1. Objective

Collect the daily prices of all listed companies in the Taiwan stock market for the last two years, check the data quality, summarize it, and publish this report to RPubs.

The data come from one file, Taiwan_Stocks_2024_2026_FINAL.csv, which already combines the TWSE and GreTai (TPEx) markets from 2024-10-07 to 2026-10-05.

2. Settings

csv_file <- file.path("data", "Taiwan_Stocks_2024_2026_FINAL.csv")
out_dir  <- "output"    # folder for the cleaned data set

if (!file.exists(csv_file)) {
  stop("File not found: '", csv_file, "'. Put the CSV in a folder named 'data' ",
       "next to this .Rmd file.")
}
dir.create(out_dir, showWarnings = FALSE)

3. Import the CSV

Important details:

COID is read as text so stock codes keep their exact form.
Date is stored as text (2024/10/07), so it is read as text first and converted to a real date afterwards.
The first line (header) is skipped and replaced by simpler column names, because the original names contain brackets such as Open(NTD). The file has a UTF-8 BOM, which read_csv() handles automatically.

col_names <- c("coid", "name", "date", "open", "high", "low",
               "close", "volume_1000s")

raw <- read_csv(
  csv_file,
  skip = 1,
  col_names = col_names,
  col_types = cols(
    coid = col_character(), name = col_character(), date = col_character(),
    open = col_double(), high = col_double(), low = col_double(),
    close = col_double(), volume_1000s = col_double()
  )
)

nrow(raw)

## [1] 957924

4. Clean the data

Steps:

Convert date from text to Date.
Remove any duplicate coid + date rows (a safety check; the file should already be free of duplicates).
Keep only the last two years counted back from the latest date in the data.
Add a security-type flag (6-digit 91xxxx codes are Taiwan Depositary Receipts, TDRs) and an approximate daily turnover in NTD.

n_raw <- nrow(raw)
n_dup <- n_raw - nrow(distinct(raw, coid, date))

stocks <- raw %>%
  mutate(date = as.Date(date, format = "%Y/%m/%d"))

n_bad_date <- sum(is.na(stocks$date))

stocks <- stocks %>%
  filter(!is.na(date)) %>%
  distinct(coid, date, .keep_all = TRUE) %>%
  filter(date > max(date) %m-% years(2)) %>%
  mutate(
    security_type = if_else(str_detect(coid, "^91\\d{4}$"), "TDR", "Stock/other"),
    turnover_ntd  = close * volume_1000s * 1000   # approximate NTD traded
  ) %>%
  arrange(coid, date) %>%
  select(coid, name, date, open, high, low, close, volume_1000s,
         turnover_ntd, security_type)

5. Data quality checks

tibble(
  Check = c("Rows in CSV",
            "Duplicate rows removed",
            "Rows with unreadable dates",
            "Rows in final data",
            "Number of companies / securities",
            "Number of trading days",
            "First date",
            "Last date",
            "Rows with High < Low",
            "Rows with missing prices",
            "Rows with zero volume"),
  Value = c(comma(n_raw),
            comma(n_dup),
            comma(n_bad_date),
            comma(nrow(stocks)),
            comma(n_distinct(stocks$coid)),
            comma(n_distinct(stocks$date)),
            as.character(min(stocks$date)),
            as.character(max(stocks$date)),
            comma(sum(stocks$high < stocks$low, na.rm = TRUE)),
            comma(sum(!complete.cases(stocks[, c("open", "high", "low", "close")]))),
            comma(sum(stocks$volume_1000s == 0, na.rm = TRUE)))
) %>%
  kable(caption = "Summary of the final data set")

Summary of the final data set
Check	Value
Rows in CSV	957,924
Duplicate rows removed	0
Rows with unreadable dates	0
Rows in final data	957,924
Number of companies / securities	1,987
Number of trading days	485
First date	2024-10-07
Last date	2026-10-05
Rows with High < Low	0
Rows with missing prices	0
Rows with zero volume	10,442

Preview of the data (TSMC, 2330, most recent 10 days):

stocks %>%
  filter(coid == "2330") %>%
  arrange(desc(date)) %>%
  head(10) %>%
  kable(digits = 2)

coid	name	date	open	high	low	close	volume_1000s	turnover_ntd	security_type
2330	TSMC	2026-10-05	2550	2580	2545	2575	26404	67990300000	Stock/other
2330	TSMC	2026-10-02	2505	2515	2495	2500	15792	39480000000	Stock/other
2330	TSMC	2026-10-01	2490	2510	2485	2510	20666	51871660000	Stock/other
2330	TSMC	2026-09-30	2495	2510	2480	2480	34282	85019360000	Stock/other
2330	TSMC	2026-09-29	2475	2495	2475	2475	26893	66560175000	Stock/other
2330	TSMC	2026-09-24	2480	2490	2470	2475	14557	36028575000	Stock/other
2330	TSMC	2026-09-23	2475	2505	2475	2500	22817	57042500000	Stock/other
2330	TSMC	2026-09-22	2505	2510	2460	2460	22009	54142140000	Stock/other
2330	TSMC	2026-09-21	2445	2485	2445	2480	16086	39893280000	Stock/other
2330	TSMC	2026-09-18	2460	2460	2435	2460	40892	100594320000	Stock/other

6. Quick look at the data

6.1 TSMC (2330) closing price

stocks %>%
  filter(coid == "2330") %>%
  ggplot(aes(date, close)) +
  geom_line(linewidth = 0.6) +
  scale_y_continuous(labels = comma) +
  labs(title = "TSMC (2330) daily closing price",
       x = NULL, y = "Close (NTD)") +
  theme_minimal()

6.2 Top 10 securities by total traded value

top10 <- stocks %>%
  group_by(coid, name) %>%
  summarise(total_turnover_bn = sum(turnover_ntd, na.rm = TRUE) / 1e9,
            .groups = "drop") %>%
  slice_max(total_turnover_bn, n = 10) %>%
  mutate(label = paste(coid, name))

ggplot(top10, aes(reorder(label, total_turnover_bn), total_turnover_bn)) +
  geom_col() +
  coord_flip() +
  scale_y_continuous(labels = comma) +
  labs(title = "Top 10 by total traded value (last two years)",
       x = NULL, y = "Total turnover (NTD billion, approximate)") +
  theme_minimal()

6.3 Number of securities traded per month

stocks %>%
  mutate(month = floor_date(date, "month")) %>%
  group_by(month) %>%
  summarise(securities = n_distinct(coid), .groups = "drop") %>%
  ggplot(aes(month, securities)) +
  geom_col() +
  labs(title = "Distinct securities with a price record, by month",
       x = NULL, y = "Securities") +
  theme_minimal()

7. Save the cleaned data

saveRDS(stocks, file.path(out_dir, "taiwan_stocks_daily_2yr.rds"))
write_csv(stocks, file.path(out_dir, "taiwan_stocks_daily_2yr.csv.gz"))

Saved to the output/ folder:

taiwan_stocks_daily_2yr.rds (open in R with readRDS())
taiwan_stocks_daily_2yr.csv.gz (compressed CSV; open in R with read_csv())

8. Notes and limitations

Prices look dividend-adjusted. Many prices have extra decimals (e.g. 31.4261), so they will not match the raw exchange quotes exactly. Use them for return and trend analysis.
ETFs are not in this file. For example 0050 does not appear, so the data cover listed companies plus a small number of TDRs (flagged in security_type).
Volume is in thousands of shares. Some rows have zero volume (no trading that day).
Coverage depends on the file supplied. Companies that were delisted before the data were built may not appear.
TWSE and GreTai are combined in this file and cannot be separated.

sessionInfo()

## R version 4.6.1 (2026-06-24)
## Platform: aarch64-apple-darwin23
## Running under: macOS Sequoia 15.7.4
## 
## Matrix products: default
## BLAS:   /Library/Frameworks/R.framework/Versions/4.6/Resources/lib/libRblas.0.dylib 
## LAPACK: /Library/Frameworks/R.framework/Versions/4.6/Resources/lib/libRlapack.dylib;  LAPACK version 3.12.1
## 
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
## 
## time zone: Asia/Taipei
## tzcode source: internal
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
## [1] knitr_1.52      scales_1.4.0    ggplot2_4.0.3   lubridate_1.9.5
## [5] stringr_1.6.0   dplyr_1.2.1     readr_2.2.0    
## 
## loaded via a namespace (and not attached):
##  [1] bit_4.6.0          gtable_0.3.6       jsonlite_2.0.0     crayon_1.5.3      
##  [5] compiler_4.6.1     tidyselect_1.2.1   parallel_4.6.1     jquerylib_0.1.4   
##  [9] yaml_2.3.12        fastmap_1.2.0      R6_2.6.1           labeling_0.4.3    
## [13] generics_0.1.4     tibble_3.3.1       RColorBrewer_1.1-3 bslib_0.12.0      
## [17] pillar_1.11.1      tzdb_0.5.0         rlang_1.3.0        cachem_1.1.0      
## [21] stringi_1.8.9      xfun_0.60          S7_0.2.2           sass_0.4.10       
## [25] bit64_4.8.6        otel_0.2.0         timechange_0.4.0   cli_3.6.6         
## [29] withr_3.0.3        magrittr_2.0.5     digest_0.6.39      grid_4.6.1        
## [33] vroom_1.7.1        rstudioapi_0.19.0  hms_1.1.4          lifecycle_1.0.5   
## [37] vctrs_0.7.3        evaluate_1.0.5     glue_1.8.1         farver_2.1.2      
## [41] rmarkdown_2.32     tools_4.6.1        pkgconfig_2.0.3    htmltools_0.5.9

Taiwan Listed Companies: Daily Stock Prices (Last Two Years)

kevin andretty 115035132

2026-10-05