 A genetics professor experiments with a treatment for his comatose sister that blends medical and shamanic cures, but unlocks a shocking side effect.# Top países com mais conteúdo em 2019
netflix_clean <- netflix %>%
filter(country != "", !is.na(country)) %>%
filter(!grepl(",", country))
top_countries <- netflix_clean %>%
group_by(country) %>%
summarise(total = n()) %>%
arrange(desc(total)) %>%
slice_head(n = 10)
str(top_countries)## tibble [10 × 2] (S3: tbl_df/tbl/data.frame)
## $ country: chr [1:10] "United States" "India" "United Kingdom" "Japan" ...
## $ total : int [1:10] 2555 923 397 226 183 177 134 115 101 100plot_ly(top_countries, labels = ~country, values = ~total, type = 'pie') %>%
layout(title = 'Top 10 países com mais conteúdos na Netflix (2019)',
legend = list(orientation = 'h', x = 0.1, y = -0.2))Questão 8
plot_ly(
type = 'table',
header = list(
values = c("País", "Total de conteúdos"),
align = c("center", "center"),
fill = list(color = "gray"),
font = list(color = "white", size = 14)
),
cells = list(
values = list(top_countries$country, top_countries$total),
align = "center"
)
)Questão 9
netflix_decade <- netflix %>%
filter(!is.na(release_year), release_year >= 1900) %>%
mutate(decade = floor(release_year / 10) * 10)
conteudo_por_decada <- netflix_decade %>%
group_by(decade, type) %>%
summarise(total = n(), .groups = "drop")
series <- conteudo_por_decada %>% filter(type == "TV Show")
filmes <- conteudo_por_decada %>% filter(type == "Movie")
library(plotly)
plot_ly() %>%
add_trace(data = series,
x = ~decade,
y = ~total,
type = 'scatter',
mode = 'lines+markers',
name = 'Séries',
line = list(color = 'blue')) %>%
add_trace(data = filmes,
x = ~decade,
y = ~total,
type = 'scatter',
mode = 'lines+markers',
name = 'Filmes',
line = list(color = 'yellow')) %>%
layout(title = "Quantidade de Conteúdos por Década na Netflix",
xaxis = list(title = "Década"),
yaxis = list(title = "Quantidade de Conteúdo"),
legend = list(x = 0.1, y = 1))Questão 10
# Carregar pacotes
library(dplyr)
library(tidyr)## Warning: package 'tidyr' was built under R version 4.2.3library(plotly)
# Carregar os dados
netflix <- read.csv("netflix_titles.csv")
# Preparar os dados: só filmes, anos de 2000 a 2010, e extrair o primeiro gênero
netflix_filmes <- netflix %>%
filter(type == "Movie",
!is.na(release_year),
release_year >= 2000 & release_year <= 2010,
!is.na(listed_in)) %>%
mutate(first_genre = sub(",.*", "", listed_in)) # pegar o primeiro gênero
# Filtrar apenas os gêneros desejados
generos_desejados <- c("Dramas", "Action & Adventure", "Comedies")
# Contar por ano e gênero
dados_genero <- netflix_filmes %>%
filter(first_genre %in% generos_desejados) %>%
group_by(release_year, first_genre) %>%
summarise(total = n(), .groups = "drop")
# Expandir todos os anos e gêneros (mesmo se total for 0)
todos_anos <- 2000:2010
dados_completos <- expand.grid(release_year = todos_anos, first_genre = generos_desejados) %>%
left_join(dados_genero, by = c("release_year", "first_genre")) %>%
mutate(total = ifelse(is.na(total), 0, total)) # preencher zeros
# Reestruturar para colunas por gênero
dados_genero_wide <- dados_completos %>%
pivot_wider(names_from = first_genre, values_from = total)
# Criar gráfico de barras lado a lado com Plotly
plot_ly(dados_genero_wide, x = ~release_year) %>%
add_trace(y = ~`Dramas`, name = 'Dramas', type = 'bar', marker = list(color = 'blue')) %>%
add_trace(y = ~`Action & Adventure`, name = 'Action & Adventure', type = 'bar', marker = list(color = 'orange')) %>%
add_trace(y = ~`Comedies`, name = 'Comedies', type = 'bar', marker = list(color = 'green')) %>%
layout(
barmode = 'group',
title = 'Quantidade de Filmes por Gênero (2000–2010)',
xaxis = list(title = 'Ano'),
yaxis = list(title = 'Quantidade de Filmes')
)