Visualização de dados
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)
layout(1)
par(mar = c(4, 4, 2, 2))
max_x <- max(clock)
max_y <- max(c(MRT_1F, MRT_3F, MRT_5F, MRT_10F, MRT_15F, MRT_sem_F))
plot(clock, MRT_1F,
type = "b",
pch = 4,
col = "black",
xlab = "Time between Things requests (seconds)",
ylab = "Response Time (sec.)",
ylim = c(0, max_y),
xlim = c(0, max_x))
lines(clock, MRT_3F, type = "b", pch = 9, col = "yellow")
lines(clock, MRT_5F, type = "b", pch = 1, col = "red")
lines(clock, MRT_10F, type = "b", pch = 2, col = "blue")
lines(clock, MRT_15F, type = "b", pch = 5, col = "purple")
lines(clock, MRT_sem_F, type = "b", 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"),
pch = c(4, 9, 1, 2, 5, 4),
lty = 1,
bty = "n")
cores_barra <- c("#E6E6E6", "#666666")
layout(matrix(c(1, 2,
3, 4,
5, 0),
nrow = 3,
ncol = 2,
byrow = TRUE))
par(mar = c(4.5, 4.5, 2.5, 1))
dados_plot1 <- rbind(MRT_sem_F, MRT_1F)
barplot(dados_plot1,
beside = TRUE,
log = "y",
col = cores_barra,
names.arg = clock,
xlab = "Time between Things requests",
ylab = "Response time (s)")
legend("topright", legend = c("w/o Fog", "1 Fog"), fill = cores_barra, bty = "n")
dados_plot2 <- rbind(MRT_sem_F, MRT_3F)
barplot(dados_plot2,
beside = TRUE,
log = "y",
col = cores_barra,
names.arg = clock,
xlab = "Time between Things requests",
ylab = "Response time (s)")
legend("topright", legend = c("w/o Fog", "3 Fogs"), fill = cores_barra, bty = "n")
dados_plot3 <- rbind(MRT_sem_F, MRT_5F)
barplot(dados_plot3,
beside = TRUE,
log = "y",
col = cores_barra,
names.arg = clock,
xlab = "Time between Things requests",
ylab = "Response time (s)")
legend("topright", legend = c("w/o Fog", "5 Fogs"), fill = cores_barra, bty = "n")
dados_plot4 <- rbind(MRT_sem_F, MRT_10F)
barplot(dados_plot4,
beside = TRUE,
log = "y",
col = cores_barra,
names.arg = clock,
xlab = "Time between Things requests",
ylab = "Response time (s)")
legend("topright", legend = c("w/o Fog", "10 Fogs"), fill = cores_barra, bty = "n")
dados_plot5 <- rbind(MRT_sem_F, MRT_15F)
barplot(dados_plot5,
beside = TRUE,
log = "y",
col = cores_barra,
names.arg = clock,
xlab = "Time between Things requests",
ylab = "Response time (s)")
legend("topright", legend = c("w/o Fog", "15 Fogs"), fill = cores_barra, bty = "n")
layout(1)
Questão 2
price_10_19 <- c(53.8, 43.6, 2.6)
price_20_29 <- c(33.9, 54.2, 11.9)
price_30_39 <- c(2.6, 60.5, 36.8)
price_40_49 <- c(0, 21.4, 78.6)
dados_matriz <- cbind(
price_10_19,
price_20_29,
price_30_39,
price_40_49
)
precos_labels <- c("$10–19", "$20–29", "$30–39", "$40–49")
qualidade_labels <- c("Good", "Very Good", "Excellent")
cores <- c("#6D926D", "#4F794F", "#3B603B")
somas_cumulativas <- apply(dados_matriz, 2, cumsum)
posicoes_y <- somas_cumulativas - (dados_matriz / 2)
labels_sem_zero <- ifelse(dados_matriz == 0, NA, paste0(dados_matriz, "%"))
bar_p <- barplot(
height = dados_matriz,
main = "Qualidade da Refeição por Categoria de Preço",
xlab = "Categoria de Preço",
ylab = "Percentual (%)",
names.arg = precos_labels,
col = cores,
legend.text = qualidade_labels,
ylim = c(0, 100),
args.legend = list(x = "topright", title = "Qualidade")
)
text(
x = rep(bar_p, each = nrow(dados_matriz)),
y = as.vector(posicoes_y),
labels = as.vector(labels_sem_zero),
col = "white",
cex = 0.8
)
Questão 3
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.1 ✔ stringr 1.5.2
## ✔ ggplot2 4.0.0 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.2.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
data("airquality")
result <- airquality %>%
filter(Month==5) %>%
mutate(temp_celsius = (Temp - 32)/1.8) %>%
select(Day, temp_celsius)
hist(
result$temp_celsius,
main = "Histograma da Temperatura em Maio (°C)",
xlab = "Temperatura (°C)",
ylab = "Dias",
col = "lightblue"
)
Questão 4
sales <- read.table("https://training-course-material.com/images/8/8f/Sales.txt",header=TRUE)
percentagens <- round(100 * sales$SALES / sum(sales$SALES), 1)
labels <- paste0(percentagens, "%")
cores <- rainbow(length(sales$SALES))
pie(
sales$SALES,
labels = labels,
col = cores,
main = "Percentual de Vendas por País"
)
legend(
"topright",
legend = sales$COUNTRY,
fill = cores,
title = "Países"
)
Questão 5
data("InsectSprays")
boxplot(
count ~ spray,
data = InsectSprays,
outline = FALSE,
main = "Contagem de Insetos por Tipo de Inseticida",
xlab = "Tipo de Inseticida",
ylab = "Número de Insetos",
col = "yellow"
)
Questão 6
convert_to_MB <- function(valor_str) {
valor_num <- as.numeric(gsub("[A-Za-z ]", "", valor_str))
unidade <- gsub("[0-9., ]", "", valor_str)
unidade <- toupper(unidade)
resultado <- switch (unidade,
"TB" = valor_num * 1000000,
"GB" = valor_num * 1024,
"MB" = valor_num,
NA
)
return (resultado)
}
layout(matrix(c(1, 2,
3, 4),
nrow = 2,
ncol = 2,
byrow = TRUE))
mem_none_w <- read.csv("monitoringCloudData_NONE.csv")
plot_data_none_w <- mem_none_w %>%
mutate(used_memory_mb = sapply(usedMemory, convert_to_MB)) %>%
mutate(time_diff_in_hour = as.numeric(difftime(currentTime, mem_none_w$currentTime[1], units="hours"))) %>%
select(time_diff_in_hour,used_memory_mb)
plot(
plot_data_none_w$time_diff_in_hour,
plot_data_none_w$used_memory_mb,
type="l",
main = "Memory Analysis (None Workload)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)",
)
mem_01_w <- read.csv("monitoringCloudData_0.1.csv")
plot_data_01_w <- mem_01_w %>%
mutate(used_memory_mb = sapply(usedMemory, convert_to_MB)) %>%
mutate(time_diff_in_hour = as.numeric(difftime(currentTime, mem_01_w$currentTime[1], units="hours"))) %>%
select(time_diff_in_hour,used_memory_mb)
plot(
plot_data_01_w$time_diff_in_hour,
plot_data_01_w$used_memory_mb,
type="l",
main = "Memory Analysis (Workload of 0.1)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)",
)
mem_05_w <- read.csv("monitoringCloudData_0.5.csv")
plot_data_05_w <- mem_05_w %>%
mutate(used_memory_mb = sapply(usedMemory, convert_to_MB)) %>%
mutate(time_diff_in_hour = as.numeric(difftime(currentTime, mem_05_w$currentTime[1], units="hours"))) %>%
select(time_diff_in_hour,used_memory_mb)
plot(
plot_data_05_w$time_diff_in_hour,
plot_data_05_w$used_memory_mb,
type="l",
main = "Memory Analysis (Workload of 0.5)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)",
)
mem_1_w <- read.csv("monitoringCloudData_1.csv")
plot_data_1_w <- mem_1_w %>%
mutate(used_memory_mb = sapply(usedMemory, convert_to_MB)) %>%
mutate(time_diff_in_hour = as.numeric(difftime(currentTime, mem_1_w$currentTime[1], units="hours"))) %>%
select(time_diff_in_hour,used_memory_mb)
plot(
plot_data_1_w$time_diff_in_hour,
plot_data_1_w$used_memory_mb,
type="l",
main = "Memory Analysis (Workload of 1.0)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)",
)
Questão 7
library(tidyverse)
library(plotly)
##
## Anexando pacote: 'plotly'
## O seguinte objeto é mascarado por 'package:ggplot2':
##
## last_plot
## O seguinte objeto é mascarado por 'package:stats':
##
## filter
## O seguinte objeto é mascarado por 'package:graphics':
##
## layout
netflix_titles <- read.csv("netflix_titles.csv")
netflix_one_country <- netflix_titles %>%
filter(!grepl(",",country), country != "")
top_10_countries <- netflix_one_country %>%
count(country, sort = TRUE, name = "contagem") %>%
slice_head(n = 10)
fig <- plot_ly(
data = top_10_countries,
labels = ~country,
values = ~contagem,
type = "pie",
textinfo = "percent",
hovertemplate = paste(
"<b>País:</b> %{label}<br>",
"<b>Total:</b> %{value}<br>",
"<b>Porcentagem:</b> %{percent}",
"<extra></extra>"
)
)
fig <- fig %>% layout(
title = "Top 10 Países com mais conteúdo na Netflix (2019)"
)
fig
Questão 8
top_10_renamed <- top_10_countries %>%
rename(
País = country,
"Total de conteúdos" = contagem
)
fig <- plot_ly(
type = 'table',
header = list(
values = colnames(top_10_renamed),
fill = list(color = 'purple'),
font = list(color = 'white', size = 14),
align = 'center'
),
cells = list(
values = unname(as.list(top_10_renamed)),
font = list(size=12),
align = 'center'
)
)
fig <- fig %>% layout(
title = "Top 10 Países por Total de Conteúdo"
)
fig
Questão 9
content_by_decade <- netflix_titles %>%
filter(!is.na(release_year)) %>%
mutate(decade = (release_year %/% 10) * 10) %>%
count(decade, type, name = "contagem") %>%
arrange(decade)
movies_data <- content_by_decade %>%
filter(type == "Movie")
tv_data <- content_by_decade %>%
filter(type == "TV Show")
fig <- plot_ly() %>%
add_trace(
data = movies_data,
x = ~decade,
y = ~contagem,
type = 'scatter',
mode = 'lines+markers',
name = 'Filmes',
line = list(color = 'orange'),
marker = list(color = 'orange')
) %>%
add_trace(
data = tv_data,
x = ~decade,
y = ~contagem,
type = 'scatter',
mode = 'lines+markers', # Linhas E PONTOS
name = 'Séries',
line = list(color = 'blue'),
marker = list(color = 'blue')
)
fig <- fig %>% layout(
xaxis = list(
title = "Década",
dtick = 10
),
yaxis = list(title = "Qnd. Conteúdo")
)
fig
Questão 10
library(stringr)
genre_data <- netflix_titles %>%
filter(type == "Movie",
release_year >= 2000,
release_year <= 2010) %>%
mutate(
main_genre = sapply(str_split(listed_in, ", "), `[`, 1)
) %>%
filter(
main_genre %in% c("Dramas", "Action & Adventure", "Comedies")
) %>%
count(release_year, main_genre, name = "contagem") %>%
mutate(release_year = as.factor(release_year))
color_map <- c(
"Dramas" = "blue",
"Action & Adventure" = "orange",
"Comedies" = "green"
)
fig <- plot_ly(
data = genre_data,
x = ~release_year,
y = ~contagem,
color = ~main_genre,
colors = color_map,
type = 'bar'
)
fig <- fig %>% layout(
barmode = 'group',
xaxis = list(title = "Ano de Lançamento"),
yaxis = list(title = "Qnt. de Lançamentos")
)
fig