HW5_114035127

# Load libraries
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.1     ✔ stringr   1.5.2
## ✔ ggplot2   4.0.0     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── 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)

# Import data
stock_df <- read_csv("stock_df.csv")

## Rows: 5 Columns: 106
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr   (1): company
## dbl (105): 2019_week1, 2019_week2, 2019_week3, 2019_week4, 2019_week5, 2019_...
## 
## 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.

# Reshape from wide to long
stock_df_long <- stock_df %>%
  pivot_longer(
    cols = starts_with("2019_week"),
    names_to = "week",
    values_to = "price"
  ) %>%
  separate(week, into = c("year", "week"), sep = "_week") %>%
  mutate(
    year = as.integer(year),
    week = as.integer(week)
  )

# View result
head(stock_df_long)

## # A tibble: 6 × 57
##   company `2020_week1` `2020_week2` `2020_week3` `2020_week4` `2020_week5`
##   <chr>          <dbl>        <dbl>        <dbl>        <dbl>        <dbl>
## 1 Amazon         1875.        1883.        1865.        1862.        2009.
## 2 Amazon         1875.        1883.        1865.        1862.        2009.
## 3 Amazon         1875.        1883.        1865.        1862.        2009.
## 4 Amazon         1875.        1883.        1865.        1862.        2009.
## 5 Amazon         1875.        1883.        1865.        1862.        2009.
## 6 Amazon         1875.        1883.        1865.        1862.        2009.
## # ℹ 51 more variables: `2020_week6` <dbl>, `2020_week7` <dbl>,
## #   `2020_week8` <dbl>, `2020_week9` <dbl>, `2020_week10` <dbl>,
## #   `2020_week11` <dbl>, `2020_week12` <dbl>, `2020_week13` <dbl>,
## #   `2020_week14` <dbl>, `2020_week15` <dbl>, `2020_week16` <dbl>,
## #   `2020_week17` <dbl>, `2020_week18` <dbl>, `2020_week19` <dbl>,
## #   `2020_week20` <dbl>, `2020_week21` <dbl>, `2020_week22` <dbl>,
## #   `2020_week23` <dbl>, `2020_week24` <dbl>, `2020_week25` <dbl>, …

# Reshape from wide to long (all years)
stock_df_long <- stock_df %>%
  pivot_longer(
    cols = matches("^\\d{4}_week\\d+$"),  # matches 2019_week1, 2020_week2, etc.
    names_to = "week",
    values_to = "price"
  ) %>%
  separate(week, into = c("year", "week"), sep = "_week") %>%
  mutate(
    year = as.integer(year),
    week = as.integer(week)
  )

# Check result
head(stock_df_long)

## # A tibble: 6 × 4
##   company  year  week price
##   <chr>   <int> <int> <dbl>
## 1 Amazon   2019     1 1848.
## 2 Amazon   2019     2 1641.
## 3 Amazon   2019     3 1696.
## 4 Amazon   2019     4 1671.
## 5 Amazon   2019     5 1626.
## 6 Amazon   2019     6 1588.