Use area charts to visualize monthly rainfall trends in 5 Indian cities, highlighting seasonal patterns.
library(ggplot2)
library(dplyr)
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, unionlibrary(readr)
library(tidyr)
library(stringr)rainfall_data <- read.csv("C:/Users/kumku/Downloads/dvfinalll.csv")
head(rainfall_data) STATE_UT_NAME DISTRICT JAN FEB MAR APR MAY JUN JUL
1 ANDAMAN And NICOBAR ISLANDS NICOBAR 107.3 57.9 65.2 117.0 358.5 295.5 285.0
2 RAJASTHAN TONK 5.0 5.3 2.7 3.0 10.1 56.1 219.7
3 RAJASTHAN UDAIPUR 2.8 2.0 4.3 2.2 8.2 73.6 207.5
4 RAJASTHAN DHOLPUR 8.6 9.5 7.0 2.5 8.6 54.5 211.7
5 RAJASTHAN BARAN 7.1 3.2 2.8 1.7 6.5 73.3 295.3
6 GUJARAT AMRELI 0.6 0.2 1.4 0.2 3.2 104.8 190.8
AUG SEP OCT NOV DEC ANNUAL Jan.Feb Mar.May Jun.Sep Oct.Dec
1 271.9 354.8 326.0 315.2 250.9 2805.2 165.2 540.7 1207.2 892.1
2 210.5 79.7 13.9 4.9 3.0 613.9 10.3 15.8 566.0 21.8
3 203.7 106.5 15.2 11.1 2.6 639.7 4.8 14.7 591.3 28.9
4 266.1 117.7 26.3 4.3 5.3 722.1 18.1 18.1 650.0 35.9
5 303.6 120.0 25.2 9.7 4.3 852.7 10.3 11.0 792.2 39.2
6 126.2 96.4 25.4 16.6 1.5 567.3 0.8 4.8 518.2 43.5Transform the data so that each row represents a single observation of rainfall for a specific district and month.
monthly_data <- rainfall_data %>%
pivot_longer(cols = JAN:DEC, names_to = "Month", values_to = "Rainfall")Ensure that months are ordered chronologically for accurate plotting.
monthly_data$Month <- factor(monthly_data$Month,
levels = c("JAN", "FEB", "MAR", "APR", "MAY", "JUN","JUL", "AUG", "SEP", "OCT", "NOV", "DEC"),
ordered = TRUE)Choose the cities you want to analyze.
selected_districts <- c("Shimoga", "Udaipur", "Chennai", "Kolkata", "Thane")Subset the data to include only the selected districts
unique(monthly_data$DISTRICT) [1] "NICOBAR" "TONK" "UDAIPUR" "DHOLPUR"
[5] "BARAN" "AMRELI" "BHAVNAGAR" "JAMNAGAR"
[9] "JUNAGADH" "KUTCH" "RAJKOT" "SURENDRANAGAR"
[13] "PORBANDAR" "DNH" "DAMAN" "DIU"
[17] "MUMBAI CITY" "RAIGAD" "RATNAGIRI" "THANE"
[21] "SINDHUDURG" "HYDERABAD" "KARIMNAGAR" "KHAMMAM"
[25] "MAHABUBNAGAR" "MEDAK" "NALGONDA" "NIZAMABAD"
[29] "WARANGAL" "RANGAREDDY" "ANANTAPUR" "CHITTOOR"
[33] "KUDDAPAH" "KURNOOL" "VELLORE" "COIMBATORE"
[37] "DHARMAPURI" "KANYAKUMARI" "CHENNAI" "MADURAI"
[41] "DHARWAD" "GULBARGA" "YADGIR" "RAICHUR"
[45] "BAGALKOTE" "GADAG" "HAVERI" "KOPPAL"
[49] "BANGALORE RUR" "BELLARY" "CHIKMAGALUR" "CHITRADURGA"
[53] "KODAGU" "HASSAN" "KOLAR" "MANDYA"
[57] "MYSORE" "SHIMOGA" "TUMKUR" "BANGALORE URB"
[61] "CHAMARAJANAGA" "DAVANGERE" "RAMNAGAR(BNGR)" "CHICKBALLAPUR"
[65] "ALAPPUZHA" "CANNUR" "ERNAKULAM" "KOTTAYAM"
[69] "KOZHIKODE" "MALAPPURAM" "PALAKKAD" "KOLLAM"
[73] "THRISSUR" "THIRUVANANTHA" "IDUKKI" "KASARGOD"
[77] "PATHANAMTHITTA" "WAYANAD" "LAKSHADWEEP" # Convert both sides to lowercase to avoid mismatch
monthly_data <- monthly_data %>%
mutate(DISTRICT = str_to_lower(DISTRICT))
selected_districts <- c("shimoga", "udaipur", "chennai", "tumkur", "thane")
rainfall_filtered <- monthly_data %>%
filter(DISTRICT %in% selected_districts)
# View the result
#head(rainfall_filtered)
summary(rainfall_filtered$Rainfall) Min. 1st Qu. Median Mean 3rd Qu. Max.
0.20 5.80 44.05 117.21 141.30 973.70 rainfall_filtered %>% filter(is.na(Rainfall))# A tibble: 0 × 9
# ℹ 9 variables: STATE_UT_NAME <chr>, DISTRICT <chr>, ANNUAL <dbl>,
# Jan.Feb <dbl>, Mar.May <dbl>, Jun.Sep <dbl>, Oct.Dec <dbl>, Month <ord>,
# Rainfall <dbl>rainfall_filtered <- rainfall_filtered %>%
filter(!is.na(Rainfall))Create an area plot to visualize the monthly rainfall trends for each selected district
# Ensure Month is a factor with all levels
rainfall_filtered$Month <- factor(
rainfall_filtered$Month,
levels = c("JAN", "FEB", "MAR", "APR", "MAY", "JUN",
"JUL", "AUG", "SEP", "OCT", "NOV", "DEC"),
ordered = TRUE
)
# Complete the data: fill in missing Month-DISTRICT combos
rainfall_completed <- rainfall_filtered %>%
tidyr::complete(DISTRICT, Month, fill = list(Rainfall = NA))
scale_x_discrete(drop = FALSE)<ggproto object: Class ScaleDiscretePosition, ScaleDiscrete, Scale, gg>
aesthetics: x xmin xmax xend
axis_order: function
break_info: function
break_positions: function
breaks: waiver
call: call
clone: function
dimension: function
drop: FALSE
expand: waiver
get_breaks: function
get_breaks_minor: function
get_labels: function
get_limits: function
get_transformation: function
guide: waiver
is_discrete: function
is_empty: function
labels: waiver
limits: NULL
make_sec_title: function
make_title: function
map: function
map_df: function
n.breaks.cache: NULL
na.translate: TRUE
na.value: NA
name: waiver
palette: function
palette.cache: NULL
position: bottom
range: environment
range_c: environment
rescale: function
reset: function
train: function
train_df: function
transform: function
transform_df: function
super: <ggproto object: Class ScaleDiscretePosition, ScaleDiscrete, Scale, gg>ggplot(rainfall_completed, aes(x = Month, group = DISTRICT)) +
geom_ribbon(aes(ymin = 0, ymax = Rainfall), fill = "skyblue", alpha = 0.5) +
geom_line(aes(y = Rainfall), color = "black", linewidth = 1) +
facet_wrap(~ DISTRICT, scales = "free_x") +
scale_x_discrete(drop = FALSE) +
labs(
title = "Monthly Rainfall Trends in Selected Indian Cities",
x = "Month",
y = "Rainfall (mm)"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))