hw01

# Load required libraries
library(tidyverse)

## ── 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   3.5.1     ✔ tibble    3.2.1
## ✔ 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(lubridate)
library(tidyquant)

## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo 
## ── Attaching core tidyquant packages ──────────────────────── tidyquant 1.0.9 ──
## ✔ PerformanceAnalytics 2.0.4      ✔ TTR                  0.24.4
## ✔ quantmod             0.4.26     ✔ xts                  0.14.0── Conflicts ────────────────────────────────────────── tidyquant_conflicts() ──
## ✖ zoo::as.Date()                 masks base::as.Date()
## ✖ zoo::as.Date.numeric()         masks base::as.Date.numeric()
## ✖ dplyr::filter()                masks stats::filter()
## ✖ xts::first()                   masks dplyr::first()
## ✖ dplyr::lag()                   masks stats::lag()
## ✖ xts::last()                    masks dplyr::last()
## ✖ PerformanceAnalytics::legend() masks graphics::legend()
## ✖ quantmod::summary()            masks base::summary()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(readxl)
library(writexl)

# Step 2: Import the data file 'bikes.xlsx' from the Desktop
# Replace 'your_username' with your actual system username
bikes_data <- read_excel("/cloud/project/bikes.xlsx")  # For Windows
# bikes_data <- read_excel("/Users/your_username/Desktop/bikes.xlsx")  # For Mac

# Step 3: Show "model" and "price" column with "price" in descending order
bikes_price_desc <- bikes_data %>%
  select(model, price) %>%
  arrange(desc(price))

# View the result
print(bikes_price_desc)

## # A tibble: 97 × 2
##    model                          price
##    <chr>                          <dbl>
##  1 Supersix Evo Black Inc.        12790
##  2 Scalpel-Si Black Inc.          12790
##  3 Habit Hi-Mod Black Inc.        12250
##  4 F-Si Black Inc.                11190
##  5 Supersix Evo Hi-Mod Team       10660
##  6 Synapse Hi-Mod Disc Black Inc.  9590
##  7 Scalpel-Si Race                 9060
##  8 F-Si Hi-Mod Team                9060
##  9 Trigger Carbon 1                8200
## 10 Supersix Evo Hi-Mod Dura Ace 1  7990
## # ℹ 87 more rows

# Step 4: Show "model" and "price" column where "price" is greater than the mean value of price
mean_price <- mean(bikes_data$price, na.rm = TRUE)

bikes_price_above_mean <- bikes_data %>%
  select(model, price) %>%
  filter(price > mean_price)

# View the result
print(bikes_price_above_mean)

## # A tibble: 35 × 2
##    model                          price
##    <chr>                          <dbl>
##  1 Supersix Evo Black Inc.        12790
##  2 Supersix Evo Hi-Mod Team       10660
##  3 Supersix Evo Hi-Mod Dura Ace 1  7990
##  4 Supersix Evo Hi-Mod Dura Ace 2  5330
##  5 Supersix Evo Hi-Mod Utegra      4260
##  6 CAAD12 Black Inc                5860
##  7 CAAD12 Disc Dura Ace            4260
##  8 Synapse Hi-Mod Disc Black Inc.  9590
##  9 Synapse Hi-Mod Disc Red         7460
## 10 Synapse Hi-Mod Dura Ace         5860
## # ℹ 25 more rows