Time Sieries Visualication
Sung Thi Tho
2026-01-07
#Đề bài: LÀm việc với tập dữ liệu Economics và trực quan biến tỷ lệ thu nhập cá nhân psavert của người dân Mỹ. Chúng ta cần trực quan dữ liệu theo chuỗi thời gian để xem xét tỷ lệ thu nhập của người dân Mỹ tăng hay giảm từ năm 1965 đến 2015 #Tiền xử lý dữ liệu
#Tập dữ liệu #Hiển thị 6 dl đầu tiên
data("economics")
head(economics)## # A tibble: 6 × 6
## date pce pop psavert uempmed unemploy
## <date> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1967-07-01 507. 198712 12.6 4.5 2944
## 2 1967-08-01 510. 198911 12.6 4.7 2945
## 3 1967-09-01 516. 199113 11.9 4.6 2958
## 4 1967-10-01 512. 199311 12.9 4.9 3143
## 5 1967-11-01 517. 199498 12.8 4.7 3066
## 6 1967-12-01 525. 199657 11.8 4.8 3018#Hiển thị 6 dl cuối cùng
tail(economics, n=6)## # A tibble: 6 × 6
## date pce pop psavert uempmed unemploy
## <date> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2014-11-01 12051. 319564. 7.3 13 9090
## 2 2014-12-01 12062 319746. 7.6 12.9 8717
## 3 2015-01-01 12046 319929. 7.7 13.2 8903
## 4 2015-02-01 12082. 320075. 7.9 12.9 8610
## 5 2015-03-01 12158. 320231. 7.4 12 8504
## 6 2015-04-01 12194. 320402. 7.6 11.5 8526#Trực quan dl
ggplot(data=economics, mapping = aes(x=date, y=psavert))+
geom_line(color = "#7d1b32", size = 0.7)+
labs(title="Pesional Saving Rate in USA from 1967 to 2015",
x="Times",
y="Pesional Saving Rate")## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
apple <- getSymbols("AAPL", return.class = "data.frame", from = "2021-01-01")
tail(AAPL, n=6)## AAPL.Open AAPL.High AAPL.Low AAPL.Close AAPL.Volume AAPL.Adjusted
## 2025-12-29 272.69 274.36 272.35 273.76 23715200 273.76
## 2025-12-30 272.81 274.08 272.28 273.08 22139600 273.08
## 2025-12-31 273.06 273.68 271.75 271.86 27293600 271.86
## 2026-01-02 272.26 277.84 269.00 271.01 37838100 271.01
## 2026-01-05 270.64 271.51 266.14 267.26 45647200 267.26
## 2026-01-06 267.00 267.55 262.12 262.36 52282100 262.36#tiền xl dl cho appple
apple <- AAPL %>%
mutate(Date = as.Date(row.names(.))) %>%
select(Date, AAPL.Close) %>%
rename(Close = AAPL.Close) %>%
mutate(Company = "Apple")
tail(apple, n=6)## Date Close Company
## 2025-12-29 2025-12-29 273.76 Apple
## 2025-12-30 2025-12-30 273.08 Apple
## 2025-12-31 2025-12-31 271.86 Apple
## 2026-01-02 2026-01-02 271.01 Apple
## 2026-01-05 2026-01-05 267.26 Apple
## 2026-01-06 2026-01-06 262.36 Applefacebook <- getSymbols("FB", return.class = "data.frame", from = "2021-01-01")
tail(FB, n=6)## FB.Open FB.High FB.Low FB.Close FB.Volume FB.Adjusted
## 2025-12-29 42.226 42.226 42.226 42.226 100 42.226
## 2025-12-30 42.160 42.210 42.160 42.210 200 42.210
## 2025-12-31 42.200 42.200 42.141 42.200 1200 42.200
## 2026-01-02 42.250 42.250 42.250 42.250 100 42.250
## 2026-01-05 42.340 42.340 42.340 42.340 100 42.340
## 2026-01-06 42.440 42.449 42.410 42.449 5300 42.449facebook <- FB %>%
mutate(Date = as.Date(row.names(.))) %>%
select(Date, FB.Close) %>%
rename(Close = FB.Close) %>%
mutate(Company = "Apple")
tail(facebook, n=6)## Date Close Company
## 2025-12-29 2025-12-29 42.226 Apple
## 2025-12-30 2025-12-30 42.210 Apple
## 2025-12-31 2025-12-31 42.200 Apple
## 2026-01-02 2026-01-02 42.250 Apple
## 2026-01-05 2026-01-05 42.340 Apple
## 2026-01-06 2026-01-06 42.449 Applelibrary(quantmod)
library(dplyr)
library(ggplot2)
library(scales)
rm(list = ls())
# ===== Apple =====
getSymbols("AAPL", src = "yahoo", from = "2021-05-05")## [1] "AAPL"apple <- data.frame(
Date = as.Date(index(AAPL)),
Close = as.numeric(AAPL$AAPL.Close)
) %>%
mutate(Company = "Apple")
# ===== Facebook (Meta) =====
getSymbols("META", src = "yahoo", from = "2021-05-05")## [1] "META"facebook <- data.frame(
Date = as.Date(index(META)),
Close = as.numeric(META$META.Close)
) %>%
mutate(Company = "Facebook")
# ===== Combine =====
data_series <- rbind(apple, facebook)
end_date <- as.Date("2022-02-28")
data_series <- data_series %>%
filter(Date <= end_date)
# ===== Plot =====
ggplot(data_series, aes(Date, Close, color = Company)) +
geom_line(size = 1) +
scale_x_date(date_breaks = "1 month",
labels = date_format("%b-%Y")) +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_y_continuous(labels = dollar) +
coord_cartesian(ylim = c(100, 450)) +
labs(
title = "NASDAQ Closing Prices",
subtitle = "From May 2021 to February 2022",
caption = "source: Yahoo Finance",
x = "",
y = "Closing Price"
) +
scale_color_brewer(palette = "Set1")
library(ggplot2)
library(tidyr)
library(gapminder)
library(dplyr)
data(gapminder)
# Subset the data
plotdata_long <- filter(gapminder,
continent == "Asia" &
year %in% c(1952, 2007)) %>%
select(country, year, lifeExp)
# Convert to wide format
plotdata_wide <- spread(plotdata_long, year, lifeExp)
names(plotdata_wide) <- c("Country", "year1952", "year2007")
# Dumbbell chart (thay cho geom_dumbbell)
ggplot(plotdata_wide, aes(y = Country)) +
# Đường nối
geom_segment(aes(x = year1952, xend = year2007,
y = Country, yend = Country),
linewidth = 0.8, color = "grey70") +
# Điểm năm 1952
geom_point(aes(x = year1952), size = 2, color = "steelblue") +
# Điểm năm 2007
geom_point(aes(x = year2007), size = 2, color = "firebrick") +
labs(
title = "Life Expectancy in Asia (1952 vs 2007)",
x = "Life Expectancy",
y = ""
) +
theme_minimal()
library(ggplot2)
library(dplyr)
# Sắp xếp theo year1952
plotdata_wide <- plotdata_wide %>%
mutate(Country = reorder(Country, year1952))
ggplot(plotdata_wide, aes(y = Country)) +
# Đường nối
geom_segment(aes(x = year1952, xend = year2007,
y = Country, yend = Country),
linewidth = 1.2, color = "grey60") +
# Điểm đầu (1952)
geom_point(aes(x = year1952),
size = 3, color = "blue") +
# Điểm cuối (2007)
geom_point(aes(x = year2007),
size = 3, color = "red") +
theme_minimal() +
labs(
title = "Change in Life Expectancy",
subtitle = "From 1952 to 2007",
x = "Life Expectancy (years)",
y = ""
)