Practice of Financial Time Series Data

assets_tbl <- tribble(~ticker, ~asset_type,
        "ESGU", "ESG Fund",
        "SUSA", "ESG Fund - Long History",
        "IVV", "Benchmark",
        "SHY", "Risk Free")

assets_tbl

asset_prices_tbl <- assets_tbl %>%
  tq_get()

asset_prices_tbl

compare_ESG_regular <- asset_prices_tbl %>%
  filter(date >= ymd("2017-12-31")) %>%
  group_by(asset_type) %>%
  mutate(index_100 = adjusted/first(adjusted) * 100) %>%    #relative return
  ggplot(aes(x = date, y = index_100, color = fct_reorder2(.f = asset_type, 
                                                           .x = date, .y = index_100))) +
  geom_line() +
  labs(color = "")

compare_ESG_regular

compare_ESG_long_regular <- asset_prices_tbl %>%
  filter(ticker != "ESGU") %>%
  group_by(asset_type) %>%
  mutate(index_100 = adjusted/first(adjusted) * 100) %>%
  ggplot(aes(x = date, y = index_100, color = fct_reorder2(.f = asset_type, .x = date, .y = index_100))) +
  geom_line() +
  labs(color = "")

compare_ESG_long_regular

ggplotly(compare_ESG_long_regular)

asset_returns <- asset_prices_tbl %>%
  group_by(ticker, asset_type) %>%
  tq_transmute(select     = adjusted,
               mutate_fun = periodReturn,
               period = "weekly") %>%
  ungroup()

asset_returns

calculate_weekly_returns <- function(data, col_rename = NULL) {
  
  data %>%
  tq_transmute(select     = adjusted,
               mutate_fun = periodReturn,
               period = "weekly",
               col_rename = col_rename)
}

benchmark_returns <- asset_returns %>%
  filter(ticker == "IVV") %>%
  select(date, benchmark_returns = weekly.returns)

benchmark_returns

esg_asset_returns <- asset_returns %>%
  filter(str_detect(asset_type, "ESG")) %>%
  rename(asset_returns = weekly.returns) %>%
  left_join(benchmark_returns, by = "date")

esg_asset_returns

esg_asset_returns %>%
  filter(date >= ymd("2018-01-01")) %>%
  group_by(ticker, asset_type) %>%
   tq_performance(Ra = asset_returns,
                 Rb = benchmark_returns,
                 performance_fun = InformationRatio,
                 scale = 52)

esg_asset_returns %>%
  filter(date >= ymd("2018-01-01")) %>%
  group_by(ticker, asset_type) %>%
   tq_performance(Ra = asset_returns,
                 Rb = benchmark_returns,
                 performance_fun = table.CAPM,
                 scale = 52)

esg_asset_returns_capm_by_year <- esg_asset_returns %>%
  filter(date >= ymd("2018-01-01")) %>%
  mutate(year = year(date)) %>%
  group_by(ticker, asset_type, year) %>%
   tq_performance(Ra = asset_returns,
                 Rb = benchmark_returns,
                 performance_fun = table.CAPM,
                 scale = 52)

esg_asset_returns_capm_by_year

esg_asset_returns_capm_by_year %>%
  ggplot(aes(x = year, y = AnnualizedAlpha, color = fct_reorder2(.f = ticker, .x = year, .y = AnnualizedAlpha))) +
  geom_line() +
  labs(color = "") +
  geom_hline(yintercept = 0, lty = "dashed")

returns_reg <- function(data) {
  lm(benchmark_returns ~ asset_returns, data = data)
}

esg_asset_returns_nested <- esg_asset_returns %>%
  filter(date >= ymd("2018-01-01")) %>%
  group_by(ticker, asset_type) %>%
  nest() %>%
  ungroup() %>%
  mutate(regression_model = map(.x = data, .f = returns_reg)) 

esg_asset_returns_nested

esg_asset_returns_nested %>%
  mutate(tidy = map(.x = regression_model, .f = broom::tidy)) %>%
  unnest(tidy)

esg_asset_returns_nested %>%
  mutate(glance = map(.x = regression_model, .f = broom::glance)) %>%
  unnest(glance)

equities_filepath <- partial(here, "01_data")

equities_filepath() %>% list.files()

## [1] "equities_data_since_2020-2022-10-03.csv"
## [2] "equity_tickers-2022_10-03.csv"          
## [3] "etf_comparison_tbl-2022-10-03.csv"      
## [4] "etf_screener_processed-2022-10-03.csv"

etf_comparison <- equities_filepath("etf_comparison_tbl-2022-10-03.csv") %>% read_csv()

## Rows: 537 Columns: 14
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): ticker, company_name, sector, esg_uw_ow
## dbl (7): esg_etf, standard_etf, esg_tilt, esg_tilt_z_score, esg_tilt_rank, e...
## lgl (3): in_esg_only, in_standard_only, in_on_index_only
## 
## 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.

etf_comparison

equities_tickers <- equities_filepath("equity_tickers-2022_10-03.csv") %>% read_csv()

## Rows: 537 Columns: 2
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): ticker, company_name
## 
## 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.

equities_tickers

start_time <- Sys.time()

equities_data <- equities_tickers %>%
  tq_get()

end_time <- Sys.time()

equities_data

end_time - start_time

## Time difference of 3.602071 mins

MMM <- tq_get("MMM", get = "stock.prices", from = "2021-10-13", to = "2022-10-13")
BLK <- tq_get("BLK", get = "stock.prices", from = "2021-10-13", to = "2022-10-13")

MMM %>%
  ggplot(aes(x = date, y = close)) +
  geom_line() +
  labs( title = "3M Stock Price Line Chart", y = "Closing Price", x = "") +
  theme_tq()

BLK %>%
  ggplot(aes(x = date, y = close)) +
  geom_candlestick(aes(open = open, high = high, low = low, close = close),
                   colour_up = "darkgreen", color_down = "red",
                   fill_up = "darkgreen", fill_down = "red") +
  labs(title = "BlackRock Candlestick Stock Price Chart", y = "Closing Price", x = "") +
  theme_tq()

## Warning: Duplicated aesthetics after name standardisation: colour_down
## Duplicated aesthetics after name standardisation: colour_down