Homec4science
Diffusion DeepHealth_UC13_seizure_detection (pyeddl_0.9.0) Browse

R9868/src_pyeddl/model_basic_lopo.py
ba9c0a2dac04pyeddl_0.9.0

Last Change
Raw File

model_basic_lopo.py
View Options

#Imports
import numpy as np
import pandas as pd
# Utility file
import ModelHandler as mh
# sklearn
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split
def main(handler):
# Msc
temp_data_folder = "../temp_data/"
model_file = "../model/model.bin"
data_folder = "/shares/eslfiler1/scratch/teijeiro/chbmit_deephealth/"
signal_length = "3mn"
# processing
validation_size=0.15
test_stride = 640 #Corresponds to 50% overlap, can be set to 1280 to have no overlap
# Model
epochs = 1
batch_size = 32
learning_rate = 0.0075 # 0.00075
with open(data_folder+"signal_mit_"+signal_length+".csv", "rb") as file:
x_data_ = file.read().splitlines()
y_data = np.loadtxt(data_folder+"labels_mit_"+signal_length+".txt")
info_data = np.loadtxt(data_folder+"infos_mit_"+signal_length+".txt", dtype="str")
# Convert from string
x_data = []
for sig in x_data_:
x_data.append(np.fromstring(sig, sep=','))
# Reshape in 2D as data are 1D in csv file
x_data = [np.reshape(np.array(x_data_i), (handler.NB_CHNS, int(len(x_data_i)/handler.NB_CHNS))) for x_data_i in x_data]
# Create the pandas df
data = pd.concat([pd.Series(y_data), pd.Series([info[0] for info in info_data]),pd.Series([info[1] for info in info_data])], axis=1)
data.columns = ["label", "patient", "file"]
data["signal"] = ""
data["signal"].astype(object)
for i, sig in enumerate(x_data):
data.at[i, "signal"] = sig
patients = np.unique(data.patient)
data.sort_values(["patient", "file", "label"], inplace=True)
data = data.reset_index(drop=True)
# Load seizure times
seizures = pd.read_csv(data_folder+"seizures.csv", delimiter='\t')
seizures_ = seizures[seizures.Patient.isin(patients)]
seizures_["length"] = seizures_.apply(lambda x: (x.end_seizure - x.start_seizure), axis=1)
results = {}
for patient in patients:
print("\nPatient: ", patient)
patient_data = data[data.patient == patient]
files = np.unique(patient_data.file)
print(' ', len(files), ' files.')
test_data = patient_data
train_data = data.drop(patient_data.index)
#Build train/test set by cutting each signals in pieces of 5 seconds, with 50% overlap
x_train, y_train, x_test, y_test = handler.cut_signal_data(train_data, test_data, stride_test=test_stride)
#Shuffle and balance classes
x_train, y_train = shuffle(x_train, y_train)
x_train, x_val, y_train, y_val = train_test_split(x_train, y_train, test_size=validation_size, stratify = y_train)
x_train = np.array(x_train)
x_val = np.array(x_val)
x_train = x_train.reshape((len(x_train), handler.NB_CHNS, 1280, 1))
x_val = x_val.reshape((len(x_val), handler.NB_CHNS, 1280, 1))
y_train = np.eye(2)[np.array(y_train).astype(int)]
y_val = np.eye(2)[np.array(y_val).astype(int)]
handler.train(model_file, epochs, batch_size, learning_rate, x_train, y_train, x_val, y_val)
x_test = np.array(x_test)
x_test_splitted = np.array_split(x_test, len(files))
y_test_splitted = np.array_split(np.array(y_test), len(files))
for x_test, y_test, file in zip(x_test_splitted, y_test_splitted, files):
x_test = np.array(x_test)
x_test = x_test.reshape((len(x_test), handler.NB_CHNS, 1280, 1))
y_test = np.eye(2)[np.array(y_test).astype(int)]
handler.evaluate(model_file, x_test, y_test)
if __name__ == '__main__':
model_handler = mh.ModelHandler()
main(model_handler)
c4science · Help