def main():
filenames, outdir = parse_arguments() #filenames will be a list
os.chdir(outdir) #change pwd to output directory
start_time_overall = time.time()
rt_grid_size = 50
mz_grid_size = 50
log_statement( "Number of mzml patient files: {}".format(len(filenames)) )
#build empty np array to be filled with LCMS values for R prediction
#dimension will be (# mzml files) by (# rt/mz bins + 1 for patient ID)
floatD = np.zeros((len(filenames),rt_grid_size*mz_grid_size), dtype=float) #i vals
strD = np.zeros((len(filenames),1), dtype='a6') #a6 is dtype for 6 char str
respD = np.hstack((strD, floatD))
#fill the array
for filecount, filename in enumerate(filenames):
if filecount<1000:
respD = fill_row_of_lcms_matrix(respD,
rt_grid_size, mz_grid_size, filecount, filename)
print "\n Data to use in R: " , respD[0:5,0:20]
log_statement("Time till beginning of R section: {} minutes".format(
(time.time() - start_time_overall)/60. ) )
#convert numpy array into data.frame recognized by R
Rdf = robj.r['data.frame'](numpy2ri(respD))
#use this dataframe in R prediction code
myRcode = """
doR <- function(python_respD, lcms_run) {
source("/srv/scratch/carolyn/Dengue_code/prediction_with_LCMS_from_python.R")
run_predictions_wrap(python_respD, lcms_run)
}
"""
Rpack = SignatureTranslatedAnonymousPackage(myRcode, "Rpack")
print Rpack.doR(Rdf, lcms_run=2) #to run the function doR, found in Rpack
log_statement("Total execution time: {} minutes".format(
(time.time() - start_time_overall)/60. ) ) #40 min to create binned data using pickles
