==============================================================
R Data Transformation Assignment
Name : Faiz Haikal Nugraha Sunarto
ID : 114035108
Task : Transform stock price data from wide to long format
==============================================================
Load required 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(scales)
##
## Attaching package: 'scales'
##
## The following object is masked from 'package:purrr':
##
## discard
##
## The following object is masked from 'package:readr':
##
## col_factor
library(readxl)
library(writexl)
————————————————————–
1. Import dataset
————————————————————–
Make sure the file path matches your actual location
stock_df <- read_csv("downloads/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.
# Preview the dataset
stock_df
## # A tibble: 5 × 106
## company `2019_week1` `2019_week2` `2019_week3` `2019_week4` `2019_week5`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Amazon 1848. 1641. 1696. 1671. 1626.
## 2 Apple 73.4 38.1 39.2 39.4 41.6
## 3 Facebook 205. 144. 150. 149. 166.
## 4 Google 1337. 1057. 1098. 1091. 1111.
## 5 Microsoft 158. 103. 108. 107. 103.
## # ℹ 100 more variables: `2019_week6` <dbl>, `2019_week7` <dbl>,
## # `2019_week8` <dbl>, `2019_week9` <dbl>, `2019_week10` <dbl>,
## # `2019_week11` <dbl>, `2019_week12` <dbl>, `2019_week13` <dbl>,
## # `2019_week14` <dbl>, `2019_week15` <dbl>, `2019_week16` <dbl>,
## # `2019_week17` <dbl>, `2019_week18` <dbl>, `2019_week19` <dbl>,
## # `2019_week20` <dbl>, `2019_week21` <dbl>, `2019_week22` <dbl>,
## # `2019_week23` <dbl>, `2019_week24` <dbl>, `2019_week25` <dbl>, …
————————————————————–
2. Transform data (Wide → Long)
————————————————————–
stock_df_long <- stock_df %>%
pivot_longer(cols = !company,
names_to = c("year", "week"),
names_sep = "_week",
names_transform = list(year = as.integer, week = as.integer),
values_to = "price")