ML_ECMO/data_cleaning.py
95b55da20f4bmaster

data_cleaning.py
View Options

			import process_data as prd
			import param_str as ps
			import pandas as pd
			import numpy as np
			import os, os.path

			n = 6

			path = "data_CHUV"

			# Change the time format, not really optimized, take time
			#prd.change_time_format(path, n)

			# Create file for each patient from different files
			#prd.create_file_for_each_patient_mult_files(path, n)

			DIR = path + '/data_tmp'
			nb_files = len([name for name in os.listdir(DIR) if os.path.isfile(os.path.join(DIR, name))])

			# Create file for each patient
			#prd.create_file_for_each_patient(path, n)

			# Get the time and parameter range for each patient
			#times, params = prd.get_time_param_range_all(path, nb_files)

			#np.save('times.npy', times)
			#np.save('params.npy', params)

			times = np.load('times.npy', allow_pickle=True)
			params = np.load('params.npy', allow_pickle=True)
			# Combining both functions above
			#times, params = prd.create_patient_file_and_extract_time_param(path, n)

			# Rearrange each patient's file
			prd.rearrange_files(path, times, params, ps.param_str, nb_files)

			#np.save('times.npy', times)
			#np.save('params.npy', params)

			# Interpolate missing values
			prd.interpolate_all(path, nb_files)