aboutsummaryrefslogtreecommitdiff
path: root/tests/unit/computations/test_rust_correlation.py
blob: ac27dea9ab7013b86572ca7f66965b7cf0169b42 (plain)
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
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
"""gn3.computations.rust_correlation unittests"""

import json
import os
import pytest

from gn3.computations.rust_correlation import generate_json_file
from gn3.computations.rust_correlation import generate_input_files
from gn3.computations.rust_correlation import parse_correlation_output


@pytest.mark.unit_test
def test_generate_input():
    """test generating text files"""

    test_dataset = [
        "14_at,12.1,14.1,None",
        "15_at,12.2,14.1,None",
        "17_at,12.1,14.1,11.4"

    ]

    (_tmp_dir, tmp_file) = generate_input_files(test_dataset,
                                                output_dir="/tmp")

    with open(tmp_file, "r", encoding="utf-8") as file_reader:
        test_results = [line.rstrip() for line in file_reader]

    os.remove(tmp_file)

    assert test_results == test_dataset


@pytest.mark.unit_test
def test_json_file():
    """test for generating json files """

    tmp_file = generate_json_file(tmp_dir="/tmp/correlation",
                                  tmp_file="/data.txt",
                                  method="pearson",
                                  x_vals="12.1,11.3,16.5,7.5,3.2",
                                  delimiter=",")

    with open(tmp_file, "r+", encoding="utf-8") as file_reader:
        results = json.load(file_reader)

    assert results == {
        "method": "pearson",
        "file_path": "/data.txt",
        "x_vals": "12.1,11.3,16.5,7.5,3.2",
        "file_delimiter": ","}


@pytest.mark.unit_test
def test_parse_results():
    """test for parsing file results"""

    raw_data = [
        ["63.62", "0.97", "0.00"],
        ["19", "-0.96", "0.22"],
        ["77.92", "-0.94", "0.31"],
        ["84.04", "0.94", "0.11"],
        ["23", "-0.91", "0.11"]
    ]

    expected_results = [{"trait_name": name, "corr_coeff": corr,
                         "p_val": pval} for (name, corr, pval) in raw_data]

    assert (parse_correlation_output(
        "tests/unit/computations/data/correlation/sorted_results.txt")
        == expected_results)