lazytrade (version 0.5.4)

mt_evaluate: Function to score data and predict current market type using pre-trained classification model

Description

PURPOSE: Function that uses Deep Learning model and Time Series Column of the dataframe to find out specific market type of the financial asset it will also discard bad result outputting -1 if it is the case

Usage

mt_evaluate(x, path_model, num_cols, timeframe)

Value

dataframe with predicted value of the market type

Arguments

x

• dataframe with one column containing asset indicator in the time descending order, typically 64 or more values

path_model

String, path to the model

num_cols

Integer, number of columns (features) in the final vector input to the model

timeframe

Integer, timeframe in Minutes.

Details

it is mandatory to switch on the virtual h2o machine with h2o.init() also to shut it down with h2o.shutdown(prompt = F)

Examples

# \donttest{

library(h2o)
library(magrittr)
library(dplyr)
library(readr)
library(lazytrade)

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

data(macd_ML60M)

# start h2o engine (using all CPU's by default)
h2o.init(nthreads = 2)

# performing Deep Learning Regression using the custom function
# this function stores model to the temp location
mt_make_model(indicator_dataset = macd_ML60M,
              num_bars = 64,
              timeframe = 60,
              path_model = path_model,
              path_data = path_data,
              activate_balance = TRUE,
              num_nn_options = 3)


# Use sample data
data(macd_100)

# use one column for testing
x <- macd_100[ ,2]


mt_evaluate(x = x,
            path_model = path_model,
            num_cols = 64,
            timeframe = 60)

h2o.shutdown(prompt = FALSE)

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

# }