aml_score_data function

Function to score new data and predict change for each single currency pair

Function is using the latest data from the financial assets indicator pattern and deep learning model. Prediction is a future price change for that asset

aml_score_data(symbol, timeframe, path_model, path_data, path_sbxm, path_sbxs)

Arguments

• symbol: Character symbol of the asset for which the model shall predict
• timeframe: Data timeframe e.g. 60 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
• path_sbxm: Path to the sandbox where file with predicted price should be written (master terminal)
• path_sbxs: Path to the sandbox where file with predicted price should be written (slave terminal)

Returns

Function is writing file into Decision Support System folder, mainly file with price change prediction in pips

Details

Performs fresh data reading from the rds file

Examples

# test of function aml_make_model is duplicated here
library(dplyr)
library(readr)
library(lubridate)
library(h2o)
library(magrittr)
library(lazytrade)

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

ind = system.file("extdata", "AI_RSIADXUSDJPY60.csv",
                  package = "lazytrade") %>% read_csv(col_names = FALSE)

ind$X1 <- ymd_hms(ind$X1)

write_csv(ind, file.path(path_data, "AI_RSIADXUSDJPY60.csv"), col_names = FALSE)

# add tick data to the folder
tick = system.file("extdata", "TickSize_AI_RSIADX.csv",
                  package = "lazytrade") %>% read_csv(col_names = FALSE)

write_csv(tick, file.path(path_data, "TickSize_AI_RSIADX.csv"), col_names = FALSE)

# data transformation using the custom function for one symbol
aml_collect_data(indicator_dataset = ind,
                 symbol = 'USDJPY',
                 timeframe = 60,
                 path_data = path_data)
# start h2o engine (using all CPU's by default)

h2o.init(nthreads = 2)

# performing Deep Learning Regression using the custom function
aml_make_model(symbol = 'USDJPY',
               timeframe = 60,
               path_model = path_model,
               path_data = path_data,
               force_update=FALSE,
               num_nn_options = 2)

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 = 'USDJPY',
               timeframe = 60,
               path_model = path_model,
               path_data = path_data,
               path_sbxm = path_sbxm,
               path_sbxs = path_sbxs)

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

#set delay to insure h2o unit closes properly before the next test
Sys.sleep(5)

Author(s)

(C) 2020 Vladimir Zhbanko