##Q2

library(rvest)
library(robotstxt)

paths_allowed("https://en.wikipedia.org/wiki/List_of_current_United_States_governors")
##  en.wikipedia.org
## [1] TRUE

##Q3

library(rvest)
library(dplyr)
## 
## 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
url <- "https://en.wikipedia.org/wiki/List_of_current_United_States_governors"
webpage <- read_html(url)
governors_table <- webpage %>%
  html_node("table.wikitable") %>%
  html_table()
governors_tibble <- as_tibble(governors_table, .name_repair = "unique")
## New names:
## • `Party[12]` -> `Party[12]...4`
## • `Party[12]` -> `Party[12]...5`
print(governors_tibble)
## # A tibble: 50 × 10
##    State              Image `Governor[12]` `Party[12]...4` `Party[12]...5` Born 
##    <chr>              <lgl> <chr>          <lgl>           <chr>           <chr>
##  1 Alabama (list)     NA    Kay Ivey       NA              Republican      (194…
##  2 Alaska (list)      NA    Mike Dunleavy  NA              Republican      (196…
##  3 Arizona (list)     NA    Katie Hobbs    NA              Democratic      (196…
##  4 Arkansas (list)    NA    Sarah Huckabe… NA              Republican      (198…
##  5 California (list)  NA    Gavin Newsom   NA              Democratic      (196…
##  6 Colorado (list)    NA    Jared Polis    NA              Democratic      (197…
##  7 Connecticut (list) NA    Ned Lamont     NA              Democratic      (195…
##  8 Delaware (list)    NA    Matt Meyer     NA              Democratic      (197…
##  9 Florida (list)     NA    Ron DeSantis   NA              Republican      (197…
## 10 Georgia (list)     NA    Brian Kemp     NA              Republican      (196…
## # ℹ 40 more rows
## # ℹ 4 more variables: `Prior public experience[13]` <chr>,
## #   `Inauguration[12]` <chr>, `End of term[12]` <chr>, Ref. <chr>

##Q4

str(governors_tibble)
## tibble [50 × 10] (S3: tbl_df/tbl/data.frame)
##  $ State                      : chr [1:50] "Alabama (list)" "Alaska (list)" "Arizona (list)" "Arkansas (list)" ...
##  $ Image                      : logi [1:50] NA NA NA NA NA NA ...
##  $ Governor[12]               : chr [1:50] "Kay Ivey" "Mike Dunleavy" "Katie Hobbs" "Sarah Huckabee Sanders" ...
##  $ Party[12]...4              : logi [1:50] NA NA NA NA NA NA ...
##  $ Party[12]...5              : chr [1:50] "Republican" "Republican" "Democratic" "Republican" ...
##  $ Born                       : chr [1:50] "(1944-10-15) October 15, 1944 (age 80)" "(1961-05-05) May 5, 1961 (age 63)" "(1969-12-28) December 28, 1969 (age 55)" "(1982-08-13) August 13, 1982 (age 42)" ...
##  $ Prior public experience[13]: chr [1:50] "Lieutenant GovernorState Treasurer" "Alaska Senate" "Secretary of StateMinority Leader of the Arizona SenateArizona House" "White House Press Secretary" ...
##  $ Inauguration[12]           : chr [1:50] "April 10, 2017" "December 3, 2018" "January 2, 2023" "January 10, 2023" ...
##  $ End of term[12]            : chr [1:50] "2027 (term limits)" "2026 (term limits)" "2027" "2027" ...
##  $ Ref.                       : chr [1:50] "[16]" "[17]" "[18]" "[19]" ...

##Q5

all_na_columns <- sum(sapply(governors_tibble, function(column) all(is.na(column))))
print(all_na_columns)
## [1] 2

##Q6

cleaned_governors <- governors_tibble %>%
  select(where(~ !all(is.na(.))))

colnames(cleaned_governors) <- gsub("\\[\\d+\\]", "", colnames(cleaned_governors))
print(colnames(cleaned_governors))
## [1] "State"                   "Governor"               
## [3] "Party...5"               "Born"                   
## [5] "Prior public experience" "Inauguration"           
## [7] "End of term"             "Ref."

##Q8

library(jsonlite)
library(httr)

url2 <- "https://min-api.cryptocompare.com/data/v2/histoday?fsym=XMR&tsym=USD&limit=200"
data <- fromJSON(url2)
xmr_data <- as_tibble(data$Data$Data)

xmr_data <- xmr_data %>%
  mutate(time = as.POSIXct(time, origin = "1970-01-01"))

min_open_price <- min(xmr_data$open, na.rm = TRUE)
min_open_time <- xmr_data %>%
  filter(open == min_open_price) %>%
  select(time) %>%
  pull()

print(min_open_price)
## [1] 136.72
print(min_open_time)
## [1] "2024-10-02 20:00:00 EDT"

##Q9

observation_number <- which(xmr_data$open == min_open_price)
regular_date_time <- as.POSIXct(xmr_data$time[observation_number], origin = "1970-01-01")
print(regular_date_time)
## [1] "2024-10-02 20:00:00 EDT"

##Q10

data(airquality)
summary(airquality)
##      Ozone           Solar.R           Wind             Temp      
##  Min.   :  1.00   Min.   :  7.0   Min.   : 1.700   Min.   :56.00  
##  1st Qu.: 18.00   1st Qu.:115.8   1st Qu.: 7.400   1st Qu.:72.00  
##  Median : 31.50   Median :205.0   Median : 9.700   Median :79.00  
##  Mean   : 42.13   Mean   :185.9   Mean   : 9.958   Mean   :77.88  
##  3rd Qu.: 63.25   3rd Qu.:258.8   3rd Qu.:11.500   3rd Qu.:85.00  
##  Max.   :168.00   Max.   :334.0   Max.   :20.700   Max.   :97.00  
##  NA's   :37       NA's   :7                                       
##      Month            Day      
##  Min.   :5.000   Min.   : 1.0  
##  1st Qu.:6.000   1st Qu.: 8.0  
##  Median :7.000   Median :16.0  
##  Mean   :6.993   Mean   :15.8  
##  3rd Qu.:8.000   3rd Qu.:23.0  
##  Max.   :9.000   Max.   :31.0  
##

##Q11

data(airquality)
hot_days <- subset(airquality, Wind < 8 & Temp > 90)
num_hot_days <- nrow(hot_days)
num_hot_days
## [1] 9

##Q12

plot(airquality$Month, airquality$Temp, main="Temperature by Month", 
     xlab="Month", ylab="Temperature", pch=19)

lowest_temp_month <- airquality$Month[which.min(airquality$Temp)]
lowest_temp_month
## [1] 5

##Q15

library(nycflights13)
total_delay_by_airport <- flights %>%
  group_by(origin) %>%
  summarise(total_delay = sum(dep_delay, na.rm = TRUE)) %>%
  arrange(desc(total_delay))
total_delay_by_airport
## # A tibble: 3 × 2
##   origin total_delay
##   <chr>        <dbl>
## 1 EWR        1776635
## 2 JFK        1325264
## 3 LGA        1050301