Week 3B

Window Functions

Load Libraries

# import(tidyverse)
library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.4.3

## Warning: package 'ggplot2' was built under R version 4.4.3

## Warning: package 'tibble' was built under R version 4.4.3

## Warning: package 'readr' was built under R version 4.4.3

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── 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(glue)

## Warning: package 'glue' was built under R version 4.4.3

Load Data

delhi_data <- read.csv("DailyDelhiClimateTrain.csv")

Define Year to Date Function

yearToDate <- function(data, end, col) {
  # Ensure dates in date column are of Date type
  data <- data %>% mutate(date = ymd(data$date))
  
  # Subset data from beginning of year to given date
  subset_data <- data[data$date <= end, ,drop = FALSE]
  
  # Find the mean for target column
  mean_temp <- mean(subset_data[[col]], na.rm = TRUE)
  
  return(mean_temp)
}

Testing YTD

# Testing 

date1 <- ymd("2013-02-01")
test <- yearToDate(delhi_data, date1, "humidity") %>%
  round(2)

glue("Expected YTD Result: 73.02 \n Actual Result: {test}")

## Expected YTD Result: 73.02 
## Actual Result: 73.03

Define 6 Day Average Function

sixDayAvg <- function(data, start_date, col) {
  # Ensure dates in date column are of Date type
  data <- data %>% mutate(date = ymd(data$date))
  
  # Define the 6-day window
  end_date <- start_date + 5
  
  # Subset the data for those 6 days
  subset_data <- data[data$date >= start_date & data$date <= end_date, , drop = FALSE]
  
  # Find mean for column
  mean_temp <- mean(subset_data[[col]], na.rm = TRUE)
  
  return(mean_temp)
}

Testing 6 Day Avg

date2 <- ymd("2013-02-01")
test2 <- sixDayAvg(delhi_data, date2, "humidity") %>%
  round(2)

glue("Expected 6 Day Result: 75.68 \n Actual Result: {test2}")

## Expected 6 Day Result: 75.68 
## Actual Result: 75.69