def saveSubmission(trainFilePath, testFilePath, submissionFilePath, trainerFunc): header, trainData = readCsvData(trainFilePath) header, testData = readCsvData(testFilePath) trainData = processData1(trainData, False) testData = processData1(testData, True) output = computePrediction(trainData, testData, trainerFunc) open_file_object = csv.writer(open(submissionFilePath, "wb")) test_file_object = csv.reader(open(testFilePath, 'rb')) #Load in the csv file test_file_object.next() i = 0 for row in test_file_object: row.insert(0,output[i].astype(np.uint8)) open_file_object.writerow(row) i += 1 #header, allData = readCsvData('../csv/train.csv') #print len(allData) #trainData, validData, testData = splitCsvData(allData) #print len(trainData) #print len(validData) #print len(testData) # #print costFunction(np.array([1,0,0,0,1,1,1,0,1]),np.array([1,1,0,1,1,0,1,1,0]))
""" Writing my first randomforest code. Author : AstroDave Date : 23rd September, 2012 please see packages.python.org/milk/randomforests.html for more """ from src.processors import processData1, processData2 from src.validations import validationLOO import utilities as ut header, trainSet = ut.readCsvData("../csv/train.csv") trainSet1 = processData1(trainSet.copy()) validationLOO(trainSet1, True) trainSet2 = processData2(trainSet.copy()) validationLOO(trainSet2, True) # if cumErr/N < 0.10: # print "writing file..." # ut.saveSubmission('../csv/train.csv', '../csv/test.csv', '../csv/submission.csv', trainerFunc)