You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
privacykit/notebooks/data-preparation.ipynb

96 lines
3.1 KiB
Plaintext

6 years ago
{
"cells": [
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" skiping ...\n",
" skiping ...\n",
" skiping ...\n",
" skiping ...\n",
" skiping ...\n",
" skiping ...\n",
" skiping ...\n"
]
},
{
"data": {
"text/plain": [
"2"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\"\"\n",
" This notebook is designed to generate SQL syntax all the quasi-identifiers for the patients in the database\n",
" The resulting SQL will be run against bigquery to produce a table with every record mapping to a patient\n",
" \n",
"\"\"\"\n",
"\n",
"from risk import *\n",
"ihandle = UtilHandler(path='/home/steve/dev/google-cloud-sdk/accounts/curation-prod.json',dataset='combined20180822',key_field='person_id',key_table='person',filter=['person','observation'])\n",
"r = ihandle.migrate_tables()\n",
"len(r)\n"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"u' SELECT person.person_id , person.year_of_birth , person.month_of_birth , person.day_of_birth , person.birth_datetime , person.race_concept_id , person.ethnicity_concept_id , person.location_id , person.care_site_id , person.person_source_value , person.gender_source_value , person.gender_source_concept_id , person.race_source_value , person.ethnicity_source_value , basic_observation.sex_at_birth AS sex_at_birth1 , basic_observation.birth_date AS birth_date1 , basic_observation.race AS race1 , basic_observation.zip AS zip1 , basic_observation.city AS city1 , basic_observation.state AS state1 , basic_observation.gender AS gender1 FROM (select * from deid_image.person ) as person INNER JOIN (select * from deid_image.basic_observation ) as basic_observation ON basic_observation.person_id = person.person_id '"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ihandle = UtilHandler(path='/home/steve/dev/google-cloud-sdk/accounts/curation-test.json',dataset='deid_image',key_field='person_id',key_table='person',filter=['person','basic_observation'])\n",
"ihandle.create_table().replace('\\n',' ')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.15rc1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}