comparison tests/test_read.py @ 0:5dba84370182

initial commit; half-working prototype
author Jeff Hammel <k0scist@gmail.com>
date Sat, 24 Jun 2017 12:03:39 -0700
parents
children 1b94f3bf97e5
comparison
equal deleted inserted replaced
-1:000000000000 0:5dba84370182
1 #!/usr/bin/env python
2
3 """
4 test data reading + loading
5 """
6
7 import os
8 import unittest
9 from globalneighbors import schema
10 from globalneighbors.read import read_tsv
11
12
13 here = os.path.dirname(os.path.abspath(__file__))
14 data = os.path.join(here, 'data')
15
16 class TestDataRead(unittest.TestCase):
17
18 # created with
19 # head -n 10 cities1000.txt > GlobalNeighbors/tests/data/sample.tsv
20 test_tsv = os.path.join(data, 'sample.tsv')
21 test_tsv_lines = 10
22
23 # full dataset: test with caution
24 full_tsv = os.path.join(data, 'cities1000.txt')
25 full_tsv_lines = 149092
26
27 def test_read_tsv(self):
28 """test reading a tsv file chunk"""
29
30 assert os.path.isfile(self.test_tsv)
31 sample = read_tsv(self.test_tsv)
32
33 assert len(sample) == 10
34 for row in sample:
35 assert len(row) == len(schema.descriptions)
36
37 def test_full_dataset(self):
38 """ensure we can operate on the full dataset"""
39
40 assert os.path.isfile(self.full_tsv)
41 cities = read_tsv(self.full_tsv)
42 assert len(cities) == self.full_tsv_lines
43 for row in cities:
44 assert len(row) == len(schema.descriptions)
45
46 # cast the data into types we want
47 for row in cities:
48 row = schema.cast_row(row, types=schema.types)
49
50
51 if __name__ == '__main__':
52 unittest.main()