-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat: add sample donor csv repository along with tests
- Loading branch information
1 parent
790612d
commit 356bf26
Showing
2 changed files
with
104 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,46 @@ | ||
from datetime import datetime | ||
import logging | ||
import os | ||
from typing import List | ||
|
||
from model.gender import get_gender_from_abbreviation | ||
from model.sample_donor import SampleDonor | ||
from persistence.sample_donor_repository import SampleDonorRepository | ||
from util.custom_logger import setup_logger | ||
import pandas as pd | ||
|
||
setup_logger() | ||
logger = logging.getLogger() | ||
|
||
|
||
class SampleDonorCsvRepository(SampleDonorRepository): | ||
"""Class for handling sample donors stored in Csv files""" | ||
|
||
def __init__(self, records_path: str, separator: str, donor_parsing_map: dict): | ||
self._dir_path = records_path | ||
self._ids: set = set() | ||
self.separator = separator | ||
self._donor_parsing_map = donor_parsing_map | ||
logger.debug(f"Loaded the following donor parsing map {donor_parsing_map}") | ||
|
||
def get_all(self) -> List[SampleDonor]: | ||
for dir_entry in os.scandir(self._dir_path): | ||
if dir_entry.name.endswith(".csv"): | ||
yield from self.__extract_donor_from_csv_file(dir_entry) | ||
|
||
def __extract_donor_from_csv_file(self, dir_entry: os.DirEntry) -> SampleDonor: | ||
file_content = pd.read_csv(dir_entry, sep= self.separator, dtype=str) | ||
for _, row in file_content.iterrows(): | ||
try: | ||
donor = SampleDonor(row[self._donor_parsing_map.get("id")]) | ||
donor.gender = get_gender_from_abbreviation(row[self._donor_parsing_map.get("gender")]) | ||
year_of_birth = row[self._donor_parsing_map.get("birthDate")] | ||
if year_of_birth is not None: | ||
donor.date_of_birth = datetime.strptime(year_of_birth, '%Y') | ||
if donor.identifier not in self._ids: | ||
self._ids.add(donor.identifier) | ||
yield donor | ||
except TypeError as e: | ||
logger.info(e , "Skipping...") | ||
return | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,58 @@ | ||
import unittest | ||
|
||
import pytest | ||
from pyfakefs.fake_filesystem_unittest import patchfs | ||
|
||
from model.gender import Gender | ||
from model.sample_donor import SampleDonor | ||
from persistence.sample_donor_csv_repository import SampleDonorCsvRepository | ||
from util.config import PARSING_MAP_CSV | ||
|
||
|
||
class TestDonorCsvRepo(unittest.TestCase): | ||
header = "sample_ID;patient_pseudonym;sex;birth_year;date_of_diagnosis;diagnosis;donor_age;sampling_date;sampling_type;storage_temperature;available_number_of_samples \n" | ||
|
||
content = "34;1113;f;1939;2100-10-22;M329;49;2007-10-22;serum;-20;1" | ||
|
||
dir_path = "/mock_dir/" | ||
|
||
@pytest.fixture(autouse=True) | ||
def run_around_tests(self): | ||
self.donor_repository = SampleDonorCsvRepository(records_path=self.dir_path, | ||
donor_parsing_map=PARSING_MAP_CSV['donor_map'], | ||
separator=";") | ||
|
||
@patchfs | ||
def test_get_all_ok(self, fake_fs): | ||
fake_fs.create_file(self.dir_path + "mock_file.csv", contents=self.header + self.content) | ||
for donor in self.donor_repository.get_all(): | ||
self.assertIsInstance(donor, SampleDonor) | ||
self.assertEqual("1113", donor.identifier) | ||
self.assertEqual(Gender.FEMALE, donor.gender) | ||
|
||
@patchfs | ||
def test_get_all_with_one_wrongly_formatted_file(self, fake_fs): | ||
fake_fs.create_file(self.dir_path + "mock_file.csv", contents=self.header + self.content) | ||
fake_fs.create_file(self.dir_path + "mock_wrong_file.csv", contents="badly_formated_csv") | ||
for donor in self.donor_repository.get_all(): | ||
self.assertIsInstance(donor, SampleDonor) | ||
self.assertEqual("1113", donor.identifier) | ||
|
||
@patchfs | ||
def test_get_all_does_not_return_duplicate_patients(self, fake_fs): | ||
fake_fs.create_file(self.dir_path + "mock_file.csv", contents=self.header + self.content) | ||
fake_fs.create_file(self.dir_path + "mock_file_duplicate.csv", contents=self.header + self.content) | ||
counter = 0 | ||
for donor in self.donor_repository.get_all(): | ||
self.assertIsInstance(donor, SampleDonor) | ||
self.assertEqual("1113", donor.identifier) | ||
counter += 1 | ||
self.assertEqual(1, counter) | ||
|
||
@patchfs | ||
def test_get_all_with_empty_repository_throws_no_errors(self, fake_fs): | ||
fake_fs.create_dir(self.dir_path) | ||
counter = 0 | ||
for _ in self.donor_repository.get_all(): | ||
counter += 1 | ||
self.assertEqual(0, counter) |