Story 5
CN
2024-04-01
#For the story of this week I used three data : global temperature data, Hurricanes data, and storms data that I collect from my google search.
# data and libraries:
library(rvest)## Warning: package 'rvest' was built under R version 4.3.2library(dplyr)## Warning: package 'dplyr' was built under R version 4.3.2##
## 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(kableExtra) ## Warning: package 'kableExtra' was built under R version 4.3.2##
## Attaching package: 'kableExtra'## The following object is masked from 'package:dplyr':
##
## group_rowslibrary(tidyverse)## Warning: package 'ggplot2' was built under R version 4.3.2## Warning: package 'tidyr' was built under R version 4.3.2## Warning: package 'readr' was built under R version 4.3.2## Warning: package 'purrr' was built under R version 4.3.2## Warning: package 'stringr' was built under R version 4.3.2## Warning: package 'lubridate' was built under R version 4.3.2## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ readr 2.1.5
## ✔ ggplot2 3.4.4 ✔ stringr 1.5.1
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ kableExtra::group_rows() masks dplyr::group_rows()
## ✖ readr::guess_encoding() masks rvest::guess_encoding()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(plotly)## Warning: package 'plotly' was built under R version 4.3.3##
## 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':
##
## layoutlibrary(readr)
library(ggplot2)
data= read.csv("C:/Users/Chafiaa/Downloads/data.csv")
data## Year Anomaly
## 1 1999 0.62
## 2 2000 0.40
## 3 2001 0.42
## 4 2002 0.57
## 5 2003 0.62
## 6 2004 0.62
## 7 2005 0.57
## 8 2006 0.68
## 9 2007 0.68
## 10 2008 0.59
## 11 2009 0.58
## 12 2010 0.68
## 13 2011 0.72
## 14 2012 0.61
## 15 2013 0.67
## 16 2014 0.68
## 17 2015 0.76
## 18 2016 0.94
## 19 2017 1.02
## 20 2018 0.92
## 21 2019 0.87
## 22 2020 1.00
## 23 2021 0.99
## 24 2022 0.87
## 25 2023 0.89
## 26 2024 1.22ggplot(data, aes(x = Year, y = Anomaly, color = "Annual Mean")) +
geom_line(linetype = "solid", linewidth = 0.5) +
geom_point(color = "red", shape = 21) +
geom_smooth(method = "lm", formula = y ~ x, se = FALSE, aes(color = "Linear Regression"), linetype = "solid", linewidth = 0.5) +
scale_x_continuous(breaks = seq(1880, 2023, 20), expand = c(0,0)) +
scale_y_continuous(limits = c(-0.5, 1.5), expand = c(0,0)) +
scale_color_manual(name = "Legend", values = c("Annual Mean" = "blue", "Linear Regression" = "green"),
labels = c("Annual Mean", "Linear Regression")) +
theme_light() +
labs(x = "Year", y = "Temperature Anomaly",
title = "GLOBAL LAND AND OCEAN TEMPERATURE",
subtitle = "YEARLY TEMPERATURE ANOMALIES 1997 to 2022") +
theme(legend.position = c(0.2, 0.85),
plot.title = element_text(color = "purple", face = "bold")) 
# from the plot of global temperature we can see that the ocean and the land is getting warmer over the years, but during covid pandemic lock down we can see the temperature is lower ~2021.data1= read.csv("C:/Users/Chafiaa/Downloads/Tornado statistics.csv")
data1## Date Tornadoes Fatalities
## 1 1995 1162 37
## 2 1996 1205 26
## 3 1997 1149 72
## 4 1998 1448 128
## 5 1999 1421 94
## 6 2000 972 31
## 7 2001 1101 32
## 8 2002 934 28
## 9 2003 1555 97
## 10 2004 1640 29
## 11 2005 1322 17
## 12 2006 1140 83
## 13 2007 1148 87
## 14 2008 1722 130
## 15 2009 1122 22
## 16 2010 1195 37
## 17 2011 1802 557
## 18 2012 923 75
## 19 2013 844 45
## 20 2014 929 51
## 21 2015 1071 16
## 22 2016 1109 38
## 23 2017 1389 41
## 24 2018 983 6
## 25 2019 1651 42
## 26 2020 1150 80
## 27 2021 984 13
## 28 2022 1387 106
## 29 2023 1393 NAlibrary(ggplot2)
ggplot(data=data1, aes(x=Date, y=Tornadoes, group=1)) +
geom_line(color="red")+
geom_point()
# from Tornadoes plot we can see the tornadoes are fluctuate but I see few during the global lock down on 2021 data2= read.csv("C:/Users/Chafiaa/Downloads/Global Historical Tropical Cyclone Statistics.csv")
data2## Year Named.Storms Named.Storm.Days Hurricanes Hurricanes.Days
## 1 1980 73 367.25 43 143.75
## 2 1981 82 363.75 45 125.75
## 3 1982 81 428.75 46 162.25
## 4 1983 79 369.50 42 150.00
## 5 1984 93 439.00 47 160.25
## 6 1985 95 455.25 51 163.50
## 7 1986 88 407.75 48 172.25
## 8 1987 83 400.75 39 133.75
## 9 1988 74 336.25 39 146.00
## 10 1989 91 440.00 55 199.25
## 11 1990 92 499.25 58 218.75
## 12 1991 79 433.00 47 188.25
## 13 1992 101 559.75 59 253.75
## 14 1993 79 394.25 49 164.00
## 15 1994 93 514.75 51 213.25
## 16 1995 80 408.75 49 179.25
## 17 1996 100 505.50 57 218.25
## 18 1997 97 535.25 58 220.25
## 19 1998 89 418.50 50 179.25
## 20 1999 74 317.50 39 135.50
## 21 2000 90 392.50 45 160.50
## 22 2001 88 373.50 51 162.75
## 23 2002 82 384.50 41 171.50
## 24 2003 85 418.00 50 175.00
## 25 2004 86 442.00 51 216.00
## 26 2005 96 428.75 51 189.50
## 27 2006 81 369.50 42 165.75
## 28 2007 80 303.50 44 118.75
## 29 2008 90 376.75 40 132.50
## 30 2009 85 324.75 38 115.25
## 31 2010 68 289.75 39 112.00
## 32 2011 75 335.50 39 121.00
## 33 2012 88 424.75 47 154.00
## 34 2013 90 353.25 46 127.75
## 35 2014 77 368.75 46 150.75
## 36 2015 95 500.50 54 221.00
## 37 2016 83 413.50 47 163.25
## 38 2017 84 354.75 43 135.75
## 39 2018 103 540.75 59 223.50
## 40 2019 98 449.00 55 172.25
## 41 2020 104 380.25 46 115.25
## 42 2021 94 354.75 37 119.00
## 43 2022 87 335.75 40 115.25
## Cat..3..Hurricanes Cat..3..Hurricanes.Days Accumulated.Cyclone.Energy
## 1 19 30.25 638.0
## 2 15 19.50 554.7
## 3 21 37.75 709.2
## 4 21 47.25 680.0
## 5 20 41.25 726.2
## 6 24 27.75 717.8
## 7 16 31.00 695.0
## 8 18 39.75 649.1
## 9 19 41.25 625.4
## 10 25 56.75 853.9
## 11 21 60.75 930.8
## 12 25 65.75 860.6
## 13 32 89.00 1163.1
## 14 24 43.75 710.4
## 15 31 80.50 1019.0
## 16 24 54.25 779.3
## 17 27 68.00 960.0
## 18 28 87.75 1099.2
## 19 21 46.00 773.1
## 20 21 46.50 606.4
## 21 20 39.25 677.3
## 22 24 38.50 672.4
## 23 27 69.50 812.0
## 24 25 68.00 833.0
## 25 32 99.00 1024.4
## 26 27 79.50 899.6
## 27 27 59.25 761.0
## 28 22 41.75 568.1
## 29 24 33.25 613.9
## 30 21 49.00 609.6
## 31 19 38.75 526.8
## 32 21 36.50 573.8
## 33 24 47.50 740.5
## 34 22 37.00 618.5
## 35 26 54.50 724.0
## 36 39 88.00 1047.0
## 37 26 58.75 806.5
## 38 20 34.25 621.1
## 39 33 91.00 1108.4
## 40 35 64.50 854.8
## 41 24 35.50 599.1
## 42 16 49.00 621.1
## 43 17 36.25 559.6data2<- data2 %>%
pivot_longer(cols = c("Named.Storms", "Hurricanes", "Cat..3..Hurricanes"),
names_to = "Category", values_to = "Count")
# Define the order of the facets
category_order <- c("Named.Storms", "Hurricanes", "Cat..3..Hurricanes")
# Reorder the levels of the "Category" factor
data2$Category <- factor(data2$Category, levels = category_order)
# Plot the data using facets and add connecting lines
p <- ggplot(data2, aes(x = Year, y = Count, color = Category, group = Category)) +
geom_point() +
geom_line() +
facet_wrap(~Category, scales = "free_y", nrow = 3) +
labs(x = "Year", y = "Count") +
theme_minimal() +
theme(legend.position = "bottom") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
p <- p + labs(
title = "Meteorological Statistics",
subtitle = "Yearly counts of meteorological events"
)
p <- p + scale_color_manual(values = c("NAMED STORMS" = "red", "HURRICAINES" = "green", "CAT 3 HURRICAINES" = "purple"))
p
# For Hurricanes we can see from the plot below it high on the 90s and from 2010 to 2020 and low during covid lock down