bulk_insert_test.py
1.52 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
import pandas as pd
import unittest
import sqlalchemy
import bulk_insert
import clarity_to_csv as ctc
conn = ctc.get_clarity_engine(host='claritydev.uphs.upenn.edu').connect()
#conn = ctc.get_clarity_engine(host='clarityprod.uphs.upenn.edu').connect()
#TODO - scramble this damn data so it isn't PHI
class TestStuff(unittest.TestCase):
def test_something(self):
self.assertEqual(2+1, 3)
def test_integration_1(self):
# Integration test, desired workflow as of July 2021
datadir = 'C:/Users/LynchSe/Documents/Data/Clarity_Tools_Selah/'
dfp = pd.read_csv(datadir + "test_cohort_36559.csv")
dfc = dfp[['PAT_ID', 'BIRTH_DATE', 'ENC_CNT_2017']]
tabledef = '''PAT_ID VARCHAR(18) NOT NULL, BIRTH_DATE DATETIME, ENC_CNT_2017 INTEGER
'''
import clarity_to_csv as ctc
conn = ctc.get_clarity_engine().connect()
bulk_insert.create_and_import(dfc, '##cohort_sample2', tabledef, conn)
def test_integration_2(self):
datadir = 'C:/Users/LynchSe/Documents/Data/Clarity_Tools_Selah/'
dfcohort_inp1 = pd.read_excel(datadir + 'geobirth_patient_list_2018_2021.xls')
#TODO - scramble this data so it isn't PHI
import bulk_insert
table_def = 'MRN VARCHAR(100)'
bulk_insert.create_and_import(dfcohort_inp1[['mrn']], '##cohort_inp', table_def, conn, max_insert=1000)
if __name__ == '__main__':
unittest.main()
# t = TestStuff()
# t.test_something()