library(readr)
library(dplyr)
library(lubridate)

# Read a delimited file into a tibble
data <- read_csv("Downloads/S123_69f6a2b6440848bab051f597ff4a8bf2_CSV/_25_Million_Trees_Initiative_Survey_0.csv")

# Examine the column specifications for a data frame
spec(data)

# Parse date-times with year, month, and day, hour, minute, and second components from col_character.
data <- data %>% 
  mutate(
    `Start Date of Planting` = mdy_hms(`Start Date of Planting`),
    `End Date of Planting` = mdy_hms(`End Date of Planting`)
)

# Get/set months and years component of lanting date-time.
data <- data %>%
  mutate(
    plant_month = month(`Start Date of Planting`),   # Extracts the month
    plant_year = year(`Start Date of Planting`)      # Extracts the year
  )

# Group by municipality & county and summerize the total number of trees planted.
aggregated_data <- data %>%
  group_by(`Year of Planting`, `Month of Planting`, Municipality, County) %>%
  summarize(`Total Tree Plantings` = sum(`Number of Trees Planted`, na.rm = TRUE))

# View the aggregated data
print(aggregated_data)