HK ETF 2822 Daily

# Load data from star schema
etf_daily <- open_dataset(DAILY_PARQUET_DIR)

# Filter for stock_code 2800
etf_2800_all <- etf_daily %>%
  filter(stock_code == STOCK_CODE) %>%
  collect()

if (nrow(etf_2800_all) == 0) {
  stop("No data found for stock_code ", STOCK_CODE)
}

# Ensure trade_date is Date type
etf_2800_all$trade_date <- as.Date(etf_2800_all$trade_date)

# Sort by date (most recent first)
etf_2800_all <- etf_2800_all %>%
  arrange(desc(trade_date))

# Get last 5 days and last 30 days
etf_2800_recent <- etf_2800_all %>% slice_head(n = DAYS_TO_SHOW)
etf_2800_last30 <- etf_2800_all %>% slice_head(n = 30)

# Key variables
key_vars <- c("trade_date", "volume_cleaned", "turnover_cleaned", "aum_cleaned", 
              "closing_price", "nav", "day_high", "day_low", 
              "outstanding_units_cleaned", "premium_discount_percent")

# Calculate historical statistics (needed early for comparisons)
stats <- etf_2800_all %>%
  summarise(
    volume_median = median(volume_cleaned, na.rm = TRUE),
    volume_mean = mean(volume_cleaned, na.rm = TRUE),
    volume_min = min(volume_cleaned, na.rm = TRUE),
    volume_max = max(volume_cleaned, na.rm = TRUE),
    turnover_median = median(turnover_cleaned, na.rm = TRUE),
    turnover_mean = mean(turnover_cleaned, na.rm = TRUE),
    turnover_min = min(turnover_cleaned, na.rm = TRUE),
    turnover_max = max(turnover_cleaned, na.rm = TRUE),
    total_days = n()
  )

# Prepare comparison data
comparison <- etf_2800_recent %>%
  select(trade_date, volume_cleaned, turnover_cleaned) %>%
  mutate(
    volume_vs_median = ifelse(is.na(volume_cleaned), NA, volume_cleaned / stats$volume_median),
    volume_vs_mean = ifelse(is.na(volume_cleaned), NA, volume_cleaned / stats$volume_mean),
    turnover_vs_median = ifelse(is.na(turnover_cleaned), NA, turnover_cleaned / stats$turnover_median),
    turnover_vs_mean = ifelse(is.na(turnover_cleaned), NA, turnover_cleaned / stats$turnover_mean),
    volume_pct_rank = NA_real_,
    turnover_pct_rank = NA_real_
  )

# Calculate percentile ranks
for (i in 1:nrow(comparison)) {
  if (!is.na(comparison$volume_cleaned[i])) {
    comparison$volume_pct_rank[i] <- mean(etf_2800_all$volume_cleaned <= comparison$volume_cleaned[i], na.rm = TRUE) * 100
  }
  if (!is.na(comparison$turnover_cleaned[i])) {
    comparison$turnover_pct_rank[i] <- mean(etf_2800_all$turnover_cleaned <= comparison$turnover_cleaned[i], na.rm = TRUE) * 100
  }
}

Data Overview

cat("**Stock Code:**", STOCK_CODE, "\n\n")

## **Stock Code:** 2822

cat("**Total Records:**", nrow(etf_2800_all), "\n\n")

## **Total Records:** 65

cat("**Date Range:**", format(min(etf_2800_all$trade_date)), "to", format(max(etf_2800_all$trade_date)), "\n\n")

## **Date Range:** 2025-09-17 to 2025-12-19

cat("**Last Updated:**", format(Sys.Date()))

## **Last Updated:** 2025-12-20

---

Closing Price Trend

# Prepare data for chart - order by date ascending for line chart
chart_data <- etf_2800_all %>%
  select(trade_date, closing_price) %>%
  arrange(trade_date) %>%
  mutate(
    is_latest = trade_date == max(trade_date, na.rm = TRUE)
  )

# Get latest date for labeling
latest_date <- max(chart_data$trade_date, na.rm = TRUE)
latest_price <- chart_data$closing_price[chart_data$trade_date == latest_date][1]

ggplot(chart_data, aes(x = trade_date, y = closing_price)) +
  geom_line(color = "#007bff", size = 0.8) +
  geom_point(data = chart_data %>% filter(is_latest), 
             color = "red", size = 3, shape = 19) +
  geom_point(data = chart_data %>% filter(!is_latest), 
             color = "#007bff", size = 0.5, alpha = 0.6) +
  labs(
    title = paste("Closing Price Trend - ETF", STOCK_CODE),
    subtitle = paste("Latest:", format(latest_date), "- Price:", ifelse(is.na(latest_price), "NA", formatC(latest_price, format = "f", digits = 4))),
    x = "Date",
    y = "Closing Price (HKD)",
    caption = "Red dot indicates latest data point"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(size = 14, face = "bold"),
    plot.subtitle = element_text(size = 11, color = "gray50"),
    axis.title = element_text(size = 11),
    axis.text = element_text(size = 9),
    plot.caption = element_text(size = 9, color = "gray60", hjust = 0),
    panel.grid.minor = element_blank()
  ) +
  scale_x_date(date_labels = "%Y-%m-%d", date_breaks = "1 month") +
  scale_y_continuous(labels = scales::number_format(accuracy = 0.01))

---

Latest Date Verification

latest_date <- max(etf_2800_all$trade_date)
dec_16 <- etf_2800_recent %>%
  filter(trade_date == latest_date)

if (nrow(dec_16) > 0) {
  # Create a summary table
  latest_summary <- data.frame(
    Metric = c("Date", "Volume", "Turnover", "AUM", "Closing Price", "NAV", "Suspension Flag"),
    Value = c(
      format(latest_date),
      ifelse(is.na(dec_16$volume_cleaned[1]), "NA (missing/suspended)", 
             formatC(dec_16$volume_cleaned[1], format = "d", big.mark = ",")),
      ifelse(is.na(dec_16$turnover_cleaned[1]), "NA (missing/suspended)",
             formatC(dec_16$turnover_cleaned[1], format = "f", digits = 2, big.mark = ",")),
      ifelse(is.na(dec_16$aum_cleaned[1]), "NA",
             formatC(dec_16$aum_cleaned[1], format = "f", digits = 0, big.mark = ",")),
      ifelse(is.na(dec_16$closing_price[1]), "NA",
             formatC(dec_16$closing_price[1], format = "f", digits = 4)),
      ifelse(is.na(dec_16$nav[1]), "NA",
             formatC(dec_16$nav[1], format = "f", digits = 4)),
      ifelse(is.na(dec_16$suspension_flag[1]), "NA", dec_16$suspension_flag[1])
    ),
    stringsAsFactors = FALSE
  )
  
  # Add comparison metrics if available
  if (!is.na(dec_16$volume_cleaned[1]) && !is.na(dec_16$turnover_cleaned[1])) {
    vol_idx <- which(comparison$trade_date == latest_date)
    comparison_metrics <- data.frame(
      Metric = c("Volume vs Median", "Volume vs Mean", 
                 "Turnover vs Median", "Turnover vs Mean"),
      Value = c(
        sprintf("%.2fx (%s percentile)", 
                dec_16$volume_cleaned[1] / stats$volume_median,
                sprintf("%.1f%%", comparison$volume_pct_rank[vol_idx])),
        sprintf("%.2fx", dec_16$volume_cleaned[1] / stats$volume_mean),
        sprintf("%.2fx (%s percentile)",
                dec_16$turnover_cleaned[1] / stats$turnover_median,
                sprintf("%.1f%%", comparison$turnover_pct_rank[vol_idx])),
        sprintf("%.2fx", dec_16$turnover_cleaned[1] / stats$turnover_mean)
      ),
      stringsAsFactors = FALSE
    )
    latest_summary <- rbind(latest_summary, comparison_metrics)
  }
  
  latest_summary %>%
    gt() %>%
    tab_header(
      title = "Latest Date Data Summary",
      subtitle = paste("ETF", STOCK_CODE, "-", format(latest_date))
    ) %>%
    cols_label(
      Metric = "Metric",
      Value = "Value"
    ) %>%
    tab_style(
      style = cell_text(weight = "bold"),
      locations = cells_column_labels()
    ) %>%
    tab_style(
      style = cell_text(align = "left"),
      locations = cells_body(columns = Metric)
    ) %>%
    tab_style(
      style = cell_text(align = "right"),
      locations = cells_body(columns = Value)
    ) %>%
    opt_table_font(font = "Arial") %>%
    tab_options(
      table.width = pct(60),
      column_labels.background.color = "#f8f9fa",
      table_body.hlines.color = "#e9ecef",
      heading.border.bottom.color = "#dee2e6"
    )
} else {
  cat("⚠ Warning: No data found for latest date\n")
}

Latest Date Data Summary
ETF 2822 - 2025-12-19
Metric	Value
Date	2025-12-19
Volume	979,543
Turnover	14,613,448.00
AUM	NA
Closing Price	14.9200
NAV	NA
Suspension Flag	No
Volume vs Median	0.39x (12.3% percentile)
Volume vs Mean	0.35x
Turnover vs Median	0.38x (12.3% percentile)
Turnover vs Mean	0.34x

---

Comparison: Recent vs Historical

Percentile Explanation: Percentile rank shows what percentage of historical values are less than or equal to the current value. For example, a 75th percentile means the current value is higher than 75% of all historical values (higher is better for volume/turnover). A 25th percentile means it’s higher than only 25% of historical values (lower activity).

comparison_display <- comparison %>%
  select(trade_date, volume_cleaned, volume_vs_median, volume_vs_mean, volume_pct_rank,
         turnover_cleaned, turnover_vs_median, turnover_vs_mean, turnover_pct_rank)

comparison_display %>%
  gt() %>%
  tab_header(
    title = "Recent Performance vs Historical Statistics",
    subtitle = paste("ETF", STOCK_CODE, "- Comparison of last 5 days")
  ) %>%
  fmt_date(columns = trade_date, date_style = "yMd") %>%
  fmt_number(columns = volume_cleaned, decimals = 0, use_seps = TRUE) %>%
  fmt_number(columns = volume_vs_median, decimals = 2, pattern = "{x}x") %>%
  fmt_number(columns = volume_vs_mean, decimals = 2, pattern = "{x}x") %>%
  fmt_number(columns = volume_pct_rank, decimals = 1, pattern = "{x}%") %>%
  fmt_number(columns = turnover_cleaned, decimals = 2, use_seps = TRUE) %>%
  fmt_number(columns = turnover_vs_median, decimals = 2, pattern = "{x}x") %>%
  fmt_number(columns = turnover_vs_mean, decimals = 2, pattern = "{x}x") %>%
  fmt_number(columns = turnover_pct_rank, decimals = 1, pattern = "{x}%") %>%
  sub_missing(columns = everything(), missing_text = "NA") %>%
  cols_label(
    trade_date = "Date",
    volume_cleaned = "Volume",
    volume_vs_median = "vs Median",
    volume_vs_mean = "vs Mean",
    volume_pct_rank = "Percentile",
    turnover_cleaned = "Turnover",
    turnover_vs_median = "vs Median",
    turnover_vs_mean = "vs Mean",
    turnover_pct_rank = "Percentile"
  ) %>%
  tab_spanner(
    label = "Volume",
    columns = c(volume_cleaned, volume_vs_median, volume_vs_mean, volume_pct_rank)
  ) %>%
  tab_spanner(
    label = "Turnover",
    columns = c(turnover_cleaned, turnover_vs_median, turnover_vs_mean, turnover_pct_rank)
  ) %>%
  tab_style(
    style = cell_text(weight = "bold"),
    locations = cells_column_labels()
  ) %>%
  tab_style(
    style = cell_text(align = "right"),
    locations = cells_body()
  ) %>%
  tab_style(
    style = cell_text(weight = "bold", align = "center"),
    locations = cells_column_spanners()
  ) %>%
  opt_table_font(font = "Arial") %>%
  tab_options(
    table.width = pct(100),
    column_labels.background.color = "#f8f9fa",
    table_body.hlines.color = "#e9ecef",
    heading.border.bottom.color = "#dee2e6"
  )

Recent Performance vs Historical Statistics
ETF 2822 - Comparison of last 5 days
Date	Volume				Turnover
	Volume	vs Median	vs Mean	Percentile	Turnover	vs Median	vs Mean	Percentile
12/19/2025	979,543	0.39x	0.35x	12.3%	14,613,448.00	0.38x	0.34x	12.3%
12/18/2025	7,217,503	2.85x	2.55x	100.0%	107,231,767.00	2.81x	2.51x	100.0%
12/17/2025	2,788,289	1.10x	0.98x	58.5%	42,558,792.00	1.11x	0.99x	58.5%
12/16/2025	3,876,354	1.53x	1.37x	75.4%	58,555,518.00	1.53x	1.37x	76.9%
12/15/2025	781,265	0.31x	0.28x	6.2%	11,939,860.00	0.31x	0.28x	6.2%

---

Recent 5 Days

display_data <- etf_2800_recent %>%
  select(any_of(key_vars))

display_data %>%
  gt() %>%
  tab_header(
    title = "Recent 5 Days - Key Metrics",
    subtitle = paste("ETF", STOCK_CODE)
  ) %>%
  fmt_date(columns = trade_date, date_style = "yMd") %>%
  fmt_number(columns = volume_cleaned, decimals = 0, use_seps = TRUE) %>%
  fmt_number(columns = turnover_cleaned, decimals = 2, use_seps = TRUE) %>%
  fmt_number(columns = aum_cleaned, decimals = 0, use_seps = TRUE) %>%
  fmt_number(columns = closing_price, decimals = 4) %>%
  fmt_number(columns = nav, decimals = 4) %>%
  fmt_number(columns = day_high, decimals = 4) %>%
  fmt_number(columns = day_low, decimals = 4) %>%
  fmt_number(columns = outstanding_units_cleaned, decimals = 0, use_seps = TRUE) %>%
  fmt_number(columns = premium_discount_percent, decimals = 2) %>%
  cols_label(
    trade_date = "Date",
    volume_cleaned = "Volume",
    turnover_cleaned = "Turnover",
    aum_cleaned = "AUM",
    closing_price = "Close Price",
    nav = "NAV",
    day_high = "Day High",
    day_low = "Day Low",
    outstanding_units_cleaned = "Outstanding Units",
    premium_discount_percent = "Premium/Discount %"
  ) %>%
  tab_style(
    style = cell_text(weight = "bold"),
    locations = cells_column_labels()
  ) %>%
  tab_style(
    style = cell_text(align = "right"),
    locations = cells_body()
  ) %>%
  opt_table_font(font = "Arial") %>%
  tab_options(
    table.width = pct(100),
    column_labels.background.color = "#f8f9fa",
    table_body.hlines.color = "#e9ecef",
    heading.border.bottom.color = "#dee2e6"
  )

Recent 5 Days - Key Metrics
ETF 2822
Date	Volume	Turnover	AUM	Close Price	NAV	Day High	Day Low	Outstanding Units	Premium/Discount %
12/19/2025	979,543	14,613,448.00	NA	14.9200	NA	15.0000	14.8700	549,500,000	NA
12/18/2025	7,217,503	107,231,767.00	NA	14.9100	NA	14.9200	14.7900	549,500,000	−0.02
12/17/2025	2,788,289	42,558,792.00	8,420,000,000	15.3000	15.3300	15.3600	15.0200	549,500,000	−0.17
12/16/2025	3,876,354	58,555,518.00	8,330,000,000	15.1000	15.1000	15.2400	15.0400	552,000,000	−0.02
12/15/2025	781,265	11,939,860.00	8,420,000,000	15.2300	15.2600	15.3900	15.2300	552,000,000	−0.21

---

Recent 30 Days

table_30days <- etf_2800_last30 %>%
  select(any_of(key_vars)) %>%
  arrange(desc(trade_date))

table_30days %>%
  gt() %>%
  tab_header(
    title = "Recent 30 Days - Complete Data",
    subtitle = paste("ETF", STOCK_CODE, "- Most recent dates first")
  ) %>%
  fmt_date(columns = trade_date, date_style = "yMd") %>%
  fmt_number(columns = volume_cleaned, decimals = 0, use_seps = TRUE) %>%
  fmt_number(columns = turnover_cleaned, decimals = 2, use_seps = TRUE) %>%
  fmt_number(columns = aum_cleaned, decimals = 0, use_seps = TRUE) %>%
  fmt_number(columns = closing_price, decimals = 4) %>%
  fmt_number(columns = nav, decimals = 4) %>%
  fmt_number(columns = day_high, decimals = 4) %>%
  fmt_number(columns = day_low, decimals = 4) %>%
  fmt_number(columns = outstanding_units_cleaned, decimals = 0, use_seps = TRUE) %>%
  fmt_number(columns = premium_discount_percent, decimals = 2) %>%
  sub_missing(columns = everything(), missing_text = "NA") %>%
  cols_label(
    trade_date = "Date",
    volume_cleaned = "Volume",
    turnover_cleaned = "Turnover",
    aum_cleaned = "AUM",
    closing_price = "Close Price",
    nav = "NAV",
    day_high = "Day High",
    day_low = "Day Low",
    outstanding_units_cleaned = "Outstanding Units",
    premium_discount_percent = "Premium/Discount %"
  ) %>%
  tab_style(
    style = cell_text(weight = "bold"),
    locations = cells_column_labels()
  ) %>%
  tab_style(
    style = cell_text(align = "right"),
    locations = cells_body()
  ) %>%
  opt_table_font(font = "Arial") %>%
  tab_options(
    table.width = pct(100),
    column_labels.background.color = "#f8f9fa",
    table_body.hlines.color = "#e9ecef",
    heading.border.bottom.color = "#dee2e6",
    table.font.size = px(12)
  )

Recent 30 Days - Complete Data
ETF 2822 - Most recent dates first
Date	Volume	Turnover	AUM	Close Price	NAV	Day High	Day Low	Outstanding Units	Premium/Discount %
12/19/2025	979,543	14,613,448.00	NA	14.9200	NA	15.0000	14.8700	549,500,000	NA
12/18/2025	7,217,503	107,231,767.00	NA	14.9100	NA	14.9200	14.7900	549,500,000	−0.02
12/17/2025	2,788,289	42,558,792.00	8,420,000,000	15.3000	15.3300	15.3600	15.0200	549,500,000	−0.17
12/16/2025	3,876,354	58,555,518.00	8,330,000,000	15.1000	15.1000	15.2400	15.0400	552,000,000	−0.02
12/15/2025	781,265	11,939,860.00	8,420,000,000	15.2300	15.2600	15.3900	15.2300	552,000,000	−0.21
12/12/2025	1,887,432	28,865,615.00	8,460,000,000	15.3300	15.3400	15.3500	15.1900	552,000,000	−0.09
12/11/2025	2,155,170	33,027,480.00	8,420,000,000	15.2300	15.2700	15.3600	15.2100	552,000,000	−0.24
12/10/2025	4,383,679	66,729,255.00	8,500,000,000	15.2800	15.3300	15.3500	15.1600	555,000,000	−0.33
12/9/2025	2,014,331	30,984,860.00	8,540,000,000	15.3500	15.4000	15.4300	15.3000	555,000,000	−0.34
12/8/2025	2,767,600	42,556,724.00	8,600,000,000	15.3600	15.4100	15.4800	15.3000	558,500,000	−0.33
12/5/2025	4,388,079	66,775,142.00	8,530,000,000	15.2600	15.2900	15.3200	15.1100	558,500,000	−0.19
12/4/2025	2,299,848	34,833,089.00	8,490,000,000	15.1800	15.2100	15.2000	15.0200	558,500,000	−0.17
12/3/2025	1,747,530	26,528,318.00	8,460,000,000	15.0800	15.1500	15.2700	15.0800	558,500,000	−0.45
12/2/2025	674,100	10,256,438.00	8,510,000,000	15.2200	15.2400	15.3000	15.1700	558,500,000	−0.15
12/1/2025	3,284,349	49,899,591.00	8,530,000,000	15.2300	15.2800	15.2400	15.1100	558,500,000	−0.33
11/28/2025	4,757,947	71,861,957.00	8,450,000,000	15.1000	15.1500	15.1700	15.0300	558,500,000	−0.31
11/27/2025	2,253,438	34,116,937.00	8,450,000,000	15.1100	15.1400	15.2600	15.1000	558,500,000	−0.18
11/26/2025	2,376,985	35,850,815.00	8,430,000,000	15.0600	15.1100	15.1600	14.9900	558,500,000	−0.30
11/25/2025	3,116,239	46,643,228.00	8,350,000,000	14.9800	14.9600	15.0200	14.8700	558,500,000	0.15
11/24/2025	3,927,633	58,273,532.00	8,280,000,000	14.8200	14.8300	14.9400	14.7700	558,500,000	−0.07
11/21/2025	6,652,966	99,192,747.00	8,490,000,000	14.8300	14.9000	15.1200	14.8000	570,000,000	−0.45
11/20/2025	1,882,806	28,747,366.00	8,660,000,000	15.1900	15.2000	15.3300	15.1500	570,000,000	−0.05
11/19/2025	2,700,962	41,197,573.00	8,730,000,000	15.2200	15.2700	15.3300	15.1500	572,000,000	−0.34
11/18/2025	1,507,071	22,796,422.00	8,660,000,000	15.0900	15.1400	15.2200	15.0600	572,000,000	−0.33
11/17/2025	2,431,613	36,875,015.00	8,730,000,000	15.1600	15.1900	15.2700	15.1000	575,000,000	−0.17
11/14/2025	1,392,429	21,416,504.00	8,810,000,000	15.2700	15.3300	15.5000	15.2400	575,000,000	−0.37
11/13/2025	1,529,173	23,603,372.00	8,930,000,000	15.4600	15.5300	15.5000	15.3000	575,000,000	−0.46
11/12/2025	1,225,902	18,778,376.00	8,810,000,000	15.3400	15.3400	15.3700	15.2500	575,000,000	0.02
11/11/2025	1,633,286	24,875,240.00	8,790,000,000	15.2400	15.2400	15.3500	15.1700	577,000,000	−0.01
11/10/2025	611,683	9,364,603.00	8,870,000,000	15.3600	15.3700	15.3700	15.1800	577,000,000	−0.08

---

Historical Statistics

Volume Statistics

volume_stats_df <- data.frame(
  Metric = c("Median", "Mean", "Minimum", "Maximum", "Total Days"),
  Value = c(
    stats$volume_median,
    stats$volume_mean,
    stats$volume_min,
    stats$volume_max,
    stats$total_days
  )
)

volume_stats_df %>%
  gt() %>%
  fmt_number(columns = Value, rows = 1:4, decimals = 0, use_seps = TRUE) %>%
  fmt_number(columns = Value, rows = 5, decimals = 0, use_seps = FALSE) %>%
  cols_label(
    Metric = "Metric",
    Value = "Value"
  ) %>%
  tab_style(
    style = cell_text(weight = "bold"),
    locations = cells_column_labels()
  ) %>%
  tab_style(
    style = cell_text(align = "right"),
    locations = cells_body(columns = Value)
  ) %>%
  opt_table_font(font = "Arial") %>%
  tab_options(
    table.width = pct(50),
    column_labels.background.color = "#f8f9fa",
    table_body.hlines.color = "#e9ecef"
  )

Metric	Value
Median	2,532,510
Mean	2,830,877
Minimum	611,683
Maximum	7,217,503
Total Days	65

Turnover Statistics

turnover_stats_df <- data.frame(
  Metric = c("Median", "Mean", "Minimum", "Maximum"),
  Value = c(
    stats$turnover_median,
    stats$turnover_mean,
    stats$turnover_min,
    stats$turnover_max
  )
)

turnover_stats_df %>%
  gt() %>%
  fmt_number(columns = Value, decimals = 2, use_seps = TRUE) %>%
  cols_label(
    Metric = "Metric",
    Value = "Value"
  ) %>%
  tab_style(
    style = cell_text(weight = "bold"),
    locations = cells_column_labels()
  ) %>%
  tab_style(
    style = cell_text(align = "right"),
    locations = cells_body(columns = Value)
  ) %>%
  opt_table_font(font = "Arial") %>%
  tab_options(
    table.width = pct(50),
    column_labels.background.color = "#f8f9fa",
    table_body.hlines.color = "#e9ecef"
  )

Metric	Value
Median	38,217,284.00
Mean	42,781,986.28
Minimum	9,364,603.00
Maximum	107,231,767.00

---

Report generated: 2025-12-20 08:23:36.644634