Zoldin

#!/usr/bin/Rscript
library(Matrix)
library(glmnet)

args = commandArgs(trailingOnly=TRUE)

if (!length(args)==3) {
  stop("Three arguments must be supplied ( file name where model is stored (RDataname), test file (.txt, matrix) and file name for AUC output).n", call.=FALSE)
} 

Zoldin

#!/usr/bin/Rscript
library(text2vec)
library(MASS)
library(Matrix)

args = commandArgs(trailingOnly=TRUE)

if (!length(args)==4) {
  stop("Four arguments must be supplied ( train file (csv format) ,test data set (csv format), train output file name and test output file name - txt files ).n", call.=FALSE)
} 

Zoldin

#!/usr/bin/Rscript
library(XML)

args = commandArgs(trailingOnly=TRUE)
if (!length(args)==2) {
  stop("Two arguments must be supplied (input file name ,output file name - csv ext).n", call.=FALSE)
} 


#read XML line by line

Zoldin

#!/usr/bin/Rscript
install.packages("XML")
install.packages("caret")
install.packages("text2vec")
install.packages("MASS")
install.packages("Matrix")
install.packages("glmnet")

Zoldin

#!/usr/bin/Rscript
library(Matrix)
library(glmnet)

    # three arguments needs to be provided - train file (.txt, matrix), seed and output name for RData file

args = commandArgs(trailingOnly=TRUE)

if (!length(args)==3) {
  stop("Three arguments must be supplied ( train file (.txt, matrix), seed and argument for RData model name).n", call.=FALSE)

Zoldin

#!/usr/bin/Rscript
library(caret)

args = commandArgs(trailingOnly=TRUE)

if (!length(args)==5) {
  stop("Five arguments must be supplied (input file name, splitting ratio related to test data set, seed, train output file name, test output file name).n", call.=FALSE)
} 

Zoldin

import numpy as np
from sklearn.ensemble import RandomForestClassifier
import sys
try: import cPickle as pickle   # python2
except: import pickle           # python3
from scipy import sparse
from numpy import loadtxt


if len(sys.argv) != 4:

Zoldin

import numpy as np
from sklearn.ensemble import RandomForestClassifier
import sys
try: import cPickle as pickle   # python2
except: import pickle           # python3
from scipy import sparse
from numpy import loadtxt
import feather as ft

if len(sys.argv) != 4:

Zoldin

from sklearn.metrics import precision_recall_curve
import sys
import sklearn.metrics as metrics
from scipy import sparse
from numpy import loadtxt
try: import cPickle as pickle   # python2
except: import pickle           # python3
import feather as ft

if len(sys.argv) != 4:

Zoldin

Let's prepare the data with Python:

```{python data_load}
import pandas as pd
data = pd.read_csv("15m.csv") 
data.rename(columns={"Unnamed: 0": "datetime"},inplace=True)
    
data.head()
```