DSA_SS24/scripts/generate_data.py

79 lines
3.1 KiB
Python

import wfdb
import os
import pickle
import bz2
import numpy as np
import pandas as pd
# Funktionen zum Bearbeiten der Daten
def get_diagnosis_ids(record):
diagnosis = record.comments[2]
diagnosis = diagnosis.replace('Dx: ', '')
list_diagnosis = [int(x.strip()) for x in diagnosis.split(',')]
return list_diagnosis
def get_diagnosis_name(diagnosis):
name = [diagnosis_lookup[diagnosis_lookup['Snomed_CT'] == x]['Full Name'].to_string(index=False) for x in diagnosis]
return name
def filter_signal_df_on_diag(df_dict, diagnosis_dict, filter_codes_df):
filter_cod_li = list(filter_codes_df['Snomed_CT']) + [0]
filter_dict_diag = {k: v for k, v in diagnosis_dict.items() if all(i in filter_cod_li for i in v)}
filtered_df_dict = {i: df.loc[df.index.isin(filter_dict_diag.keys())] for i, df in df_dict.items()}
return filtered_df_dict
# Verzeichnisse und Dateipfade
project_dir = 'C:/Users/arman/PycharmProjects/pythonProject/DSA/a-large-scale-12-lead-electrocardiogram-database-for-arrhythmia-study-1.0.0'
data_dir = project_dir + '/WFDBRecords'
path_diag_lookup = "C:/Users/arman/PycharmProjects/pythonProject/DSA/a-large-scale-12-lead-electrocardiogram-database-for-arrhythmia-study-1.0.0/ConditionNames_SNOMED-CT.csv"
# Daten erkunden
diagnosis_lookup = pd.read_csv(path_diag_lookup)
categories = {
'SB': [426177001],
'AFIB': [164889003, 164890007],
'GSVT': [426761007, 713422000, 233896004, 233897008, 713422000],
'SR': [426783006, 427393009]
}
diag_dict = {k: [] for k in categories.keys()}
counter = 0
max_counter = 100_000
for dir_th in os.listdir(data_dir):
path_to_1000_records = data_dir + '/' + dir_th
for dir_hd in os.listdir(path_to_1000_records):
path_to_100_records = path_to_1000_records + '/' + dir_hd
for record_name in os.listdir(path_to_100_records):
if '.hea' not in record_name:
continue
record_name = record_name.replace('.hea', '')
try:
record = wfdb.rdrecord(path_to_100_records + '/' + record_name)
diagnosis = np.array(get_diagnosis_ids(record))
for category_name, category_codes in categories.items():
if any(i in category_codes for i in diagnosis):
diag_dict[category_name].append(record)
break
counter += 1
counter_bool = counter >= max_counter
if counter % 100 == 0:
print(f"Gelesen {counter} Datensätze")
if counter_bool:
break
except Exception as e:
print(f"Fehler beim Lesen des Datensatzes {record_name}: {e}")
if counter_bool:
break
if counter_bool:
break
for cat_name, records in diag_dict.items():
print(f"Schreibe {cat_name} in eine komprimierte Datei mit {len(records)} Datensätzen")
if not os.path.exists('./data'):
os.makedirs('./data')
compressed_filename = f'./data/{cat_name}.pkl.bz2'
with bz2.open(compressed_filename, 'wb') as f:
pickle.dump(records, f)