def run(ModelType, args):
print("\n********* %s %s Model *********" % (("Logistic" if ModelType == LogisticRegression else "Linear"), ("Wait" if args.time == 'w' else "Help")))
vectorizers = init_vectorizers()
trainLoader = DataLoader()
evaluateLoader = DataLoader()
testLoader = DataLoader()
# Filter out bad requests if we are running on help time
if args.time == 'h':
trainLoader.loadData('../dataset/dataset-train.npy', filterFn=lambda x: x.getHelpTimeMinutes() >= 2.0)
evaluateLoader.loadData('../dataset/dataset-dev.npy', filterFn=lambda x: x.getHelpTimeMinutes() >= 2.0)
testLoader.loadData('../dataset/dataset-test.npy', filterFn=lambda x: x.getHelpTimeMinutes() >= 2.0)
else:
trainLoader.loadData('../dataset/dataset-train.npy')
evaluateLoader.loadData('../dataset/dataset-dev.npy')
testLoader.loadData('../dataset/dataset-test.npy')
if ModelType == LogisticRegression:
buckets = make_buckets(trainLoader, args.buckets, args.time)
mapper = make_bucket_mapper(buckets)
else:
mapper = lambda x: x
labelFn = lambda x: mapper(x.getWaitTimeMinutes() if args.time == 'w' else x.getHelpTimeMinutes())
trainLabels = trainLoader.getLabels(labelFn)
trainInputs = trainLoader.applyVectorizers(vectorizers, "train", args.time)
devLabels = evaluateLoader.getLabels(labelFn)
devInputs = evaluateLoader.applyVectorizers(vectorizers, "dev", args.time)
testLabels = testLoader.getLabels(labelFn)
testInputs = evaluateLoader.applyVectorizers(vectorizers, "test", args.time)
trainedModel = trainModel(ModelType, trainInputs, trainLabels)
evaluateModel(trainedModel, devInputs, devLabels)
evaluateModel(trainedModel, testInputs, testLabels)
