def cmdStackEvalPrepare():
print 'load train data'
trainRows = data.loadTrainJson('d/train.toks.csv')
print 'load test data'
testRows = data.loadTrainJson('d/test1.toks.csv')
print 'prepare eval'
ev = stack.StackEval('d/stack_1')
ev.prepare(trainRows, testRows)
def cmdStackEvalPrepare():
print 'load train data'
trainRows = data.loadTrainJson('d/train.toks.csv')
print 'load test data'
testRows = data.loadTrainJson('d/test1.toks.csv')
print 'prepare eval'
ev = stack.StackEval('d/stack_1')
ev.prepare(trainRows, testRows)
def cmdStackEval():
print 'load train data'
trainRows = data.loadTrainJson('d/train.toks.csv')
print 'load test data'
testRows = data.loadTrainJson('d/test1.toks.csv')
print 'eval'
ev = StackEval('d/stack_1')
auc, e = ev.eval(lambda: ensemble.ExtraTreesRegressor(n_estimators = 4000, compute_importances = True, n_jobs = -1))
print 'auc: %f' % auc
print
print 'features'
print '\n'.join(map(str, e.feature_importances_))
def cmdMakeSubmission(n_estimators, k, n, trainFile, testFile, outFile):
dt = datetime.now()
print 'load train data... ',
trainRows = data.loadTrainJson(trainFile)
print str(datetime.now() - dt)
dt = datetime.now()
print 'load test data... ',
testRows = data.loadTestJson(testFile)
print str(datetime.now() - dt)
dt = datetime.now()
print 'train model'
m = StackModel(n_estimators, k, n)
m.train(trainRows)
print 'train model, done in %s' % str(datetime.now() - dt)
m.estimator.n_jobs = 1
dt = datetime.now()
print 'generate submission'
with open(outFile, 'w') as f:
f.write('Insult,Date,Comment\n')
f.writelines(('%f,%s,%s\n' % (m.classify1(row), row.dt, row.rawText) for row in testRows))
print 'generate submission, done in %s' % str(datetime.now() - dt)
def cmdMakeSubmission(n_estimators, k, n, trainFile, testFile, outFile):
dt = datetime.now()
print 'load train data... ',
trainRows = data.loadTrainJson(trainFile)
print str(datetime.now() - dt)
dt = datetime.now()
print 'load test data... ',
testRows = data.loadTestJson(testFile)
print str(datetime.now() - dt)
dt = datetime.now()
print 'train model'
m = StackModel(n_estimators, k, n)
m.train(trainRows)
print 'train model, done in %s' % str(datetime.now() - dt)
m.estimator.n_jobs = 1
dt = datetime.now()
print 'generate submission'
with open(outFile, 'w') as f:
f.write('Insult,Date,Comment\n')
f.writelines(('%f,%s,%s\n' % (m.classify1(row), row.dt, row.rawText)
for row in testRows))
print 'generate submission, done in %s' % str(datetime.now() - dt)
def cmdStackEval():
print 'load train data'
trainRows = data.loadTrainJson('d/train.toks.csv')
print 'load test data'
testRows = data.loadTrainJson('d/test1.toks.csv')
print 'eval'
ev = StackEval('d/stack_1')
auc, e = ev.eval(lambda: ensemble.ExtraTreesRegressor(
n_estimators=4000, compute_importances=True, n_jobs=-1))
print 'auc: %f' % auc
print
print 'features'
print '\n'.join(map(str, e.feature_importances_))
def mkSub(modelF, trainFile, testFile, outFile):
printNow("make submission")
trainRows = list(loadTrainJson(trainFile))
printNow(" load train rows")
m = modelF()
m.train(trainRows)
printNow(" trained")
makeSubmission(m, testFile, outFile)
return m
def mkSub(modelF, trainFile, testFile, outFile):
printNow("make submission")
trainRows = list(loadTrainJson(trainFile))
printNow(" load train rows")
m = modelF()
m.train(trainRows)
printNow(" trained")
makeSubmission(m, testFile, outFile)
return m
