README.md

@@ -2,12 +2,8 @@
 
 This project was developed through the Data Science and Analytics course at the Mannheim University of Applied Sciences. A data science cycle was taught theoretically on the basis of lectures and implemented practically in the project. 
 
-<<<<<<< HEAD
-# Analysis of cardiovascular diseases using ECG data
-=======
 
 ## Analysis of cardiovascular diseases using ECG data
->>>>>>> bc4897dacb83ed2c3722b7b5d66b2fff23fdcb6a
 
 
 ## Table of Contents

scripts/generate_data.py

@@ -1,78 +1,105 @@
+"""
+This script reads the WFDB records and extracts the diagnosis information from the comments.
+The diagnosis information is then used to classify the records into categories.
+The categories are defined by the diagnosis codes in the comments.
+The records are then saved to pickle files based on the categories.
+"""
+
 import wfdb
 import os
-import pickle
-import bz2
 import numpy as np
-import pandas as pd
+import pickle
 
-# Funktionen zum Bearbeiten der Daten
+# Directories and file paths
+# --------------------------------------------------------------------------------
+# NOTE: Specify the directory where the WFDB records are stored
+project_dir = 'C:/Users/felix/OneDrive/Studium/Master MDS/1 Semester/DSA/physionet/large_12_ecg_data/a-large-scale-12-lead-electrocardiogram-database-for-arrhythmia-study-1.0.0'
+data_dir = project_dir + '/WFDBRecords'
+path_diag_lookup = project_dir + "/ConditionNames_SNOMED-CT.csv"
+ # --------------------------------------------------------------------------------
+# Functions
 def get_diagnosis_ids(record):
+    """
+    Extracts diagnosis IDs from a record and returns them as a list.
+    Args:
+        record (object): The record object containing the diagnosis information.
+    Returns:
+        list: A list of diagnosis IDs extracted from the record.
+    """
+    # Get the diagnosis
     diagnosis = record.comments[2]
+    # clean the diagnosis
     diagnosis = diagnosis.replace('Dx: ', '')
     list_diagnosis = [int(x.strip()) for x in diagnosis.split(',')]
     return list_diagnosis
+# --------------------------------------------------------------------------------
+# Generate the data
+# --------------------------------------------------------------------------------
+if __name__ == '__main__':
+    """
+    The following categories are used to classify the records:
 
-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,    Sinusbradykardie
+    AFIB,  Vorhofflimmern und Vorhofflattern (AFL)
+    GSVT,  supraventrikulärer Tachykardie, Vorhoftachykardie, AV-Knoten-Reentry-Tachykardie, AV-Reentry-Tachykardie, Vorhofschrittmacher
+    SR     Sinusrhythmus und Sinusunregelmäßigkeiten
+    """
+    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
+    diag_dict = {k: [] for k in categories.keys()}
 
-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)
+    # Create a counter for the number of records
+    counter = 0
+    max_counter = 100_000
+    failed_records = []
+    # Loop through the records
+    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):
+                # check if .hea is in the record_name 
+                if '.hea' not in record_name:
+                    continue
+                # Remove the .hea extension from record_name
+                record_name = record_name.replace('.hea', '')
+                try:
+                    # Read the record
+                    record = wfdb.rdrecord(path_to_100_records + '/' + record_name)
+                    # Get the diagnosis
+                    diagnosis = np.array(get_diagnosis_ids(record))
+                    # check if diagnosis is a subset of one of the categories
+                    for category_name, category_codes in categories.items():
+                        # if any of the diagnosis codes is in the category_codes
+                        if any(i in category_codes for i in diagnosis):
+                            diag_dict[category_name].append(record)
+                            break
+                    # Increment the counter of how many records we have read
+                    counter += 1
+                    counter_bool = counter >= max_counter
+                    # Break the loop if we have read max_counter records
+                    if counter % 100 == 0:
+                        print(f"Read {counter} records")
+                    if counter_bool:
                         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}")
+                except Exception as e:
+                    failed_records.append(record_name)
+                    print(f"Failed to read record {record_name} due to ValueError. Sum of failed records: {len(failed_records)}")
+            if counter_bool:
+                break
         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)
+    # write to pickle
+    for cat_name, records in diag_dict.items():
+        print(f"Writing {cat_name} to pickle with {len(records)} records")
+        # if path not exists create it
+        if not os.path.exists('./data'):
+            os.makedirs('./data')
+        with open(f'./data/{cat_name}.pkl', 'wb') as f:
+            pickle.dump(records, f)