Importation des librairies
library("ggplot2")
library("lubridate")
library("dplyr")
Exercice 1
df1 <- data.frame(
Date = as.Date(c("2023-01-01", "2023-01-02", "2023-01-03",
"2023-01-04", "2023-01-05", "2023-01-06",
"2023-01-07", "2023-01-08", "2023-01-09",
"2023-01-10")),
Price = c(100, 105, 110, 108, 112, 115, 118, 120, 122, 125)
)
df1
## Date Price
## 1 2023-01-01 100
## 2 2023-01-02 105
## 3 2023-01-03 110
## 4 2023-01-04 108
## 5 2023-01-05 112
## 6 2023-01-06 115
## 7 2023-01-07 118
## 8 2023-01-08 120
## 9 2023-01-09 122
## 10 2023-01-10 125
Exercice 2
dates <- seq(as.Date("2016-01-02"), by = "month", length.out = 10)
df2 <- data.frame(
id = 1:10,
date = dates,
année = format(dates, "%Y"),
mois = format(dates, "%m"),
semaine = isoweek(dates),
jour = format(dates, "%d")
)
df2
## id date année mois semaine jour
## 1 1 2016-01-02 2016 01 53 02
## 2 2 2016-02-02 2016 02 5 02
## 3 3 2016-03-02 2016 03 9 02
## 4 4 2016-04-02 2016 04 13 02
## 5 5 2016-05-02 2016 05 18 02
## 6 6 2016-06-02 2016 06 22 02
## 7 7 2016-07-02 2016 07 26 02
## 8 8 2016-08-02 2016 08 31 02
## 9 9 2016-09-02 2016 09 35 02
## 10 10 2016-10-02 2016 10 39 02
Exercice 3
df3 <- data.frame(
id = 1:7,
date = seq(
from = as.POSIXct("2025-01-23 15:00", format = "%Y-%m-%d %H:%M"),
to = as.POSIXct("2025-01-23 21:00", format = "%Y-%m-%d %H:%M"),
by = "hour"
)
)
df3$minute <- format(df3$date, "%M")
df3$seconde <- format(df3$date, "%S")
df3
## id date minute seconde
## 1 1 2025-01-23 15:00:00 00 00
## 2 2 2025-01-23 16:00:00 00 00
## 3 3 2025-01-23 17:00:00 00 00
## 4 4 2025-01-23 18:00:00 00 00
## 5 5 2025-01-23 19:00:00 00 00
## 6 6 2025-01-23 20:00:00 00 00
## 7 7 2025-01-23 21:00:00 00 00
Exercice 4
aujourdhui <- Sys.Date()
df2$jours_ecoules <- as.numeric(aujourdhui - df2$date)
df2$semaines_ecoulees <- round(df2$jours_ecoules / 7, 1)
intervalle <- interval(df2$date, aujourdhui)
df2$mois_ecoules <- round(time_length(intervalle, "month"), 1)
df2$annees_ecoulees <- round(time_length(intervalle, "year"), 1)
df2
## id date année mois semaine jour jours_ecoules semaines_ecoulees
## 1 1 2016-01-02 2016 01 53 02 3320 474.3
## 2 2 2016-02-02 2016 02 5 02 3289 469.9
## 3 3 2016-03-02 2016 03 9 02 3260 465.7
## 4 4 2016-04-02 2016 04 13 02 3229 461.3
## 5 5 2016-05-02 2016 05 18 02 3199 457.0
## 6 6 2016-06-02 2016 06 22 02 3168 452.6
## 7 7 2016-07-02 2016 07 26 02 3138 448.3
## 8 8 2016-08-02 2016 08 31 02 3107 443.9
## 9 9 2016-09-02 2016 09 35 02 3076 439.4
## 10 10 2016-10-02 2016 10 39 02 3046 435.1
## mois_ecoules annees_ecoulees
## 1 109 9.1
## 2 108 9.0
## 3 107 8.9
## 4 106 8.8
## 5 105 8.8
## 6 104 8.7
## 7 103 8.6
## 8 102 8.5
## 9 101 8.4
## 10 100 8.3
Exercice 5
Série temporelle
ggplot(df1, aes(x = Date, y = Price)) +
geom_line(color = "blue") +
geom_point() +
labs(title = "Évolution des prix", x = "Date", y = "Prix")
Graphique en chandelier
candle_data <- data.frame(
Date = seq(as.Date("2023-01-01"), by = "day", length.out = 10),
Open = c(100, 105, 110, 108, 112, 115, 118, 120, 122, 125),
High = c(102, 107, 112, 110, 115, 118, 120, 122, 125, 128),
Low = c(98, 103, 108, 106, 110, 113, 116, 118, 120, 123),
Close = c(101, 106, 111, 109, 114, 117, 119, 121, 124, 127)
)
ggplot(candle_data, aes(x = Date)) +
geom_segment(aes(x = Date, xend = Date, y = Low, yend = High), color = "black") +
geom_rect(aes(xmin = Date - 0.2, xmax = Date + 0.2, ymin = pmin(Open, Close), ymax = pmax(Open, Close), fill = Open < Close)) +
scale_fill_manual(values = c("TRUE" = "darkgreen", "FALSE" = "firebrick")) +
labs(title = "Graphique en chandelier", x = "Date", y = "Prix", fill = "Tendance") +
theme_minimal() +
theme(legend.position = "none")
Visualisation de saisonnalité
season_data <- data.frame(
Date = seq(as.Date("2020-01-01"), by = "month", length.out = 48),
Ventes = round(100 + 50*sin(seq(0, 4*pi, length.out=48)) + rnorm(48, 0, 10))
)
ggplot(season_data, aes(x = Date, y = Ventes)) +
geom_line(color = "steelblue") +
geom_point() +
geom_smooth(method = "loess", formula = y ~ x, color = "red", se = FALSE) +
labs(title = "Saisonnalité des ventes", subtitle = "Avec tendance polynomiale") +
scale_x_date(date_breaks = "3 months", date_labels = "%b %Y") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Calendrier thermique
heatmap_data <- data.frame(
Date = seq(as.Date("2023-01-01"), as.Date("2023-12-31"), by = "day"),
Valeur = sample(10:100, 365, replace = TRUE)
) |>
mutate(
Mois = month(Date, label = TRUE, abbr = FALSE),
Semaine = week(Date),
Jour = wday(Date, label = TRUE)
)
ggplot(heatmap_data, aes(Semaine, Jour, fill = Valeur)) +
geom_tile(color = "pink") +
facet_grid(.~Mois) +
scale_fill_gradient(low = "pink", high = "purple") +
labs(title = "Calendrier thermique 2023") +
theme_minimal() +
theme(axis.text.x = element_blank())
