aggregate_price_and_mean_windows: Get Price and historic price mean windows from price...
In benSepanski/pfselect:

Given price relatives and window sizes, returns a tibble with price windows, historic mean windows, and momentum values if desired.

aggregate_price_and_mean_windows(
  price_relative_matrix,
  decay_factor,
  price_window_size,
  historic_mean_window_size,
  initial_prices = NULL,
  include_missing = FALSE,
  .check_input = TRUE
)

`price_relative_matrix`	a matrix of price relatives, each row representing a trading period and each column an asset. A price relative is p_{t+1} / p_t, i.e. the ratio of trading price to next price. Prices change according to the price relatives after the trade, i.e. the price relatives for the trading period are not known at trading time
`decay_factor`	the decay factor for the mean (see description)
`historic_mean_window_size`	The size of the historic price mean window to include
`initial_prices`	A vector holding the initial prices of each asset i
`include_missing`	If `TRUE`, includes rows for trading periods with either missing windows or missing next values/momenta
`.check_input`	If `TRUE`, checks that input meets the given assumptions.
`momentum_window_size`	determines how momentum is computed.

A tibble (arranged by c(trading_period, asset)) subclassed to be of class @eval{AGG_WINDOW_CLASS_NAME} with columns

trading_period: The trading period during which prices change
asset: The name (or column index if no names are present) of the asset, corresponding with the column names of the argument price_relative_matrix
price: The price before the prices change at the end of the trading period
next_price: The price after the prices change at the end of the trading period
price_window: The price_window_size previous prices (including the price during the trading period) in chronological order (i.e. oldest first, newest last)
historic_price_mean: The historic price mean with decay factor decay_factor (see compute_historic_price_means) during trading (before prices changes at the end of the current trading period)
next_historic_price_mean: The historic price mean with decay factor decay_factor (see compute_historic_price_means) after trading (after prices change at the end of the current trading period)
historic_price_mean_window: The previous historic_mean_window_size many historic price means. These are not used to compute anything, but may be desired as features. They are also in chronological order, oldest -> newest.

You should not modify the values of these columns except using methods defined in this package (unless you know what you're doing... you know who you are)

benSepanski/pfselect documentation built on May 1, 2020, 1:57 p.m.