def GenerateFinalTrainingFile(model_output):
ncols = 0
nrows = 0
final_file = ""
ngroups = len(config.LABEL_GROUPS)
###export csv
#"""
first = glob.glob(config.TEMPDATA_OUTPUT + '/*/training_data.csv')[0]
final_csv = CSVFile()
temp = CSVFile()
temp.from_file(first)
final_csv.setHeader(temp.getHeader())
#"""
###export csv---
current_file = CSVFile()
for filename in glob.glob(config.TEMPDATA_OUTPUT + '/*/training_data.csv'):
current_file.from_file(filename)
nrows += current_file.get_row_count()
ncols = len(current_file.getHeader())
for row in current_file.getRows():
#ecsv
final_csv.addRow(row)
#ecsv--
#last ngroups rows are labels, which are ints
for v in row[:-ngroups]:
floatval = "0 "
try:
floatval = "{0:.10f}".format(float(v)) + " "
except:
print("Warning: can't transform to float: ", v)
final_file += floatval
for group_label in row[-ngroups:]:
final_file += group_label + ' '
final_file += '\n'
mkdir(config.DATA_OUTPUT + '/training')
final_csv.saveAs(config.DATA_OUTPUT + "/training/final_training_data")
with open(config.DATA_OUTPUT + "/training/final_training_data.txt",
"w") as output:
output.write("0\n 0 \n {} {} {}\n".format(ncols, nrows, ngroups))
for name in utils.get_group_names(config.LABEL_GROUPS):
output.write(name + " ")
output.write(model_output + "\n")
output.write(final_file)
def GenerateFinalRegressionTrainingFile():
ncols = 0
nrows = 0
final_file = ""
###export csv
first = glob.glob(config.TEMPDATA_OUTPUT +
'/*/regression_training_data.csv')[0]
final_csv = CSVFile()
temp = CSVFile()
temp.from_file(first)
final_csv.setHeader(temp.getHeader())
###export csv---
current_file = CSVFile()
for filename in glob.glob(config.TEMPDATA_OUTPUT +
'/*/regression_training_data.csv'):
current_file.from_file(filename)
nrows += current_file.get_row_count()
ncols = len(current_file.getHeader())
for row in current_file.getRows():
#ecsv
final_csv.addRow(row)
#ecsv--
for v in row:
final_file += "{0:.10f}".format(float(v)) + " "
final_file += "\n"
final_csv.saveAs(config.DATA_OUTPUT +
"/training/final_regression_training_data")
with open(
config.DATA_OUTPUT +
"/training/final_regression_training_data.txt", "w") as output:
outputDimensions = len(config.WINDOW_VALUES)
inputDimensions = ncols - outputDimensions
output.write("0 \n 1 \n {} {} {}\n".format(inputDimensions,
outputDimensions, nrows))
output.write(final_file)