lazytrade (version 0.3.9)

aml_test_model: Function to test the model and conditionally decide to update existing model for a single currency pair

Description

Function is designed to test the trading decision generated by the Deep learning regression model. The outcome of this function will be used to perform update of existing model with a fresh data.

Usage

aml_test_model(symbol, num_bars, timeframe, path_model, path_data)

Arguments

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_model

Path where the models are be stored

path_data

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

Value

Function is writing file into Decision Support System folder

Details

Function is reading shifted price data and corresponding indicator. Starting from the trained model function will test the trading strategy using simplified trading approach. Trading approach will entail using the last available indicator data, predict the price change for every row, shift predicted value by 75 bars as we will hold the asset for 75 bars. Account for the real price change after 75 bars by creating a cumulative sum column Verify obtained summary results on the model and obtain virtual real/simulated result is consolidated to calculate model quality. Whenever this value is less than 0 function is writing dedicated decision using simple *.csv file Such file will be used by the function aml_make_model.R to decide whether model must be updated...

Examples

# NOT RUN {
# }
# NOT RUN {
library(dplyr)
library(readr)
library(h2o)
library(lazytrade)

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

data(EURUSDM15X75)
write_rds(EURUSDM15X75, file.path(path_data, 'EURUSDM15X75.rds'))

# start h2o engine (using all CPU's by default)
h2o.init()


# performing Deep Learning Regression using the custom function
aml_make_model(symbol = 'EURUSD',
               num_bars = 75,
               timeframe = 15,
               path_model = path_model,
               path_data = path_data)

path_sbxm <- normalizePath(tempdir(),winslash = "/")
path_sbxs <- normalizePath(tempdir(),winslash = "/")

# score the latest data to generate predictions for one currency pair
aml_score_data(symbol = 'EURUSD',
               num_bars = 75,
               timeframe = 15,
               path_model = path_model,
               path_data = path_data,
               path_sbxm = path_sbxm,
               path_sbxs = path_sbxs)

# test the results of predictions
aml_test_model(symbol = 'EURUSD',
               num_bars = 75,
               timeframe = 15,
               path_model = path_model,
               path_data = path_data)

# stop h2o engine
h2o.shutdown(prompt = F)

# }
# NOT RUN {


# }