aboutsummaryrefslogtreecommitdiff
path: root/tests/test_tableflow.py
blob: 0ab8e762c10a3e56c82788c749f03cdf26315a54 (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
72
73
74
75
import pytest
import qolab.tableflow as tblfl
import pandas as pd

def test_table_load_noinputs():
    assert tblfl.loadInOutTables() == (None, None)
    assert tblfl.loadInOutTables(inputFileName=None, outputFileName="non_existing_file") == (None, None)

def test_wrong_comment_in_table_file_to_load():
    with pytest.raises(Exception) as exc_info:
        # should raise ParserError
        tblfl.loadInOutTables(inputFileName='tests/tableflow_test_data/tableIn1.csv', outputFileName=None, comment='%')

def test_right_comment_in_table_file_to_load():
    tIn,tOut = tblfl.loadInOutTables(inputFileName='tests/tableflow_test_data/tableIn1.csv', outputFileName=None, comment='#')
    assert type(tIn) == pd.core.frame.DataFrame

def test_table_equality_with_no_output_file_name():
    tIn,tOut = tblfl.loadInOutTables(inputFileName='tests/tableflow_test_data/tableIn1.csv', outputFileName=None, comment='#')
    assert type(tIn) == pd.core.frame.DataFrame
    assert type(tOut) == pd.core.frame.DataFrame
    assert tIn.equals(tOut)
    col0 = tIn.keys()[0]
    vBefore = tIn.at[0, col0]
    tIn.at[0, col0] = vBefore + 1
    assert not tIn.equals(tOut)

def test_table_load_with_in_out_file_names():
    tIn,tOut = tblfl.loadInOutTables(inputFileName='tests/tableflow_test_data/tableIn1.csv', outputFileName='tests/tableflow_test_data/tableOut1nonProcessed.csv', comment='#')
    assert type(tIn) == pd.core.frame.DataFrame
    assert type(tOut) == pd.core.frame.DataFrame
    assert tIn.equals(tOut)

def test_for_existing_row():
    tbl1 = pd.DataFrame( {'a':[1,2,3], 'b':[1,4,6]})
    r = pd.Series({'a':2, 'b':4})
    assert tblfl.ilocRowOrAdd(tbl1, r) == 1

def test_for_existing_row_with_NA():
    # NA in both table and raw should return a hit
    tbl1 = pd.DataFrame( {'a':[1,2,3], 'b':[1,pd.NA,6]})
    r = pd.Series({'a':2, 'b':pd.NA})
    assert tblfl.ilocRowOrAdd(tbl1, r) == 1

    # should insert new row
    tbl1 = pd.DataFrame( {'a':[1,2,3], 'b':[1,4,6]})
    r = pd.Series({'a':2, 'b':pd.NA})
    assert tblfl.ilocRowOrAdd(tbl1, r) == 3

    # should insert new row
    tbl1 = pd.DataFrame( {'a':[1,2,3], 'b':[1,4,6]})
    r = pd.Series({'a':2, 'b':pd.NA})
    assert tblfl.ilocRowOrAdd(tbl1, r) == 3

def test_for_nonexisting_row_and_its_insertion():
    tbl1 = pd.DataFrame( {'a':[1,2,3], 'b':[1,4,6]})
    r = pd.Series({'a':2, 'b':10})
    assert len(tbl1) == 3
    assert tblfl.ilocRowOrAdd(tbl1, r) == 3
    assert len(tbl1) == 4

def test_isRedoNeeded():
    r = pd.Series({'a':2, 'b':4, 'c':pd.NA})
    assert not tblfl.isRedoNeeded(r, ['a','b'])
    assert tblfl.isRedoNeeded(r, ['c'])
    assert tblfl.isRedoNeeded(r, ['non_existing'])
    assert not tblfl.isRedoNeeded(r, ['b', 'c'])

def test_reflowTable():
    tIn,tOut = tblfl.loadInOutTables(inputFileName='tests/tableflow_test_data/tableIn1.csv', outputFileName='tests/tableflow_test_data/tableOut1pariallyProcessed.csv', comment='#')
    tOutRef = tOut.copy()
    with pytest.warns(UserWarning):
        tblfl.reflowTable(tIn,tOut)