|
a |
|
b/generating_data.ipynb |
|
|
1 |
{ |
|
|
2 |
"cells": [ |
|
|
3 |
{ |
|
|
4 |
"cell_type": "code", |
|
|
5 |
"execution_count": null, |
|
|
6 |
"id": "04c762a0-d289-4e23-b0f3-3ea6b3aa2e32", |
|
|
7 |
"metadata": {}, |
|
|
8 |
"outputs": [], |
|
|
9 |
"source": [ |
|
|
10 |
"import pandas as pd\n", |
|
|
11 |
"import numpy as np\n", |
|
|
12 |
"\n", |
|
|
13 |
"# Patients table\n", |
|
|
14 |
"np.random.seed(0)\n", |
|
|
15 |
"num_rows = 10000\n", |
|
|
16 |
"patients = pd.DataFrame({\n", |
|
|
17 |
" 'patient_id': np.arange(1, num_rows + 1),\n", |
|
|
18 |
" 'age': np.random.randint(18, 85, num_rows),\n", |
|
|
19 |
" 'gender': np.random.choice(['Male', 'Female'], num_rows),\n", |
|
|
20 |
" 'admission_date': pd.date_range('2020-01-01', periods=num_rows),\n", |
|
|
21 |
" 'discharge_date': pd.date_range('2020-01-15', periods=num_rows)\n", |
|
|
22 |
"})\n", |
|
|
23 |
"\n", |
|
|
24 |
"# Diagnoses table\n", |
|
|
25 |
"diagnoses = pd.DataFrame({\n", |
|
|
26 |
" 'diagnosis_id': np.arange(1, num_rows + 1),\n", |
|
|
27 |
" 'patient_id': patients['patient_id'],\n", |
|
|
28 |
" 'icd_code': np.random.choice(['A00-B99', 'C00-D49', 'D50-D89', 'E00-E89', 'F00-F99'], num_rows),\n", |
|
|
29 |
" 'diagnosis_date': [pd.date_range(row['admission_date'], row['discharge_date'])[np.random.randint(0, len(pd.date_range(row['admission_date'], row['discharge_date']))) - 1] for index, row in patients.iterrows()]\n", |
|
|
30 |
"})\n", |
|
|
31 |
"\n", |
|
|
32 |
"# Medications table\n", |
|
|
33 |
"medications = pd.DataFrame({\n", |
|
|
34 |
" 'medication_id': np.arange(1, num_rows + 1),\n", |
|
|
35 |
" 'patient_id': patients['patient_id'],\n", |
|
|
36 |
" 'medication_name': np.random.choice(['Medication A', 'Medication B', 'Medication C', 'Medication D', 'Medication E'], num_rows),\n", |
|
|
37 |
" 'start_date': [pd.date_range(row['admission_date'], row['discharge_date'])[np.random.randint(0, len(pd.date_range(row['admission_date'], row['discharge_date']))) - 1] for index, row in patients.iterrows()]\n", |
|
|
38 |
"})\n", |
|
|
39 |
"\n", |
|
|
40 |
"medications = medications.merge(patients[['patient_id', 'admission_date', 'discharge_date']], on='patient_id')\n", |
|
|
41 |
"\n", |
|
|
42 |
"medications['end_date'] = [pd.date_range(row['start_date'], row['discharge_date'])[np.random.randint(0, len(pd.date_range(row['start_date'], row['discharge_date']))) - 1] if len(pd.date_range(row['start_date'], row['discharge_date'])) > 1 else row['discharge_date'] for index, row in medications.iterrows()]\n", |
|
|
43 |
"\n", |
|
|
44 |
"# Lab results table\n", |
|
|
45 |
"lab_results = pd.DataFrame({\n", |
|
|
46 |
" 'lab_result_id': np.arange(1, num_rows + 1),\n", |
|
|
47 |
" 'patient_id': patients['patient_id'],\n", |
|
|
48 |
" 'lab_test': np.random.choice(['Lab Test A', 'Lab Test B', 'Lab Test C', 'Lab Test D', 'Lab Test E'], num_rows),\n", |
|
|
49 |
" 'result_value': np.random.uniform(100, 300, num_rows),\n", |
|
|
50 |
" 'result_date': [pd.date_range(row['admission_date'], row['discharge_date'])[np.random.randint(0, len(pd.date_range(row['admission_date'], row['discharge_date']))) - 1] for index, row in patients.iterrows()]\n", |
|
|
51 |
"})\n", |
|
|
52 |
"\n", |
|
|
53 |
"# Readmission risk table\n", |
|
|
54 |
"readmission_risk = pd.DataFrame({\n", |
|
|
55 |
" 'patient_id': patients['patient_id'],\n", |
|
|
56 |
" 'readmission_risk': np.random.choice([0, 1], num_rows)\n", |
|
|
57 |
"})\n", |
|
|
58 |
"\n", |
|
|
59 |
"# Save data to CSV files\n", |
|
|
60 |
"patients.to_csv('patients2.csv', index=False)\n", |
|
|
61 |
"diagnoses.to_csv('diagnoses2.csv', index=False)\n", |
|
|
62 |
"medications.to_csv('medications2.csv', index=False)\n", |
|
|
63 |
"lab_results.to_csv('lab_results2.csv', index=False)\n", |
|
|
64 |
"readmission_risk.to_csv('readmission_risk2.csv', index=False)" |
|
|
65 |
] |
|
|
66 |
} |
|
|
67 |
], |
|
|
68 |
"metadata": { |
|
|
69 |
"kernelspec": { |
|
|
70 |
"display_name": "Python 3 (ipykernel)", |
|
|
71 |
"language": "python", |
|
|
72 |
"name": "python3" |
|
|
73 |
}, |
|
|
74 |
"language_info": { |
|
|
75 |
"codemirror_mode": { |
|
|
76 |
"name": "ipython", |
|
|
77 |
"version": 3 |
|
|
78 |
}, |
|
|
79 |
"file_extension": ".py", |
|
|
80 |
"mimetype": "text/x-python", |
|
|
81 |
"name": "python", |
|
|
82 |
"nbconvert_exporter": "python", |
|
|
83 |
"pygments_lexer": "ipython3", |
|
|
84 |
"version": "3.9.18" |
|
|
85 |
} |
|
|
86 |
}, |
|
|
87 |
"nbformat": 4, |
|
|
88 |
"nbformat_minor": 5 |
|
|
89 |
} |