import os, sys, glob, math
import utilities
from TransformFunctions import *
inFilePath = sys.argv[1]
hasHeaderRow = sys.argv[2] == "True"
transformFunction = getattr(sys.modules[__name__], sys.argv[3])
outFilePath = sys.argv[4]
data = utilities.readMatrixFromFile(inFilePath)
if hasHeaderRow:
headerRow = data.pop(0)
rowNames = [x[0] for x in data]
data = [x[1:] for x in data]
data = utilities.transposeMatrix(data)
data = [transformFunction([y for y in x]) for x in data]
data = utilities.transposeMatrix(data)
data = [[rowNames[i]] + data[i] for i in range(len(data))]
if hasHeaderRow:
data.insert(0, headerRow)
utilities.writeMatrixToFile(data, outFilePath)
import os, sys
import utilities
inFilePath = sys.argv[1]
outFilePath = sys.argv[2]
data = utilities.readMatrixFromFile(inFilePath)
if len(data[0]) == len(data[1]) - 1:
data[0].insert(0, " ")
utilities.writeMatrixToFile(utilities.transposeMatrix(data), outFilePath)
inFilePath = sys.argv[1]
classFilePath = sys.argv[2]
ignorePatientID = sys.argv[3]
includeIDs = sys.argv[4] == "True"
outFilePath = sys.argv[5]
patientClassDict = {}
for line in file(classFilePath):
if line.startswith("#"):
continue
lineItems = line.rstrip().split("\t")
patientClassDict[lineItems[0]] = lineItems[1]
if os.path.exists(inFilePath):
data = utilities.transposeMatrix(utilities.readMatrixFromFile(inFilePath))
features = data.pop(0)
features.pop(0)
else:
data = [[patientID] for patientID in patientClassDict.keys()]
features = []
outFile = open(outFilePath, "w")
outFile.write("@relation data\n\n")
if includeIDs:
outFile.write("@attribute id string\n")
for feature in features:
outFile.write("@attribute %s numeric\n" % feature.replace("'", "prime"))
import os, sys
import utilities
inFilePath = sys.argv[1]
outFilePath = sys.argv[2]
data = utilities.readMatrixFromFile(inFilePath)
if len(data) > 1 and len(data[0]) == len(data[1]) - 1:
data[0].insert(0, " ")
utilities.writeMatrixToFile(utilities.transposeMatrix(data), outFilePath)
inFilePath = sys.argv[1]
classFilePath = sys.argv[2]
ignorePatientID = sys.argv[3]
includeIDs = sys.argv[4] == "True"
outFilePath = sys.argv[5]
patientClassDict = {}
for line in file(classFilePath):
if line.startswith("#"):
continue
lineItems = line.rstrip().split("\t")
patientClassDict[lineItems[0]] = lineItems[1]
if os.path.exists(inFilePath):
data = utilities.transposeMatrix(utilities.readMatrixFromFile(inFilePath))
features = data.pop(0)
features.pop(0)
else:
data = [[patientID] for patientID in patientClassDict.keys()]
features = []
outFile = open(outFilePath, 'w')
outFile.write("@relation data\n\n")
if includeIDs:
outFile.write("@attribute id string\n")
for feature in features:
outFile.write("@attribute %s numeric\n" % feature.replace("'", "prime"))