lazytrade (version 0.3.9)

aml_collect_data: Function to read new data, transform data, save data for further retraining of regression model for a single currency pair

Description

Function is collecting data from the files using dedicated function load_asset_data.R. One file with a prices of the asset and another file with the corresponding indicator pattern. Both data objects are transformed to be siutable for Regression Modelling. Indicator values will be placed into the column X1-X75 and price change is in the column 'LABEL' Result would be written to new or aggregated to the existing file

Function is also checking that generated dataset is not too big. Should the dataset is too big (e.g. > 1000000 rows), then only latest 950000 rows will be used. Note: the amount 1000000 rows is not verified in practice, further testing is required.

Usage

aml_collect_data(
  price_dataset,
  indicator_dataset,
  symbol,
  num_bars,
  timeframe,
  path_data
)

Arguments

price_dataset

Dataset containing assets prices. It will be used as a label

indicator_dataset

Dataset containing assets indicator which pattern will be used as predictor

symbol

Character symbol of the asset for which to train the model

num_bars

Number of bars used to detect pattern

timeframe

Data timeframe e.g. 1 min

path_data

Path where the aggregated historical data is stored, if exists in rds format

Value

Function is writing files into Decision Support System folder, mainly file object with the model

Details

Function is handling shift of the price and indicator datasets. New data will be always on the 'bottom' of the dataset

The amount of rows is customizable however it must be selected once for the function to start working. Other 'aml_*' functions will rely on this selections, use the same number accordingly!

Examples

# NOT RUN {
# write examples for the function
library(dplyr)
library(readr)
library(lubridate)
library(lazytrade)

path_terminal <- system.file("extdata", package = "lazytrade")
macd <- load_asset_data(path_terminal = path_terminal, trade_log_file = "AI_Macd",
                        time_period = 15, data_deepth = "300")

prices <- load_asset_data(path_terminal = path_terminal, trade_log_file = "AI_CP",
                          time_period = 15, data_deepth = "300")

path_data <- normalizePath(tempdir(),winslash = "/")


# data transformation using the custom function for one symbol
aml_collect_data(price_dataset = prices,
                 indicator_dataset = macd,
                 symbol = 'EURUSD',
                 num_bars = 75,
                 timeframe = 15,
                 path_data = path_data)




# }