# Reference: https://www.ncei.noaa.gov/access/monitoring/climate-at-a-glance/global/time-series/globe/land_ocean/12/9/1998-2023?trend=true&trend_base=100&begtrendyear=1998&endtrendyear=2023
df1 = read.csv("https://raw.githubusercontent.com/enidroman/Data_608_Knowledge_and_Visual_Analytics/main/Global%20Land%20and%20Ocean%20Temp%202.csv")
df1
## Global.Land.and.Ocean.October...September.Temperature.Anomalies X
## 1 Units: Degrees Celsius
## 2 Base Period: 1901-2000
## 3 Missing: -999
## 4 Year Anomaly
## 5 1997 0.42
## 6 1998 0.67
## 7 1999 0.44
## 8 2000 0.45
## 9 2001 0.48
## 10 2002 0.63
## 11 2003 0.6
## 12 2004 0.57
## 13 2005 0.67
## 14 2006 0.67
## 15 2007 0.69
## 16 2008 0.53
## 17 2009 0.64
## 18 2010 0.75
## 19 2011 0.63
## 20 2012 0.64
## 21 2013 0.68
## 22 2014 0.76
## 23 2015 0.83
## 24 2016 1.08
## 25 2017 0.94
## 26 2018 0.86
## 27 2019 0.95
## 28 2020 1.04
## 29 2021 0.86
## 30 2022 0.93
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.2.3
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
df_row<- df1[-c(1, 2, 3, 4), ]
df_row
## Global.Land.and.Ocean.October...September.Temperature.Anomalies X
## 5 1997 0.42
## 6 1998 0.67
## 7 1999 0.44
## 8 2000 0.45
## 9 2001 0.48
## 10 2002 0.63
## 11 2003 0.6
## 12 2004 0.57
## 13 2005 0.67
## 14 2006 0.67
## 15 2007 0.69
## 16 2008 0.53
## 17 2009 0.64
## 18 2010 0.75
## 19 2011 0.63
## 20 2012 0.64
## 21 2013 0.68
## 22 2014 0.76
## 23 2015 0.83
## 24 2016 1.08
## 25 2017 0.94
## 26 2018 0.86
## 27 2019 0.95
## 28 2020 1.04
## 29 2021 0.86
## 30 2022 0.93
colnames(df_row) <- c("YEAR", "ANOMALY TEMP") # change column names of all the columns in the dataframe print(df)
df_row
## YEAR ANOMALY TEMP
## 5 1997 0.42
## 6 1998 0.67
## 7 1999 0.44
## 8 2000 0.45
## 9 2001 0.48
## 10 2002 0.63
## 11 2003 0.6
## 12 2004 0.57
## 13 2005 0.67
## 14 2006 0.67
## 15 2007 0.69
## 16 2008 0.53
## 17 2009 0.64
## 18 2010 0.75
## 19 2011 0.63
## 20 2012 0.64
## 21 2013 0.68
## 22 2014 0.76
## 23 2015 0.83
## 24 2016 1.08
## 25 2017 0.94
## 26 2018 0.86
## 27 2019 0.95
## 28 2020 1.04
## 29 2021 0.86
## 30 2022 0.93
str(df_row)
## 'data.frame': 26 obs. of 2 variables:
## $ YEAR : chr "1997" "1998" "1999" "2000" ...
## $ ANOMALY TEMP: chr "0.42" "0.67" "0.44" "0.45" ...
#install.packages('weathermetrics')
library('weathermetrics')
## Warning: package 'weathermetrics' was built under R version 4.2.3
# Convert "ANOMALY TEMP" column to numeric
df_row$`ANOMALY TEMP` <- as.numeric(df_row$`ANOMALY TEMP`)
# Check the data types again
str(df_row)
## 'data.frame': 26 obs. of 2 variables:
## $ YEAR : chr "1997" "1998" "1999" "2000" ...
## $ ANOMALY TEMP: num 0.42 0.67 0.44 0.45 0.48 0.63 0.6 0.57 0.67 0.67 ...
# Now you can apply the temperature conversion
df_f <- df_row
df_f$`ANOMALY TEMP` <- celsius.to.fahrenheit(df_f$`ANOMALY TEMP`)
df_f
## YEAR ANOMALY TEMP
## 5 1997 32.76
## 6 1998 33.21
## 7 1999 32.79
## 8 2000 32.81
## 9 2001 32.86
## 10 2002 33.13
## 11 2003 33.08
## 12 2004 33.03
## 13 2005 33.21
## 14 2006 33.21
## 15 2007 33.24
## 16 2008 32.95
## 17 2009 33.15
## 18 2010 33.35
## 19 2011 33.13
## 20 2012 33.15
## 21 2013 33.22
## 22 2014 33.37
## 23 2015 33.49
## 24 2016 33.94
## 25 2017 33.69
## 26 2018 33.55
## 27 2019 33.71
## 28 2020 33.87
## 29 2021 33.55
## 30 2022 33.67
df_index <- df_f # Duplicate data
rownames(df_index) <- 1:nrow(df_index) # Assign sequence to row names
df_index
## YEAR ANOMALY TEMP
## 1 1997 32.76
## 2 1998 33.21
## 3 1999 32.79
## 4 2000 32.81
## 5 2001 32.86
## 6 2002 33.13
## 7 2003 33.08
## 8 2004 33.03
## 9 2005 33.21
## 10 2006 33.21
## 11 2007 33.24
## 12 2008 32.95
## 13 2009 33.15
## 14 2010 33.35
## 15 2011 33.13
## 16 2012 33.15
## 17 2013 33.22
## 18 2014 33.37
## 19 2015 33.49
## 20 2016 33.94
## 21 2017 33.69
## 22 2018 33.55
## 23 2019 33.71
## 24 2020 33.87
## 25 2021 33.55
## 26 2022 33.67
df_rank <- df_index
df_rank$RANK <- rank(-df_rank$`ANOMALY TEMP`)
df_rank
## YEAR ANOMALY TEMP RANK
## 1 1997 32.76 26.0
## 2 1998 33.21 14.0
## 3 1999 32.79 25.0
## 4 2000 32.81 24.0
## 5 2001 32.86 23.0
## 6 2002 33.13 18.5
## 7 2003 33.08 20.0
## 8 2004 33.03 21.0
## 9 2005 33.21 14.0
## 10 2006 33.21 14.0
## 11 2007 33.24 11.0
## 12 2008 32.95 22.0
## 13 2009 33.15 16.5
## 14 2010 33.35 10.0
## 15 2011 33.13 18.5
## 16 2012 33.15 16.5
## 17 2013 33.22 12.0
## 18 2014 33.37 9.0
## 19 2015 33.49 8.0
## 20 2016 33.94 1.0
## 21 2017 33.69 4.0
## 22 2018 33.55 6.5
## 23 2019 33.71 3.0
## 24 2020 33.87 2.0
## 25 2021 33.55 6.5
## 26 2022 33.67 5.0
library(DT)
## Warning: package 'DT' was built under R version 4.2.3
df_table <- datatable(df_rank)
df_table
df_rank$`ANOMALY TEMP` <- as.numeric(df_rank$`ANOMALY TEMP`)
str(df_rank)
## 'data.frame': 26 obs. of 3 variables:
## $ YEAR : chr "1997" "1998" "1999" "2000" ...
## $ ANOMALY TEMP: num 32.8 33.2 32.8 32.8 32.9 ...
## $ RANK : num 26 14 25 24 23 18.5 20 21 14 14 ...
library(plotly)
## Warning: package 'plotly' was built under R version 4.2.3
## Loading required package: ggplot2
## Warning: package 'ggplot2' was built under R version 4.2.3
##
## 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':
##
## layout
x <- df_rank$YEAR
y <- df_rank$`ANOMALY TEMP`
rank <- df_rank$'RANK'
# Create hover text with temperature, year, and rank
hover_text <- paste("ANOMALY TEMP: ", y, "°F<br>YEAR: ", x, "<br>RANK: ", rank)
fig <- plot_ly(data = df_rank, x = ~x, y = ~y, type = 'bar',
text = hover_text, # Include the hover text with all information
hoverinfo = 'text', # Specify hoverinfo to show the text
marker = list(color = 'rgb(192, 57, 79)',
line = list(color = 'rgb(8, 48, 107)', width = 1.5)))
fig <- fig %>% layout(
xaxis = list(title = "Year"),
yaxis = list(title = "Number of Temperature °F", range = c(32, max(y))),
bargap = 0.05,
height = 500, # Adjust the height as needed to make the graph taller
width = 800 # Adjust the width to make the graph wider
)
## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()
# Add HTML-based annotations for title and subtitle
fig <- fig %>% add_annotations(
text = "<b>GLOBAL LAND AND OCEAN TEMPERATURE</b>",
x = 0, xref = "paper",
y = 1.05, yref = "paper",
showarrow = FALSE,
font = list(size = 20),
align = "left"
)
fig <- fig %>% add_annotations(
text = "YEARLY TEMPERATURE ANOMALIES 1997 to 2022",
x = 0, xref = "paper",
y = 0.97, yref = "paper",
showarrow = FALSE,
font = list(size = 16),
align = "left"
)
fig
x <- df_rank$YEAR
y <- df_rank$`ANOMALY TEMP`
rank <- df_rank$'RANK'
# Create hover text with year, temperature, and rank
hover_text <- paste("Year: ", x, "<br>ANOMALY TEMP: ", y, "<br>RANK: ", rank)
fig <- plot_ly(x = ~x, y = ~y, type = 'scatter', mode = 'lines', text = hover_text, textposition = 'top',
hoverinfo = 'text', # Specify hoverinfo to show the text
line = list(color = 'rgb(192, 57, 79)'))
fig <- fig %>% layout(
xaxis = list(title = "Year"),
yaxis = list(title = "Temperature °F", range = c(32, max(y))),
height = 500, # Adjust the height as needed
width = 800 # Adjust the width as needed
)
## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()
# Add HTML-based annotations for title and subtitle
fig <- fig %>% add_annotations(
text = "<b>GLOBAL LAND AND OCEAN TEMPERATURE</b>",
x = 0, xref = "paper",
y = 1.05, yref = "paper",
showarrow = FALSE,
font = list(size = 20),
align = "left"
)
fig <- fig %>% add_annotations(
text = "YEARLY TEMPERATURE ANOMALIES 1997 to 2022",
x = 0, xref = "paper",
y = 0.97, yref = "paper",
showarrow = FALSE,
font = list(size = 16),
align = "left"
)
fig
# reference: https://www.ncei.noaa.gov/access/monitoring/tornadoes/12/9?fatalities=false
df2 = read.csv("https://raw.githubusercontent.com/enidroman/Data_608_Knowledge_and_Visual_Analytics/main/Tornado%20statistics%20for%20the%20Contiguous%20U.S..csv")
df2
## October.September.U.S..Tornadoes...denotes.preliminary.data. X
## 1 Date Tornadoes
## 2 195109 246
## 3 195209 255
## 4 195309 392
## 5 195409 556
## 6 195509 578
## 7 195609 505
## 8 195709 787
## 9 195809 624
## 10 195909 621
## 11 196009 608
## 12 196109 676
## 13 196209 704
## 14 196309 452
## 15 196409 677
## 16 196509 900
## 17 196609 582
## 18 196709 882
## 19 196809 676
## 20 196909 644
## 21 197009 633
## 22 197109 854
## 23 197209 789
## 24 197309 1008
## 25 197409 1040
## 26 197509 912
## 27 197609 897
## 28 197709 794
## 29 197809 815
## 30 197909 835
## 31 198009 889
## 32 198109 789
## 33 198209 964
## 34 198309 935
## 35 198409 949
## 36 198509 730
## 37 198609 757
## 38 198709 634
## 39 198809 612
## 40 198909 928
## 41 199009 1143
## 42 199109 1177
## 43 199209 1143
## 44 199309 1297
## 45 199409 1068
## 46 199509 1162
## 47 199609 1205
## 48 199709 1149
## 49 199809 1448
## 50 199909 1421
## 51 200009 972
## 52 200109 1101
## 53 200209 934
## 54 200309 1555
## 55 200409 1640
## 56 200509 1322
## 57 200609 1140
## 58 200709 1148
## 59 200809 1722
## 60 200909 1122
## 61 201009 1195
## 62 201109 1802
## 63 201209 923
## 64 201309 844
## 65 201409 929
## 66 201509 1071
## 67 201609 1109
## 68 201709 1389
## 69 201809 983
## 70 201909 1651
## 71 202009 1150
## 72 202109 984
## 73 202209 1387
## 74 202309 1393*
## X.1
## 1 Fatalities
## 2 35
## 3 233
## 4 470
## 5 81
## 6 131
## 7 85
## 8 147
## 9 109
## 10 62
## 11 45
## 12 52
## 13 31
## 14 31
## 15 49
## 16 319
## 17 98
## 18 106
## 19 141
## 20 69
## 21 68
## 22 163
## 23 34
## 24 76
## 25 376
## 26 64
## 27 45
## 28 40
## 29 51
## 30 82
## 31 34
## 32 25
## 33 57
## 34 36
## 35 122
## 36 96
## 37 18
## 38 42
## 39 34
## 40 30
## 41 84
## 42 41
## 43 11
## 44 135
## 45 45
## 46 37
## 47 26
## 48 72
## 49 128
## 50 94
## 51 31
## 52 32
## 53 28
## 54 97
## 55 29
## 56 17
## 57 83
## 58 87
## 59 130
## 60 22
## 61 37
## 62 557
## 63 75
## 64 45
## 65 51
## 66 16
## 67 38
## 68 41
## 69 6
## 70 42
## 71 80
## 72 13
## 73 106
## 74
df2_row<- df2[-c(1:47, 74), ]
df2_row
## October.September.U.S..Tornadoes...denotes.preliminary.data. X X.1
## 48 199709 1149 72
## 49 199809 1448 128
## 50 199909 1421 94
## 51 200009 972 31
## 52 200109 1101 32
## 53 200209 934 28
## 54 200309 1555 97
## 55 200409 1640 29
## 56 200509 1322 17
## 57 200609 1140 83
## 58 200709 1148 87
## 59 200809 1722 130
## 60 200909 1122 22
## 61 201009 1195 37
## 62 201109 1802 557
## 63 201209 923 75
## 64 201309 844 45
## 65 201409 929 51
## 66 201509 1071 16
## 67 201609 1109 38
## 68 201709 1389 41
## 69 201809 983 6
## 70 201909 1651 42
## 71 202009 1150 80
## 72 202109 984 13
## 73 202209 1387 106
colnames(df2_row) <- c("DATE", "TORNADOES", "FATALITIES") # change column names of all the columns in the dataframe print(df)
df2_row
## DATE TORNADOES FATALITIES
## 48 199709 1149 72
## 49 199809 1448 128
## 50 199909 1421 94
## 51 200009 972 31
## 52 200109 1101 32
## 53 200209 934 28
## 54 200309 1555 97
## 55 200409 1640 29
## 56 200509 1322 17
## 57 200609 1140 83
## 58 200709 1148 87
## 59 200809 1722 130
## 60 200909 1122 22
## 61 201009 1195 37
## 62 201109 1802 557
## 63 201209 923 75
## 64 201309 844 45
## 65 201409 929 51
## 66 201509 1071 16
## 67 201609 1109 38
## 68 201709 1389 41
## 69 201809 983 6
## 70 201909 1651 42
## 71 202009 1150 80
## 72 202109 984 13
## 73 202209 1387 106
df2_index <- df2_row # Duplicate data
rownames(df2_index) <- 1:nrow(df2_index) # Assign sequence to row names
df2_index
## DATE TORNADOES FATALITIES
## 1 199709 1149 72
## 2 199809 1448 128
## 3 199909 1421 94
## 4 200009 972 31
## 5 200109 1101 32
## 6 200209 934 28
## 7 200309 1555 97
## 8 200409 1640 29
## 9 200509 1322 17
## 10 200609 1140 83
## 11 200709 1148 87
## 12 200809 1722 130
## 13 200909 1122 22
## 14 201009 1195 37
## 15 201109 1802 557
## 16 201209 923 75
## 17 201309 844 45
## 18 201409 929 51
## 19 201509 1071 16
## 20 201609 1109 38
## 21 201709 1389 41
## 22 201809 983 6
## 23 201909 1651 42
## 24 202009 1150 80
## 25 202109 984 13
## 26 202209 1387 106
# Extract only the year (first four characters) from the YEAR column
df2_index$Year <- substr(df2_index$DATE, 1, 4)
df2_index$DATE <- NULL
# Print the resulting data frame with the Year column
df2_index
## TORNADOES FATALITIES Year
## 1 1149 72 1997
## 2 1448 128 1998
## 3 1421 94 1999
## 4 972 31 2000
## 5 1101 32 2001
## 6 934 28 2002
## 7 1555 97 2003
## 8 1640 29 2004
## 9 1322 17 2005
## 10 1140 83 2006
## 11 1148 87 2007
## 12 1722 130 2008
## 13 1122 22 2009
## 14 1195 37 2010
## 15 1802 557 2011
## 16 923 75 2012
## 17 844 45 2013
## 18 929 51 2014
## 19 1071 16 2015
## 20 1109 38 2016
## 21 1389 41 2017
## 22 983 6 2018
## 23 1651 42 2019
## 24 1150 80 2020
## 25 984 13 2021
## 26 1387 106 2022
# Move the "LastColumn" to the first position
df2_col <- df2_index
df2_col <- df2_col[, c("Year", names(df2_col)[-which(names(df2_col) == "Year")])]
colnames(df2_col)[1] ="YEAR"
# Print the resulting data frame
df2_col
## YEAR TORNADOES FATALITIES
## 1 1997 1149 72
## 2 1998 1448 128
## 3 1999 1421 94
## 4 2000 972 31
## 5 2001 1101 32
## 6 2002 934 28
## 7 2003 1555 97
## 8 2004 1640 29
## 9 2005 1322 17
## 10 2006 1140 83
## 11 2007 1148 87
## 12 2008 1722 130
## 13 2009 1122 22
## 14 2010 1195 37
## 15 2011 1802 557
## 16 2012 923 75
## 17 2013 844 45
## 18 2014 929 51
## 19 2015 1071 16
## 20 2016 1109 38
## 21 2017 1389 41
## 22 2018 983 6
## 23 2019 1651 42
## 24 2020 1150 80
## 25 2021 984 13
## 26 2022 1387 106
str(df2_col)
## 'data.frame': 26 obs. of 3 variables:
## $ YEAR : chr "1997" "1998" "1999" "2000" ...
## $ TORNADOES : chr "1149" "1448" "1421" "972" ...
## $ FATALITIES: chr "72" "128" "94" "31" ...
df2_col$`TORNADOES` <- as.numeric(df2_col$`TORNADOES`)
df2_col$'FATALITIES' <- as.numeric(df2_col$'FATALITIES')
str(df2_col)
## 'data.frame': 26 obs. of 3 variables:
## $ YEAR : chr "1997" "1998" "1999" "2000" ...
## $ TORNADOES : num 1149 1448 1421 972 1101 ...
## $ FATALITIES: num 72 128 94 31 32 28 97 29 17 83 ...
df2_rank <-df2_col
df2_rank$'TORNADOES RANK' <- rank(-df2_rank$`TORNADOES`)
df2_rank$'FATALITIES RANK' <- rank(-df2_rank$`FATALITIES`)
df2_rank <- df2_rank[, c(1:2, 4, 3, 5:ncol(df2_rank))]
df2_rank
## YEAR TORNADOES TORNADOES RANK FATALITIES FATALITIES RANK
## 1 1997 1149 13 72 11
## 2 1998 1448 6 128 3
## 3 1999 1421 7 94 6
## 4 2000 972 22 31 19
## 5 2001 1101 18 32 18
## 6 2002 934 23 28 21
## 7 2003 1555 5 97 5
## 8 2004 1640 4 29 20
## 9 2005 1322 10 17 23
## 10 2006 1140 15 83 8
## 11 2007 1148 14 87 7
## 12 2008 1722 2 130 2
## 13 2009 1122 16 22 22
## 14 2010 1195 11 37 17
## 15 2011 1802 1 557 1
## 16 2012 923 25 75 10
## 17 2013 844 26 45 13
## 18 2014 929 24 51 12
## 19 2015 1071 19 16 24
## 20 2016 1109 17 38 16
## 21 2017 1389 8 41 15
## 22 2018 983 21 6 26
## 23 2019 1651 3 42 14
## 24 2020 1150 12 80 9
## 25 2021 984 20 13 25
## 26 2022 1387 9 106 4
df2_table <- datatable(df2_rank)
df2_table
library(plotly)
x <- df2_rank$YEAR
y <- df2_rank$`TORNADOES`
rank <- df2_rank$'TORNADOES RANK'
# Create hover text with temperature, year, and rank
hover_text <- paste("TORNADOES: ", y, "<br>YEAR: ", x, "<br>TORNADOES RANK: ", rank)
fig <- plot_ly(data = df2_rank, x = ~x, y = ~y, type = 'bar',
text = hover_text, # Include the hover text with all information
hoverinfo = 'text', # Specify hoverinfo to show the text
marker = list(color = 'GREEN',
line = list(color = 'rgb(8, 48, 107)', width = 1.5)))
fig <- fig %>% layout(
xaxis = list(title = "Year"),
yaxis = list(title = "Number of Tornadoes", range = c(32, max(y))),
bargap = 0.05,
height = 500, # Adjust the height as needed to make the graph taller
width = 800 # Adjust the width to make the graph wider
)
## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()
# Add HTML-based annotations for title and subtitle
fig <- fig %>% add_annotations(
text = "<b>U.S. TORNADOES</b>",
x = 0, xref = "paper",
y = 1.05, yref = "paper",
showarrow = FALSE,
font = list(size = 20),
align = "left"
)
fig <- fig %>% add_annotations(
text = "1997 TO 2022",
x = 0, xref = "paper",
y = 0.97, yref = "paper",
showarrow = FALSE,
font = list(size = 16),
align = "left"
)
fig
x <- df2_rank$YEAR
y <- df2_rank$`TORNADOES`
rank <- df2_rank$'TORNADOES RANK'
# Create hover text with year, temperature, and rank
hover_text <- paste("Year: ", x, "<br>Tornadoes: ", y, "<br>Tornadoes Rank: ", rank)
fig <- plot_ly(x = ~x, y = ~y, type = 'scatter', mode = 'lines', text = hover_text, textposition = 'top',
hoverinfo = 'text', # Specify hoverinfo to show the text
line = list(color = 'GREEN'))
fig <- fig %>% layout(
xaxis = list(title = "Year"),
yaxis = list(title = "Number of Tornadoes", range = c(32, max(y))),
height = 500, # Adjust the height as needed
width = 800 # Adjust the width as needed
)
## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()
# Add HTML-based annotations for title and subtitle
fig <- fig %>% add_annotations(
text = "<b>U.S. TORNADOES</b>",
x = 0, xref = "paper",
y = 1.05, yref = "paper",
showarrow = FALSE,
font = list(size = 20),
align = "left"
)
fig <- fig %>% add_annotations(
text = "1997 TO 2022",
x = 0, xref = "paper",
y = 0.97, yref = "paper",
showarrow = FALSE,
font = list(size = 16),
align = "left"
)
fig
x <- df2_rank$YEAR
y <- df2_rank$`FATALITIES`
rank <- df2_rank$'FATALITIES RANK'
# Create hover text with year, temperature, and rank
hover_text <- paste("Year: ", x, "<br>Fatalities: ", y, "<br>Fatalities Rank: ", rank)
fig <- plot_ly(x = ~x, y = ~y, type = 'scatter', mode = 'lines', text = hover_text, textposition = 'top',
hoverinfo = 'text', # Specify hoverinfo to show the text
line = list(color = 'BLUE'))
fig <- fig %>% layout(
xaxis = list(title = "Year"),
yaxis = list(title = "Number of Fatalities", range = c(32, max(y))),
height = 500, # Adjust the height as needed
width = 800 # Adjust the width as needed
)
## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()
# Add HTML-based annotations for title and subtitle
fig <- fig %>% add_annotations(
text = "<b>U.S. FATALITIES FROM TORNADOES</b>",
x = 0, xref = "paper",
y = 1.05, yref = "paper",
showarrow = FALSE,
font = list(size = 20),
align = "left"
)
fig <- fig %>% add_annotations(
text = "1997 TO 2022",
x = 0, xref = "paper",
y = 0.97, yref = "paper",
showarrow = FALSE,
font = list(size = 16),
align = "left"
)
fig
# References: https://tropical.atmos.colostate.edu/Realtime/index.php?arch&loc=global
df3 = read.csv("https://raw.githubusercontent.com/enidroman/Data_608_Knowledge_and_Visual_Analytics/main/Global%20Historical%20Tropical%20Cyclone%20Statistics.csv")
df3
## 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 36.25 559.6
df3_row<- df3[-c(1:17), ]
df3_row
## Year Named.Storms Named.Storm.Days Hurricanes Hurricanes.Days
## 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
## 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 36.25 559.6
colnames(df3_row) <- c("YEAR", "NAMED STORMS", "NAME STORM DAYS", "HURRICAINES", "HURRICAINES DAYS", "CAT 3 AND ABOVE HURRICAINES", "CAT 3 AND ABOVE HURRICAINES DAYS", "ACCUMULATED CYCLONE ENERGY") # change column names of all the columns in the dataframe print(df)
df3_row
## YEAR NAMED STORMS NAME STORM DAYS HURRICAINES HURRICAINES DAYS
## 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 AND ABOVE HURRICAINES CAT 3 AND ABOVE HURRICAINES DAYS
## 18 28 87.75
## 19 21 46.00
## 20 21 46.50
## 21 20 39.25
## 22 24 38.50
## 23 27 69.50
## 24 25 68.00
## 25 32 99.00
## 26 27 79.50
## 27 27 59.25
## 28 22 41.75
## 29 24 33.25
## 30 21 49.00
## 31 19 38.75
## 32 21 36.50
## 33 24 47.50
## 34 22 37.00
## 35 26 54.50
## 36 39 88.00
## 37 26 58.75
## 38 20 34.25
## 39 33 91.00
## 40 35 64.50
## 41 24 35.50
## 42 16 49.00
## 43 17 36.25
## ACCUMULATED CYCLONE ENERGY
## 18 1099.2
## 19 773.1
## 20 606.4
## 21 677.3
## 22 672.4
## 23 812.0
## 24 833.0
## 25 1024.4
## 26 899.6
## 27 761.0
## 28 568.1
## 29 613.9
## 30 609.6
## 31 526.8
## 32 573.8
## 33 740.5
## 34 618.5
## 35 724.0
## 36 1047.0
## 37 806.5
## 38 621.1
## 39 1108.4
## 40 854.8
## 41 599.1
## 42 621.1
## 43 559.6
df3_index <- df3_row # Duplicate data
rownames(df3_index) <- 1:nrow(df3_index) # Assign sequence to row names
df3_index
## YEAR NAMED STORMS NAME STORM DAYS HURRICAINES HURRICAINES DAYS
## 1 1997 97 535.25 58 220.25
## 2 1998 89 418.50 50 179.25
## 3 1999 74 317.50 39 135.50
## 4 2000 90 392.50 45 160.50
## 5 2001 88 373.50 51 162.75
## 6 2002 82 384.50 41 171.50
## 7 2003 85 418.00 50 175.00
## 8 2004 86 442.00 51 216.00
## 9 2005 96 428.75 51 189.50
## 10 2006 81 369.50 42 165.75
## 11 2007 80 303.50 44 118.75
## 12 2008 90 376.75 40 132.50
## 13 2009 85 324.75 38 115.25
## 14 2010 68 289.75 39 112.00
## 15 2011 75 335.50 39 121.00
## 16 2012 88 424.75 47 154.00
## 17 2013 90 353.25 46 127.75
## 18 2014 77 368.75 46 150.75
## 19 2015 95 500.50 54 221.00
## 20 2016 83 413.50 47 163.25
## 21 2017 84 354.75 43 135.75
## 22 2018 103 540.75 59 223.50
## 23 2019 98 449.00 55 172.25
## 24 2020 104 380.25 46 115.25
## 25 2021 94 354.75 37 119.00
## 26 2022 87 335.75 40 115.25
## CAT 3 AND ABOVE HURRICAINES CAT 3 AND ABOVE HURRICAINES DAYS
## 1 28 87.75
## 2 21 46.00
## 3 21 46.50
## 4 20 39.25
## 5 24 38.50
## 6 27 69.50
## 7 25 68.00
## 8 32 99.00
## 9 27 79.50
## 10 27 59.25
## 11 22 41.75
## 12 24 33.25
## 13 21 49.00
## 14 19 38.75
## 15 21 36.50
## 16 24 47.50
## 17 22 37.00
## 18 26 54.50
## 19 39 88.00
## 20 26 58.75
## 21 20 34.25
## 22 33 91.00
## 23 35 64.50
## 24 24 35.50
## 25 16 49.00
## 26 17 36.25
## ACCUMULATED CYCLONE ENERGY
## 1 1099.2
## 2 773.1
## 3 606.4
## 4 677.3
## 5 672.4
## 6 812.0
## 7 833.0
## 8 1024.4
## 9 899.6
## 10 761.0
## 11 568.1
## 12 613.9
## 13 609.6
## 14 526.8
## 15 573.8
## 16 740.5
## 17 618.5
## 18 724.0
## 19 1047.0
## 20 806.5
## 21 621.1
## 22 1108.4
## 23 854.8
## 24 599.1
## 25 621.1
## 26 559.6
str(df3_index)
## 'data.frame': 26 obs. of 8 variables:
## $ YEAR : int 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 ...
## $ NAMED STORMS : int 97 89 74 90 88 82 85 86 96 81 ...
## $ NAME STORM DAYS : num 535 418 318 392 374 ...
## $ HURRICAINES : int 58 50 39 45 51 41 50 51 51 42 ...
## $ HURRICAINES DAYS : num 220 179 136 160 163 ...
## $ CAT 3 AND ABOVE HURRICAINES : int 28 21 21 20 24 27 25 32 27 27 ...
## $ CAT 3 AND ABOVE HURRICAINES DAYS: num 87.8 46 46.5 39.2 38.5 ...
## $ ACCUMULATED CYCLONE ENERGY : num 1099 773 606 677 672 ...
df3_rank <- df3_index
df3_rank$'YEAR' <- as.character(df3_rank$'YEAR')
df3_rank$`NAMED STORMS` <- as.numeric(df3_rank$`NAMED STORMS`)
df3_rank$'HURRICAINES' <- as.numeric(df3_rank$'HURRICAINES')
df3_rank$'CAT 3 AND ABOVE HURRICAINES' <- as.numeric(df3_rank$'CAT 3 AND ABOVE HURRICAINES')
str(df3_rank)
## 'data.frame': 26 obs. of 8 variables:
## $ YEAR : chr "1997" "1998" "1999" "2000" ...
## $ NAMED STORMS : num 97 89 74 90 88 82 85 86 96 81 ...
## $ NAME STORM DAYS : num 535 418 318 392 374 ...
## $ HURRICAINES : num 58 50 39 45 51 41 50 51 51 42 ...
## $ HURRICAINES DAYS : num 220 179 136 160 163 ...
## $ CAT 3 AND ABOVE HURRICAINES : num 28 21 21 20 24 27 25 32 27 27 ...
## $ CAT 3 AND ABOVE HURRICAINES DAYS: num 87.8 46 46.5 39.2 38.5 ...
## $ ACCUMULATED CYCLONE ENERGY : num 1099 773 606 677 672 ...
df3_rank$'NAMED STORMS RANK' <- rank(-df3_index$`NAMED STORMS`)
df3_rank$'HURRICAINES RANK' <- rank(-df3_index$`HURRICAINES`)
df3_rank$'CAT 3 AND ABOVE HURRICAINES RANK' <- rank(-df3_index$'CAT 3 AND ABOVE HURRICAINES')
df3_rank$'ACCUMULATED CYCLONE ENERGY RANK' <- rank(-df3_index$'ACCUMULATED CYCLONE ENERGY')
df3_rank <- df3_rank[, c(1:2, 9, 3:4, 10, 5:6, 11, 7:8, 12:ncol(df3_rank))]
df3_rank
## YEAR NAMED STORMS NAMED STORMS RANK NAME STORM DAYS HURRICAINES
## 1 1997 97 4.0 535.25 58
## 2 1998 89 11.0 418.50 50
## 3 1999 74 25.0 317.50 39
## 4 2000 90 9.0 392.50 45
## 5 2001 88 12.5 373.50 51
## 6 2002 82 20.0 384.50 41
## 7 2003 85 16.5 418.00 50
## 8 2004 86 15.0 442.00 51
## 9 2005 96 5.0 428.75 51
## 10 2006 81 21.0 369.50 42
## 11 2007 80 22.0 303.50 44
## 12 2008 90 9.0 376.75 40
## 13 2009 85 16.5 324.75 38
## 14 2010 68 26.0 289.75 39
## 15 2011 75 24.0 335.50 39
## 16 2012 88 12.5 424.75 47
## 17 2013 90 9.0 353.25 46
## 18 2014 77 23.0 368.75 46
## 19 2015 95 6.0 500.50 54
## 20 2016 83 19.0 413.50 47
## 21 2017 84 18.0 354.75 43
## 22 2018 103 2.0 540.75 59
## 23 2019 98 3.0 449.00 55
## 24 2020 104 1.0 380.25 46
## 25 2021 94 7.0 354.75 37
## 26 2022 87 14.0 335.75 40
## HURRICAINES RANK HURRICAINES DAYS CAT 3 AND ABOVE HURRICAINES
## 1 2.0 220.25 28
## 2 8.5 179.25 21
## 3 23.0 135.50 21
## 4 15.0 160.50 20
## 5 6.0 162.75 24
## 6 19.0 171.50 27
## 7 8.5 175.00 25
## 8 6.0 216.00 32
## 9 6.0 189.50 27
## 10 18.0 165.75 27
## 11 16.0 118.75 22
## 12 20.5 132.50 24
## 13 25.0 115.25 21
## 14 23.0 112.00 19
## 15 23.0 121.00 21
## 16 10.5 154.00 24
## 17 13.0 127.75 22
## 18 13.0 150.75 26
## 19 4.0 221.00 39
## 20 10.5 163.25 26
## 21 17.0 135.75 20
## 22 1.0 223.50 33
## 23 3.0 172.25 35
## 24 13.0 115.25 24
## 25 26.0 119.00 16
## 26 20.5 115.25 17
## CAT 3 AND ABOVE HURRICAINES RANK CAT 3 AND ABOVE HURRICAINES DAYS
## 1 5.0 87.75
## 2 19.5 46.00
## 3 19.5 46.50
## 4 22.5 39.25
## 5 13.5 38.50
## 6 7.0 69.50
## 7 11.0 68.00
## 8 4.0 99.00
## 9 7.0 79.50
## 10 7.0 59.25
## 11 16.5 41.75
## 12 13.5 33.25
## 13 19.5 49.00
## 14 24.0 38.75
## 15 19.5 36.50
## 16 13.5 47.50
## 17 16.5 37.00
## 18 9.5 54.50
## 19 1.0 88.00
## 20 9.5 58.75
## 21 22.5 34.25
## 22 3.0 91.00
## 23 2.0 64.50
## 24 13.5 35.50
## 25 26.0 49.00
## 26 25.0 36.25
## ACCUMULATED CYCLONE ENERGY ACCUMULATED CYCLONE ENERGY RANK
## 1 1099.2 2.0
## 2 773.1 10.0
## 3 606.4 21.0
## 4 677.3 14.0
## 5 672.4 15.0
## 6 812.0 8.0
## 7 833.0 7.0
## 8 1024.4 4.0
## 9 899.6 5.0
## 10 761.0 11.0
## 11 568.1 24.0
## 12 613.9 19.0
## 13 609.6 20.0
## 14 526.8 26.0
## 15 573.8 23.0
## 16 740.5 12.0
## 17 618.5 18.0
## 18 724.0 13.0
## 19 1047.0 3.0
## 20 806.5 9.0
## 21 621.1 16.5
## 22 1108.4 1.0
## 23 854.8 6.0
## 24 599.1 22.0
## 25 621.1 16.5
## 26 559.6 25.0
df3_table <- datatable(df3_rank)
df3_table
library(ggplot2)
library(ggrepel)
## Warning: package 'ggrepel' was built under R version 4.2.2
# Your existing ggplot code
p1 <- ggplot(df3_rank, aes(x = YEAR, y = HURRICAINES, label = HURRICAINES)) +
geom_point(color = "#69b3a2") +
geom_text_repel(data = df3_rank[!is.na(df3_rank$YEAR), , ]) +
geom_segment(
color = "#69b3a2",
aes(
xend = c(tail(YEAR, n = -1), NA),
yend = c(tail(HURRICAINES, n = -1), NA)
),
arrow = arrow(length = unit(0.3, "cm"))
) +
labs(x = "Year", y = "Number of Hurricaines") +
theme(legend.position = "none")
# Rotate year labels by 45 degrees
p1 <- p1 + theme(axis.text.x = element_text(angle = 45, hjust = 1))
# Adjust height and width
p1 <- p1 + theme(
plot.background = element_rect(fill = "white"),
plot.margin = margin(20, 20, 20, 20)
)
# Add title and subtitle
p1 <- p1 + labs(
title = "HURRICAINES PER YEAR",
subtitle = "1997 to 2022"
)
# Align title to the left
p1 <- p1 + theme(
plot.title = element_text(hjust = 0)
)
# Change plot dimensions
p1 <- p1 + theme(
plot.background = element_rect(fill = "white"),
plot.margin = margin(20, 20, 20, 20)
)
# Print the modified plot
p1
## Warning: Removed 1 rows containing missing values (`geom_segment()`).
# Load necessary libraries if not loaded
library(ggplot2)
library(dplyr)
library(tidyr)
## Warning: package 'tidyr' was built under R version 4.2.2
# Assuming your data is named df3_rank and has the structure mentioned
# Create a new variable "Category" for faceting
df3_rank <- df3_rank %>%
pivot_longer(cols = c("NAMED STORMS", "HURRICAINES", "CAT 3 AND ABOVE HURRICAINES"),
names_to = "Category", values_to = "Count")
# Define the order of the facets
category_order <- c("NAMED STORMS", "HURRICAINES", "CAT 3 AND ABOVE HURRICAINES")
# Reorder the levels of the "Category" factor
df3_rank$Category <- factor(df3_rank$Category, levels = category_order)
# Plot the data using facets and add connecting lines
p <- ggplot(df3_rank, 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))
# Add title and subtitle
p <- p + labs(
title = "Meteorological Statistics Over the Years",
subtitle = "Yearly counts of meteorological events from 1997 to 2022"
)
# Set custom colors for the lines
p <- p + scale_color_manual(values = c("NAMED STORMS" = "blue", "HURRICAINES" = "green", "CAT 3 AND ABOVE HURRICAINES" = "red"))
# Print the modified plot
print(p)
