def predict(model):
X, patientIds = loadTestData()
predictions = model.predict(X).flatten()
predictions_df = pd.DataFrame({
'Patient Id': patientIds,
'Expected': predictions
}).drop_duplicates('Patient Id')
return predictions_df
def main():
k = utils.numOfClasses
columns = int(((k * k) * (k - 1)) / 4)
ecoc_matrix = np.zeros((k, columns), dtype=float)
classifiers = []
trainset = utils.fetchData()
print("total train set data len: {}".format(str(len(trainset))))
testset = utils.loadTestData()
lambda_p = 1
epoch_number = 15
pair_index = 0
# Train All-Pair Classifiers
for i in range(utils.numOfClasses):
# add all other classes that are not the positive class
oppsiteClasses = [c for c in range(utils.numOfClasses) if c != i]
for y0, y1 in get_all_pairs(oppsiteClasses):
update_ecoc_matrix(ecoc_matrix, pair_index, i, (y0, y1))
print("working on {} vs {},{}".format(i, y0, y1))
pair_index = pair_index + 1
filtered_data = filter_data(trainset, (i, y0, y1))
print("relevant data: {}".format(str(len(filtered_data))))
binary_data = utils.transformToBinaryClasses(filtered_data,
positiveClass=i)
model = utils.SVM(utils.inputDim, utils.eta, lambda_p,
epoch_number)
model.train(binary_data)
classifiers.append(model)
print("finished with #{} model".format(pair_index))
# Evaluate Test Data by Hamming Distance
utils.evaluation(testset,
utils.HammingDistance,
ecoc_matrix,
'test.random2.ham.pred',
classifiers,
distanceMetric="Hamming")
# Evaluate Test Data by Loss Base Decoding
utils.evaluation(testset,
utils.lossBaseDecoding,
ecoc_matrix,
'test.random2.loss.pred',
classifiers,
distanceMetric="LBD")
def main():
classifiers = []
trainset = utils.fetchData()
devset = utils.loadDevData()
testset = utils.loadTestData()
# train OvA classifiers
for i in range(utils.numOfClasses):
binData = utils.transformToBinaryClasses(trainset, positiveClass=[i])
model = utils.SVM(utils.inputDim, utils.eta, 1, 50)
model.train(binData)
classifiers.append(model)
print("finished with #{} model".format(i))
# Validation - Evaluate Test Data by Hamming Distance
utils.validate(devset,
utils.HammingDistance,
ecocMat,
'test.onevall.ham.pred',
classifiers,
distanceMetric="Hamming")
# Validation - Evaluate Test Data by Loss Base Decoding
utils.validate(devset,
utils.lossBaseDecoding,
ecocMat,
'test.onevall.ham.pred',
classifiers,
distanceMetric="LBD")
# Test - Evaluate test data by Hamming Distance
utils.evaluate(testset,
utils.HammingDistance,
ecocMat,
'test.onevall.ham.pred',
classifiers,
distanceMetric="Hamming")
# Test - Evaluate test data by Loss Base Decoding
utils.evaluate(testset,
utils.lossBaseDecoding,
ecocMat,
'test.onevall.loss.pred',
classifiers,
distanceMetric="LBD")
def main():
k = utils.numOfClasses
columns = int(k * (k - 1) / 2)
ecoc_matrix = np.zeros((k, columns), dtype=int)
classifiers = []
trainset = utils.fetchData()
devset = utils.loadDevData()
print("total train set data len: {}".format(str(len(trainset))))
testset = utils.loadTestData()
lambda_p = 1
epoch_number = 20
pair_index = 0
# Train All-Pair Classifiers
for y0, y1 in get_all_pairs(utils.numOfClasses):
update_ecoc_matrix(ecoc_matrix, pair_index, y0, y1)
print("working on pair {},{}".format(y0, y1))
pair_index = pair_index + 1
filtered_data = filter_data(trainset, (y0, y1))
print("pair relevant data: {}".format(str(len(filtered_data))))
binary_data = utils.transformToBinaryClasses(filtered_data,
positiveClass=[y0])
model = utils.SVM(utils.inputDim, utils.eta, lambda_p, epoch_number)
model.train(binary_data)
classifiers.append(model)
print("finished with #{} model".format(pair_index))
print(ecoc_matrix)
# Evaluate Test Data by Hamming Distance
utils.validate(devset,
utils.HammingDistance,
ecoc_matrix,
'test.allpairs.ham.pred',
classifiers,
distanceMetric="Hamming")
# Evaluate Test Data by Loss Base Decoding
utils.validate(devset,
utils.lossBaseDecoding,
ecoc_matrix,
'test.allpairs.loss.pred',
classifiers,
distanceMetric="LBD")
# Evaluate Test Data by Hamming Distance
utils.evaluate(testset,
utils.HammingDistance,
ecoc_matrix,
'test.allpairs.ham.pred',
classifiers,
distanceMetric="Hamming")
# Evaluate Test Data by Loss Base Decoding
utils.evaluate(testset,
utils.lossBaseDecoding,
ecoc_matrix,
'test.allpairs.loss.pred',
classifiers,
distanceMetric="LBD")
def main():
train_data = loadTrainData(train_file)
test_data = loadTestData(test_file)
RNNTrain(train_data)
def main():
rows = utils.numOfClasses
columns = random.randint(4, 8)
ecoc_matrix = create_ecoc_matrix(rows, columns)
classifiers = []
trainset = utils.fetchData()
print("total train set data len: {}".format(str(len(trainset))))
devset = utils.loadDevData()
testset = utils.loadTestData()
lambda_p = 1
epoch_number = 20
print(ecoc_matrix)
print(len(devset), len(testset))
for j in range(columns):
positive = []
negetive = []
for i in range(rows):
if ecoc_matrix[i][j] == 1:
positive.append(i)
elif ecoc_matrix[i][j] == -1:
negetive.append(i)
print(j, " positive: ", positive, "negetive:", negetive)
filtered_data = filter_data(trainset, negetive + positive)
print("filtered data", len(filtered_data))
# need to change this function to support list
binary_data = utils.transformToBinaryClasses(filtered_data,
positiveClass=positive)
model = utils.SVM(utils.inputDim, utils.eta, lambda_p, epoch_number)
model.train(binary_data)
classifiers.append(model)
# Validation - Evaluate Test Data by Hamming Distance
utils.validate(devset,
utils.HammingDistance,
ecoc_matrix,
'test.random.ham.pred',
classifiers,
distanceMetric="Hamming")
# Validation - Evaluate Test Data by Loss Base Decoding
utils.validate(devset,
utils.lossBaseDecoding,
ecoc_matrix,
'test.random.loss.pred',
classifiers,
distanceMetric="LBD")
# Test - Evaluate Test Data by Hamming Distance
utils.evaluate(testset,
utils.HammingDistance,
ecoc_matrix,
'test.random.ham.pred',
classifiers,
distanceMetric="Hamming")
# Test - Evaluate Test Data by Loss Base Decoding
utils.evaluate(testset,
utils.lossBaseDecoding,
ecoc_matrix,
'test.random.loss.pred',
classifiers,
distanceMetric="LBD")