hw04

# Load necessary libraries
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

library(readr)
library(tidyr)
# Load stock data
stock_df <- read_csv("/cloud/project/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.

# Assume stock_df is your original data frame
stock_df_long <- stock_df %>% 
  pivot_longer(
    cols = -company,  # Use '-' to exclude 'company' column
    names_to = c("year", "week"),  # New columns for year and week
    names_pattern = "(\\d{4})_week(\\d+)",  # Regex to match year and week format
    names_transform = list(year = as.integer, week = as.integer),  # Convert to integers
    values_to = "price"  # Values from wide format are prices
  )

# Check the result
stock_df_long

## # A tibble: 525 × 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.
##  7 Amazon   2019     7 1608.
##  8 Amazon   2019     8 1632.
##  9 Amazon   2019     9 1672.
## 10 Amazon   2019    10 1621.
## # ℹ 515 more rows