rm(list=ls())
library(tidyverse)
library(tidyquant)
library(timetk)Task: Load packages tidyquant, tidyverse and timetk.
Import the data file tej_day_price_2024_20250630.txt using
read_csv(), read_tsv() or
read_delim().
# Import data using read_tsv() since the file is tab-delimited
tej_data <- read_tsv("tej_day_price_2024_20250630.txt")
# Show the imported results
glimpse(tej_data)## Rows: 337,347
## Columns: 12
## $ CO_ID <chr> "1101 TCC", "1102 ACC", "1103 CHC", "1104 UCC", …
## $ Date <dbl> 20240102, 20240102, 20240102, 20240102, 20240102…
## $ `TSE ID` <dbl> 1101, 1102, 1103, 1104, 1108, 1109, 1110, 1201, …
## $ `TSE Sector` <chr> "01", "01", "01", "01", "01", "01", "01", "02", …
## $ `English Short Name` <chr> "TCC", "ACC", "CHC", "UCC", "Lucky Cement", "HSI…
## $ `Open(NTD)` <dbl> 32.5373, 37.2642, 17.7825, 26.0628, 14.1679, 16.…
## $ `High(NTD)` <dbl> 32.5373, 37.4442, 17.7825, 26.1505, 14.1679, 16.…
## $ `Low(NTD)` <dbl> 32.3038, 36.9492, 17.5953, 25.9750, 14.0343, 16.…
## $ `Close(NTD)` <dbl> 32.3972, 37.0392, 17.6421, 26.0628, 14.0788, 16.…
## $ `Volume(1000S)` <dbl> 14937, 6223, 171, 260, 442, 228, 57, 126, 48, 18…
## $ `Amount(NTD1000)` <dbl> 518751, 256522, 3240, 7736, 6992, 4159, 1075, 24…
## $ `Market Cap.(NTD MN)` <dbl> 262026, 145941, 14896, 19995, 6395, 6209, 10754,…Result: The dataset contains 337,347 rows and 12 columns with stock price data from the Taiwan Stock Exchange.
Task: Replace columns 2, 3, 5, 9, and 12 with new names: “date”, “id”, “name”, “price”, “cap”.
# Rename specific columns
tej_data <- tej_data %>%
rename(
date = 2,
id = 3,
name = 5,
price = 9,
cap = 12
) %>%
select(id, name, date, price, cap)
glimpse(tej_data)## Rows: 337,347
## Columns: 5
## $ id <dbl> 1101, 1102, 1103, 1104, 1108, 1109, 1110, 1201, 1203, 1210, 1213…
## $ name <chr> "TCC", "ACC", "CHC", "UCC", "Lucky Cement", "HSINGTA", "Tuna Cem…
## $ date <dbl> 20240102, 20240102, 20240102, 20240102, 20240102, 20240102, 2024…
## $ price <dbl> 32.3972, 37.0392, 17.6421, 26.0628, 14.0788, 16.1807, 18.3336, 1…
## $ cap <dbl> 262026, 145941, 14896, 19995, 6395, 6209, 10754, 9640, 13992, 52…Task: Select id, date, price columns. Change id to text, date to date format, and convert from long to wide format.
# Convert formats and reshape to wide
tej_wide <- tej_data %>%
select(id, date, price) %>%
mutate(
id = as.character(id),
date = ymd(date)
) %>%
pivot_wider(names_from = id, values_from = price)
head(tej_wide, 10)## # A tibble: 10 × 947
## date `1101` `1102` `1103` `1104` `1108` `1109` `1110` `1201` `1203`
## <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2024-01-02 32.4 37.0 17.6 26.1 14.1 16.2 18.3 18.2 55.3
## 2 2024-01-03 31.9 36.6 17.5 25.9 14.0 16.1 18.2 18.2 54.7
## 3 2024-01-04 31.9 37.0 17.5 25.5 14.1 16.1 18.4 18.1 54.1
## 4 2024-01-05 32.1 37.0 17.5 25.8 14.1 16.1 18.3 18.1 54.9
## 5 2024-01-08 32.0 37.2 17.6 25.7 14.2 16.1 18.3 18.1 54.6
## 6 2024-01-09 31.8 36.9 17.5 25.4 13.8 16.0 18.4 18.1 54.6
## 7 2024-01-10 31.5 36.6 17.4 25.4 13.7 16.0 18.5 18.0 53.4
## 8 2024-01-11 31.5 36.7 17.5 25.6 13.8 16.1 18.5 18.0 55.1
## 9 2024-01-12 31.5 36.6 17.5 25.6 13.8 16.0 18.4 18.0 54.4
## 10 2024-01-15 31.4 36.6 17.4 25.4 13.8 16.0 18.3 18.0 53.8
## # ℹ 937 more variables: `1210` <dbl>, `1213` <dbl>, `1215` <dbl>, `1216` <dbl>,
## # `1217` <dbl>, `1218` <dbl>, `1219` <dbl>, `1220` <dbl>, `1225` <dbl>,
## # `1227` <dbl>, `1229` <dbl>, `1231` <dbl>, `1232` <dbl>, `1233` <dbl>,
## # `1234` <dbl>, `1235` <dbl>, `1236` <dbl>, `1301` <dbl>, `1303` <dbl>,
## # `1304` <dbl>, `1305` <dbl>, `1307` <dbl>, `1308` <dbl>, `1309` <dbl>,
## # `1310` <dbl>, `1312` <dbl>, `1313` <dbl>, `1314` <dbl>, `1315` <dbl>,
## # `1316` <dbl>, `1319` <dbl>, `1321` <dbl>, `1323` <dbl>, `1324` <dbl>, …Task: Show stock ids with NA values and compute the number of NAs for each stock.
# Count NA values for each stock
na_summary <- tej_wide %>%
pivot_longer(-date, names_to = "key", values_to = "value") %>%
filter(is.na(value)) %>%
count(key, name = "value") %>%
arrange(value)
na_summary## # A tibble: 10 × 2
## key value
## <chr> <int>
## 1 7722 18
## 2 7732 43
## 3 7736 53
## 4 7750 108
## 5 7765 151
## 6 3716 160
## 7 4585 177
## 8 7780 196
## 9 7788 198
## 10 7799 217Result: 10 stocks contain NA values, ranging from 18 to 217 missing observations.
Task: Replace NA values with the closest available
stock prices using na.locf().
# Fill NA values forward
tej_filled <- tej_wide %>%
tk_tbl() %>%
mutate(across(-date, ~zoo::na.locf(., na.rm = FALSE)))
head(tej_filled, 10)## # A tibble: 10 × 947
## date `1101` `1102` `1103` `1104` `1108` `1109` `1110` `1201` `1203`
## <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2024-01-02 32.4 37.0 17.6 26.1 14.1 16.2 18.3 18.2 55.3
## 2 2024-01-03 31.9 36.6 17.5 25.9 14.0 16.1 18.2 18.2 54.7
## 3 2024-01-04 31.9 37.0 17.5 25.5 14.1 16.1 18.4 18.1 54.1
## 4 2024-01-05 32.1 37.0 17.5 25.8 14.1 16.1 18.3 18.1 54.9
## 5 2024-01-08 32.0 37.2 17.6 25.7 14.2 16.1 18.3 18.1 54.6
## 6 2024-01-09 31.8 36.9 17.5 25.4 13.8 16.0 18.4 18.1 54.6
## 7 2024-01-10 31.5 36.6 17.4 25.4 13.7 16.0 18.5 18.0 53.4
## 8 2024-01-11 31.5 36.7 17.5 25.6 13.8 16.1 18.5 18.0 55.1
## 9 2024-01-12 31.5 36.6 17.5 25.6 13.8 16.0 18.4 18.0 54.4
## 10 2024-01-15 31.4 36.6 17.4 25.4 13.8 16.0 18.3 18.0 53.8
## # ℹ 937 more variables: `1210` <dbl>, `1213` <dbl>, `1215` <dbl>, `1216` <dbl>,
## # `1217` <dbl>, `1218` <dbl>, `1219` <dbl>, `1220` <dbl>, `1225` <dbl>,
## # `1227` <dbl>, `1229` <dbl>, `1231` <dbl>, `1232` <dbl>, `1233` <dbl>,
## # `1234` <dbl>, `1235` <dbl>, `1236` <dbl>, `1301` <dbl>, `1303` <dbl>,
## # `1304` <dbl>, `1305` <dbl>, `1307` <dbl>, `1308` <dbl>, `1309` <dbl>,
## # `1310` <dbl>, `1312` <dbl>, `1313` <dbl>, `1314` <dbl>, `1315` <dbl>,
## # `1316` <dbl>, `1319` <dbl>, `1321` <dbl>, `1323` <dbl>, `1324` <dbl>, …Task: Delete stocks that contained NA values and show updated dimensions.
# Get list of stocks with NAs
stocks_with_na <- na_summary$key
# Remove these stocks
tej_clean <- tej_wide %>%
select(-all_of(stocks_with_na))
# Show dimensions
dim(tej_clean)## [1] 358 937Result: Data now has 358 rows and 937 columns (1 date column + 936 stocks).
Task: Convert to xts time series, calculate daily returns, remove first row, and show first 5 stocks with first 5 days.
# Convert to xts
tej_xts <- tej_clean %>%
tk_xts(date_var = date)
# Calculate daily returns
daily_returns <- Return.calculate(tej_xts, method = "discrete")
# Remove first row and show first 5 stocks, first 5 days
daily_returns[-1, 1:5] %>% head(5)## 1101 1102 1103 1104 1108
## 2024-01-03 -0.014408653 -0.012149290 -0.007958236 -0.006733735 -0.003160781
## 2024-01-04 0.000000000 0.012298711 0.000000000 -0.013558772 0.003170803
## 2024-01-05 0.004384536 -0.001214929 0.002674026 0.010306896 0.000000000
## 2024-01-08 -0.002909225 0.004865628 0.002666895 -0.003399291 0.006328664
## 2024-01-09 -0.005841680 -0.007263102 -0.002659801 -0.013655209 -0.025155457Task: Compute monthly returns, delete first row, and show first 5 stocks with first 5 months.
# Convert to monthly and calculate returns
monthly_prices <- to.monthly(tej_xts, OHLC = FALSE)
monthly_returns <- Return.calculate(monthly_prices, method = "discrete")
# Remove first row and show first 5 stocks, first 5 months
monthly_returns[-1, 1:5] %>% head(5)## 1101 1102 1103 1104 1108
## Feb 2024 0.006272034 0.01760804 -0.008404066 0.01887014 0.036185231
## Mar 2024 0.001554899 0.02101398 -0.016950585 0.06397241 0.003170803
## Apr 2024 -0.003108301 0.05811288 0.057470064 0.11234002 0.072790295
## May 2024 0.029639309 -0.04920108 0.032611536 -0.03271487 0.000000000
## Jun 2024 0.036364817 0.05535680 -0.036845213 0.04852830 -0.011805133Task: Find the 20 largest cap firms at year-end 2024 and 2025.
# Get top 20 firms for 2024 and 2025 year-ends
top_firms <- tej_data %>%
mutate(date = ymd(date)) %>%
filter(date %in% as.Date(c("2024-12-31", "2025-06-30"))) %>%
mutate(year1 = year(date)) %>%
group_by(year1) %>%
arrange(desc(cap)) %>%
slice(1:20) %>%
ungroup() %>%
mutate(cap1 = scales::dollar(cap, prefix = "$", big.mark = ",")) %>%
select(date, year1, cap, cap1, id, name)
top_firms## # A tibble: 40 × 6
## date year1 cap cap1 id name
## <date> <dbl> <dbl> <chr> <dbl> <chr>
## 1 2024-12-31 2024 27877688 $27,877,688 2330 TSMC
## 2 2024-12-31 2024 2556073 $2,556,073 2317 Hon Hai
## 3 2024-12-31 2024 2266389 $2,266,389 2454 MediaTek
## 4 2024-12-31 2024 1234015 $1,234,015 2881 Fubon Financial
## 5 2024-12-31 2024 1118242 $1,118,242 2308 DELTA
## 6 2024-12-31 2024 1108574 $1,108,574 2382 QCI
## 7 2024-12-31 2024 1001907 $1,001,907 2882 CATHAY FHC
## 8 2024-12-31 2024 958045 $958,045 2412 CHT
## 9 2024-12-31 2024 767154 $767,154 2891 CTBC Holding
## 10 2024-12-31 2024 715219 $715,219 3711 ASEH
## # ℹ 30 more rowsResult: TSMC (2330) leads with the largest market capitalization in both periods, followed by Hon Hai (2317) and MediaTek (2454).