Questões
Questão 1
# dados
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)
layout(matrix(c(1,1,
2,3,
4,5,
6,7),
nrow = 4, byrow = TRUE),
heights = c(3, 2, 2, 2)
)
# margens
par(mar = c(4,4,3,2))
# linhas
plot(clock, MRT_1F,
type = "o",
pch = 4,
col = "black",
ylim = c(0, max(MRT_1F)),
xlab = "Time Between Things requests (seconds)",
ylab = "Response Time (sec.)")
lines(clock, MRT_3F, type = "o", pch = 9, col = "yellow")
lines(clock, MRT_5F, type = "o", pch = 1, col = "red")
lines(clock, MRT_10F, type = "o", pch = 5, col = "blue")
lines(clock, MRT_15F, type = "o", pch = 16, col = "purple")
lines(clock, MRT_sem_F, type = "o", pch = 4, col = "green")
legend("topright",
legend = c("1 Fog", "3 Fogs", "5 Fogs",
"10 Fogs", "15 Fogs", "w/o Fog"),
col = c("black", "yellow", "red",
"blue", "purple", "green"),
lty = 1,
pch = c(4,9,1,5,16,4),
cex = 0.8)
# barras
cores <- c("#E6E6E6", "#666666")
# função auxiliar para gerar os gráficos de barras
grafico_barras <- function(dados, titulo){
par(mar = c(4,4,2,1))
barplot(rbind(MRT_sem_F, dados),
beside = TRUE,
col = cores,
log = "y",
names.arg = clock,
xlab = "Requests interval (s)",
ylab = "Response Time (s)"
)
legend("topright",
legend = c("w/o Fog", titulo),
fill = cores,
cex = 0.8)
}
grafico_barras(MRT_1F, "1 Fog")
grafico_barras(MRT_3F, "3 Fogs")
grafico_barras(MRT_5F, "5 Fogs")
grafico_barras(MRT_10F, "10 Fogs")
grafico_barras(MRT_15F, "15 Fogs")
Questão 2
# dados da tabela
dados <- matrix(c(
53.8, 33.9, 2.6, 0.0, # good
43.6, 54.2, 60.5, 21.4, # very good
2.6, 11.9, 36.8, 78.6 # excellent
),
nrow = 3,
byrow = TRUE)
# nomes das linhas e colunas
rownames(dados) <- c("Good", "Very Good", "Excellent")
colnames(dados) <- c("$10–19", "$20–29", "$30–39", "$40–49")
barplot(dados,
beside = FALSE, # empilhado
col = c("lightblue", "gold", "lightgreen"),
main = "Meal Quality Rating by Price Category",
xlab = "Meal Price",
ylab = "Percentage (%)",
ylim = c(0, 100))
legend("topright",
legend = rownames(dados),
fill = c("lightblue", "gold", "lightgreen"),
title = "Quality Rating")
Questão 3
# carregar dataset
data(airquality)
# filtrar apenas o mês de maio
maio <- subset(airquality, Month == 5)
# converter temperatura de fahrenheit para celsius
temp_celsius <- (maio$Temp - 32) / 1.8
# criar histograma
hist(temp_celsius,
probability = TRUE,
col = "lightblue",
border = "white",
main = "Histograma das Temperaturas de Maio",
xlab = "Temperatura (°C)",
ylab = "Densidade")
# adicionar curva de densidade
lines(density(temp_celsius),
lwd = 2)
# adicionar linha da média
abline(v = mean(temp_celsius),
lwd = 2,
lty = 2)
Questão 4
# ler dataset
sales <- read.table(
"https://training-course-material.com/images/8/8f/Sales.txt",
header = TRUE
)
# calcular porcentagens
porcentagem <- round((sales$SALES / sum(sales$SALES)) * 100, 1)
# criar rótulos com porcentagem
rotulos <- paste(sales$COUNTRY, "-", porcentagem, "%")
# definir cores
cores <- c("lightblue", "lightgreen", "pink",
"orange", "violet", "yellow")
# criar gráfico de pizza
pie(sales$SALES,
labels = rotulos,
col = cores,
main = "Porcentagem Total de Vendas por País")
# adicionar legenda
legend("topright",
legend = sales$COUNTRY,
fill = cores,
title = "Países")
Questão 5
# carregar dataset
data(InsectSprays)
boxplot(count ~ spray,
data = InsectSprays,
outline = F, # remove visualização dos outliers
col = "yellow",
main = "Contagem de Insetos por Tipo de Inseticida",
xlab = "Tipo de Inseticida",
ylab = "Quantidade de Insetos")
Questão 6
# lendo os dados
cloud_none <- read.csv("monitoringCloudData_NONE.csv")
cloud_01 <- read.csv("monitoringCloudData_0.1.csv")
cloud_05 <- read.csv("monitoringCloudData_0.5.csv")
cloud_10 <- read.csv("monitoringCloudData_1.csv")
converter_para_mb <- function(x){
valor <- as.numeric(gsub("[A-Z]+", "", x))
unidade <- gsub("[0-9.]", "", x)
resultado <- ifelse(unidade == "TB", valor * 1000000,
ifelse(unidade == "GB", valor * 1024,
ifelse(unidade == "MB", valor,
ifelse(unidade == "KB", valor / 1024,
ifelse(unidade == "B", valor / (1024^2),
NA)))))
return(resultado)
}
preparar_dados <- function(df){
# converter currentTime para datetime
df$currentTime <- as.POSIXct(df$currentTime,
format="%Y-%m-%d %H:%M:%S")
tempo_inicial <- df$currentTime[1]
df$timeHour <- as.numeric(
difftime(df$currentTime,
tempo_inicial,
units = "hours")
)
# converter usedMemory para MB
df$usedMemoryMB <- converter_para_mb(df$usedMemory)
return(df)
}
cloud_none <- preparar_dados(cloud_none)
cloud_01 <- preparar_dados(cloud_01)
cloud_05 <- preparar_dados(cloud_05)
cloud_10 <- preparar_dados(cloud_10)
# organizando os gráficos
layout(matrix(c(1,2,
3,4),
nrow = 2,
byrow = TRUE))
par(mar = c(4,4,3,1))
# none
plot(cloud_none$timeHour,
cloud_none$usedMemoryMB,
type = "l",
lwd = 2,
main = "Memory Analysis (None Workload)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)")
# 0.1
plot(cloud_01$timeHour,
cloud_01$usedMemoryMB,
type = "l",
lwd = 2,
main = "Memory Analysis (Workload of 0.1)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)")
# 0.5
plot(cloud_05$timeHour,
cloud_05$usedMemoryMB,
type = "l",
lwd = 2,
main = "Memory Analysis (Workload of 0.5)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)")
# 1.0
plot(cloud_10$timeHour,
cloud_10$usedMemoryMB,
type = "l",
lwd = 2,
main = "Memory Analysis (Workload of 1.0)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)")
Questão 7
#install.packages("plotly")
library(plotly)
netflix <- read.csv("netflix_titles.csv")
netflix <- subset(
netflix,
!is.na(country) &
trimws(country) != "" &
!grepl(",", country)
)
# contando conteúdos por país
country_count <- sort(
table(netflix$country),
decreasing = TRUE
)
# selecionando top10 países
top10 <- head(country_count, 10)
# gráfico de pizza
plot_ly(
labels = names(top10),
values = as.numeric(top10),
type = "pie",
textinfo = "label+percent",
insidetextorientation = "radial"
) %>%
layout(
title = "Top 10 Países com Mais Conteúdo na Netflix",
legend = list(title = list(text = "<b>Países</b>"))
)
Questão 8
library(plotly)
netflix <- read.csv(
"netflix_titles.csv",
stringsAsFactors = FALSE
)
netflix <- netflix[
netflix$country != "" &
!is.na(netflix$country) &
!grepl(",", netflix$country),
]
country_count <- sort(
table(trimws(netflix$country)),
decreasing = TRUE
)
top10 <- head(country_count, 10)
top10_df <- data.frame(
Pais = names(top10),
Total = as.numeric(top10),
stringsAsFactors = FALSE
)
plot_ly(
type = "table",
header = list(
values = c("País", "Total de conteúdos"),
fill = list(color = "gray"),
font = list(color = "white", size = 14),
align = "center"
),
cells = list(
values = list(
top10_df$Pais,
top10_df$Total
),
fill = list(color = "white"),
align = "center",
font = list(color = "black", size = 12)
)
)
Questão 9
library(plotly)
netflix <- read.csv(
"netflix_titles.csv",
stringsAsFactors = FALSE
)
netflix$decade <- floor(netflix$release_year / 10) * 10
movies <- netflix[netflix$type == "Movie", ]
tvshows <- netflix[netflix$type == "TV Show", ]
movies_count <- table(movies$decade)
tvshows_count <- table(tvshows$decade)
movies_df <- data.frame(
decade = as.numeric(names(movies_count)),
total = as.numeric(movies_count)
)
tvshows_df <- data.frame(
decade = as.numeric(names(tvshows_count)),
total = as.numeric(tvshows_count)
)
decadas <- sort(unique(netflix$decade))
plot_ly() %>%
add_lines(
data = tvshows_df,
x = ~decade,
y = ~total,
name = "TV Series",
line = list(color = "blue"),
mode = "lines+markers"
) %>%
add_lines(
data = movies_df,
x = ~decade,
y = ~total,
name = "Movies",
line = list(color = "yellow"),
mode = "lines+markers"
) %>%
layout(
xaxis = list(
title = "Década",
tickmode = "array",
tickvals = decadas,
ticktext = decadas
),
yaxis = list(
title = "Quantidade de Conteúdo"
)
)
Questão 10
library(plotly)
netflix <- read.csv(
"netflix_titles.csv",
stringsAsFactors = FALSE
)
movies <- netflix[
netflix$type == "Movie" &
netflix$release_year >= 2000 &
netflix$release_year <= 2010,
]
movies$main_genre <- trimws(
sub(",.*", "", movies$listed_in)
)
genres <- c("Dramas", "Action & Adventure", "Comedies")
movies_filtered <- movies[
movies$main_genre %in% genres,
]
count_data <- table(
movies_filtered$release_year,
movies_filtered$main_genre
)
count_df <- as.data.frame(count_data)
colnames(count_df) <- c("year", "genre", "total")
dramas_df <- count_df[count_df$genre == "Dramas", ]
action_df <- count_df[count_df$genre == "Action & Adventure", ]
comedy_df <- count_df[count_df$genre == "Comedies", ]
plot_ly() %>%
add_bars(
data = dramas_df,
x = ~year,
y = ~total,
name = "Drama"
) %>%
add_bars(
data = action_df,
x = ~year,
y = ~total,
name = "Ação e Aventura"
) %>%
add_bars(
data = comedy_df,
x = ~year,
y = ~total,
name = "Comédia"
) %>%
layout(
xaxis = list(
title = "Ano de Lançamento"
),
yaxis = list(
title = "Qnt. de Lançamentos"
),
barmode = "group"
)