def RNNMain():
# positive and negative dataset
positive = "../data/hsa_new.csv"
negative = "../data/pseudo_new.csv"
# partition the whole dataset into train(4/5) and test(1/5) datasets
x_train_dataset,y_train_dataset,x_test_dataset,y_test_dataset = \
dataSetPartition.train_test_partition(positive,negative)
# train the model
model = RNN_train(x_train_dataset,y_train_dataset)
model_path = "RNN_model.h5"
model.save(model_path)
print("The model is saved as",model_path,"in the current directory.")
# evaluate the performance
sensitivity,specifity,f1_score,mcc,accuracy =\
test_evaluation(model_path,x_test_dataset,y_test_dataset)
write_to_file(model_path,sensitivity,specifity,accuracy,f1_score,mcc)
# Partition the whole dataset into 10 segments with every one segment for test and
# and the remaining nine segments for train. All the data are stored in four list
x_train_list,y_train_list,x_validation_list,y_validation_list = \
dataSetPartition.fold10_cv_partition(positive,negative)
m = len(x_train_list)
for i in range(m):
model = RNN_train(x_train_list[i],y_train_list[i])
model_path = "RNN_model_10fold"+str(i)+".h5"
model.save(model_path)
print(model_path,"is stored in the current directory.")
# evaluate the performance
sensitivity,specifity,f1_score,mcc,accuracy =\
test_evaluation(model_path,x_validation_list[i],y_validation_list[i])
# write to file
write_to_file(model_path,sensitivity,specifity,accuracy,f1_score,mcc)
def FCNMain():
# positive and negative dataset
positive = "../data/hsa_new.csv"
negative = "../data/pseudo_new.csv"
# partition the whole dataset into train(4/5) and test(1/5) datasets
x_train_dataset,y_train_dataset,x_test_dataset,y_test_dataset = \
dataSetPartition.train_test_partition(positive,negative)
# train the model
model = FCN_train(x_train_dataset, y_train_dataset, "FCNModel")
model_path = "FCN_model.h5"
model.save(model_path)
print("The model is saved as", model_path, "in the current directory.")
# evaluate the performance
sensitivity,specifity,f1_score,mcc,accuracy =\
test_evaluation(model_path,x_test_dataset,y_test_dataset)
write_to_file(model_path, sensitivity, specifity, accuracy, f1_score, mcc)
# Partition the whole dataset into 10 segments with every one segment for test and
# and the remaining nine segments for train. All the data are stored in four list
x_train_list,y_train_list,x_validation_list,y_validation_list = \
dataSetPartition.fold5_cv_partition(positive,negative)
sen = []
spec = []
acc = []
f1 = []
mc = []
m = len(x_train_list)
for i in range(m):
name = "FCN_CV" + str(i)
model = FCN_train(x_train_list[i], y_train_list[i], name)
model_path = "FCN_model_5fold" + str(i) + ".h5"
model.save(model_path)
print(model_path, "is stored in the current directory.")
# evaluate the performance
sensitivity,specifity,f1_score,mcc,accuracy =\
test_evaluation(model_path,x_validation_list[i],y_validation_list[i])
sen.append(sensitivity)
spec.append(specifity)
acc.append(accuracy)
f1.append(f1_score)
mc.append(mcc)
# write to file
write_to_file(model_path, sensitivity, specifity, accuracy, f1_score,
mcc)
write_to_file("FCN_model_performanceAVG", avg(sen), avg(spec), avg(acc),
avg(f1), avg(mc))
def CNNMain():
# positive and negative dataset
positive = "../data/hsa_new.csv"
negative = "../data/pseudo_new.csv"
# partition the whole dataset into train(4/5) and test(1/5) datasets
x_train_dataset,y_train_dataset,x_test_dataset,y_test_dataset = \
dataSetPartition.train_test_partition(positive,negative)
# train the model
model = CNN_train(x_train_dataset, y_train_dataset)
model_path = "CNN_model_proj2_1.h5"
model.save(model_path)
print("The model is saved as", model_path, "in the current directory.")
# evaluate the performance
sensitivity,specifity,f1_score,mcc,accuracy =\
test_evaluation(model_path,x_test_dataset,y_test_dataset)
write_to_file(model_path, sensitivity, specifity, accuracy, f1_score, mcc)
def CNNMain():
# positive and negative dataset
positive = "../data/hsa_new.csv"
negative = "../data/pseudo_new.csv"
# partition the whole dataset into train(4/5) and test(1/5) datasets
x_train_dataset,y_train_dataset,x_test_dataset,y_test_dataset = \
dataSetPartition.train_test_partition(positive,negative)
# train the model
'''
ler = [0.0001,0.0002,0.0003,0.0004,0.0005,0.0006,0.0007,0.0008,0.0009,0.001]
drp = [0.35,0.40,0.45,0.50,0.55,0.60,0.65]
#ps = [2]
dns = [32,64,128]
'''
model = CNN_train(x_train_dataset, y_train_dataset)
model_path = "CNN_model.h5"
model.save(model_path)
print("The model is saved as", model_path, "in the current directory.")
# evaluate the performance
sensitivity,specifity,precision,f1_score,mcc,accuracy =\
test_evaluation(model_path,x_test_dataset,y_test_dataset)
write_to_file(model_path, sensitivity, specifity, precision, accuracy,
f1_score, mcc)
# Partition the whole dataset into 10 segments with every one segment for test and
# and the remaining nine segments for train. All the data are stored in four list
x_train_list,y_train_list,x_validation_list,y_validation_list = \
dataSetPartition.fold10_cv_partition(positive,negative)
m = len(x_train_list)
for i in range(m):
model = CNN_train(x_train_list[i], y_train_list[i])
model_path = "CNN_model_10fold" + str(i) + ".h5"
model.save(model_path)
print(model_path, "is stored in the current directory.")
# evaluate the performance
sensitivity,specifity,f1_score,mcc,accuracy =\
test_evaluation(model_path,x_validation_list[i],y_validation_list[i])
# write to file
write_to_file(model_path, sensitivity, specifity, accuracy, f1_score,
mcc)
""" Train the CNN model using dataset
"""
import sys
sys.path.append("../data")
from CNNModel import CNN_model
import dataSetPartition
import keras
import os
def CNN_train(x_dataset,y_dataset):
model = CNN_model()
if os.path.exists("CNN_model_preTrained.h5"):
print("load the weights")
model.load_weights("CNN_model_preTrained.h5")
model.fit(x_dataset,y_dataset,batch_size = 200, epochs = 600,\
validation_split = 0.2)
print("model train over")
return model
if __name__ == "__main__":
positive = "../data/hsa_new.csv"
negative = "../data/pseudo_new.csv"
x_train_dataset,y_train_dataset,x_test_dataset,y_test_dataset = \
dataSetPartition.train_test_partition(positive,negative)
model = CNN_train(x_train_dataset,y_train_dataset)
# model.save("CNN_model_preTrained.h5")
# print("The model is saved as CNN_model_preTrained.h5 in the current directory")