# Importing the packages and reading the data set
library(readr)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ purrr 1.0.2
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.3 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(dplyr)
my_data <- read_delim("C:/Users/user/Documents/Statistics/Telangana_2018_complete_weather_data.csv",delim=",")
## Rows: 311157 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): District, Mandal, Location, Date
## dbl (6): row_id, temp_min, temp_max, humidity_min, humidity_max, wind_speed
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
grouped_data_1 <- my_data %>%
group_by(District,Mandal,Location)%>%
summarise(temp_min,temp_max)
## Warning: Returning more (or less) than 1 row per `summarise()` group was deprecated in
## dplyr 1.1.0.
## ℹ Please use `reframe()` instead.
## ℹ When switching from `summarise()` to `reframe()`, remember that `reframe()`
## always returns an ungrouped data frame and adjust accordingly.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## `summarise()` has grouped output by 'District', 'Mandal', 'Location'. You can
## override using the `.groups` argument.
print(grouped_data_1)
## # A tibble: 311,157 × 5
## # Groups: District, Mandal, Location [1,678]
## District Mandal Location temp_min temp_max
## <chr> <chr> <chr> <dbl> <dbl>
## 1 Adilabad Adilabad (Urban) Adilabad 22.3 34.3
## 2 Adilabad Adilabad (Urban) Adilabad 22.4 35.1
## 3 Adilabad Adilabad (Urban) Adilabad 21.8 35.4
## 4 Adilabad Adilabad (Urban) Adilabad 21.5 36.1
## 5 Adilabad Adilabad (Urban) Adilabad 22.3 35
## 6 Adilabad Adilabad (Urban) Adilabad 21.4 34.9
## 7 Adilabad Adilabad (Urban) Adilabad 21.6 34.9
## 8 Adilabad Adilabad (Urban) Adilabad 19.6 35.2
## 9 Adilabad Adilabad (Urban) Adilabad 19.3 35.4
## 10 Adilabad Adilabad (Urban) Adilabad 19.3 34.8
## # ℹ 311,147 more rows
#%>%
#summarise(mean_temp_min=mean(temp_min),mean_temp_max=mean(temp_max))
#print(grouped_data_1)
grouped_data_2 <-my_data %>%
group_by(District,Mandal,Location) %>%
summarise(humidity_min,humidity_max)
## Warning: Returning more (or less) than 1 row per `summarise()` group was deprecated in
## dplyr 1.1.0.
## ℹ Please use `reframe()` instead.
## ℹ When switching from `summarise()` to `reframe()`, remember that `reframe()`
## always returns an ungrouped data frame and adjust accordingly.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## `summarise()` has grouped output by 'District', 'Mandal', 'Location'. You can
## override using the `.groups` argument.
print(grouped_data_2)
## # A tibble: 311,157 × 5
## # Groups: District, Mandal, Location [1,678]
## District Mandal Location humidity_min humidity_max
## <chr> <chr> <chr> <dbl> <dbl>
## 1 Adilabad Adilabad (Urban) Adilabad 61.1 92.4
## 2 Adilabad Adilabad (Urban) Adilabad 56.2 92.1
## 3 Adilabad Adilabad (Urban) Adilabad 55.7 92.1
## 4 Adilabad Adilabad (Urban) Adilabad 57.5 90.9
## 5 Adilabad Adilabad (Urban) Adilabad 53.9 91.7
## 6 Adilabad Adilabad (Urban) Adilabad 56.4 91.7
## 7 Adilabad Adilabad (Urban) Adilabad 58 91.6
## 8 Adilabad Adilabad (Urban) Adilabad 53.3 91
## 9 Adilabad Adilabad (Urban) Adilabad 49.5 90.5
## 10 Adilabad Adilabad (Urban) Adilabad 51.5 90.3
## # ℹ 311,147 more rows
grouped_data_3 <- my_data %>%
group_by(District,Mandal,Location) %>%
summarise(wind_speed)
## Warning: Returning more (or less) than 1 row per `summarise()` group was deprecated in
## dplyr 1.1.0.
## ℹ Please use `reframe()` instead.
## ℹ When switching from `summarise()` to `reframe()`, remember that `reframe()`
## always returns an ungrouped data frame and adjust accordingly.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## `summarise()` has grouped output by 'District', 'Mandal', 'Location'. You can
## override using the `.groups` argument.
print(grouped_data_3)
## # A tibble: 311,157 × 4
## # Groups: District, Mandal, Location [1,678]
## District Mandal Location wind_speed
## <chr> <chr> <chr> <dbl>
## 1 Adilabad Adilabad (Urban) Adilabad 5.5
## 2 Adilabad Adilabad (Urban) Adilabad 6.7
## 3 Adilabad Adilabad (Urban) Adilabad 6.6
## 4 Adilabad Adilabad (Urban) Adilabad 5.7
## 5 Adilabad Adilabad (Urban) Adilabad 7.9
## 6 Adilabad Adilabad (Urban) Adilabad 6.5
## 7 Adilabad Adilabad (Urban) Adilabad 5.4
## 8 Adilabad Adilabad (Urban) Adilabad 9
## 9 Adilabad Adilabad (Urban) Adilabad 9.6
## 10 Adilabad Adilabad (Urban) Adilabad 13
## # ℹ 311,147 more rows
avg_temp_max <- mean(grouped_data_1$temp_max)
count_greater_avg_temp <- sum(grouped_data_1$temp_max >avg_temp_max)
total_count <- nrow(my_data)
prob_temp_max_great_than_avg <- (count_greater_avg_temp)/total_count
cat("Probability that temp_max is greater than avg_temp_max:", prob_temp_max_great_than_avg, "\n")
## Probability that temp_max is greater than avg_temp_max: 0.4912054
### The probability that temperature will be greater than average temperature has been calculated
avg_humid_max <-mean(grouped_data_2$humidity_max)
count_greater_avg_humid <- sum(grouped_data_2$humidity_max >avg_humid_max)
total_count <- nrow(my_data)
prob_humid_max_great_than_avg <- (count_greater_avg_humid)/total_count
cat("Probability that humid_max is greater than avg_humid_max:", prob_humid_max_great_than_avg, "\n")
## Probability that humid_max is greater than avg_humid_max: 0.5622274
### The probability that humidity will be greater than average humidity has been calculated
avg_wind_speed <-mean(grouped_data_3$wind_speed)
count_greater_avg_wind_speed <- sum(grouped_data_3$wind_speed>avg_wind_speed)
total_count <- nrow(my_data)
prob_wind_speed_great_than_avg <- (count_greater_avg_wind_speed)/total_count
cat("Probability that wind_speed is greater than avg_wind_speed:", prob_wind_speed_great_than_avg, "\n")
## Probability that wind_speed is greater than avg_wind_speed: 0.4472405
### The probability that wind speed will be greater than average winds peed has been calculated
my_prob <- c(prob_humid_max_great_than_avg,prob_temp_max_great_than_avg,prob_wind_speed_great_than_avg)
lowest_prob_index <- which.min(my_prob)
tags <- rep("normal", length(my_prob))
tags[lowest_prob_index] <- "anomaly"
print(tags)
## [1] "normal" "normal" "anomaly"
### The lowest probability value has been indicated as an anomaly
# plotting the bar graph
ggplot(data=grouped_data_1)+
geom_bar(mapping=aes(x=District))+
theme(axis.text.x = element_text(angle = 45, hjust = 1))
# plotting the scatterplot graph
ggplot(data=my_data)+
geom_point(mapping=aes(x=temp_max,y=humidity_max))
# plotting the boxplot
ggplot(data=grouped_data_3)+
geom_boxplot(mapping=aes(x=District,y=wind_speed,fill = District))+
theme(axis.text.x = element_text(angle = 45, hjust = 1))
