dataguard/notebooks/checks.py at 83cdfb4b8314ded0b662b323174d353a289ae3fb · caiomescouto/dataguard · GitHub

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
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
import polars as pl
from dataguard import Validator, ErrorCollector


def is_between(data, arg_values=None, arg_columns=None, subject=None):
        return data.lazyframe.select(
            pl.col(data.key).is_between(arg_values[0], arg_values[1], closed='left')
        )

config_age = {
    'name': 'Age must be not null, grater than or equal to 0 and less than 150',
    'columns': [
        {
            'id': 'age',
            'data_type': 'integer',
            'nullable': False,
            'unique': False,
            'required': True,
            'checks': [
                {
                    'name': 'Tailor-made function check: is_between',
                    'error_level': 'warning',
                    'error_msg': 'Age must be between 0 (inclusive) and 150 (exclusive)',
                    'command': is_between,
                    'arg_values': [0, 150],
                },
            ],
        },
    ],
    'ids': [],
    'metadata': {},
    'checks': [],
}

df_age = pl.DataFrame({
    'age': [2, 30, None, -5, 150, 45, 50],
})

validator = Validator.config_from_mapping(config_age)

validator.validate(df_age)

ErrorCollector().get_errors()
import polars as pl
from dataguard import Validator, ErrorCollector


def is_between(data, arg_values=None, arg_columns=None, subject=None):
        return data.lazyframe.select(
            pl.col(data.key).is_between(arg_values[0], arg_values[1], closed='left')
        )

config_age = {
    'name': 'Age must be not null, grater than or equal to 0 and less than 150',
    'columns': [
        {
            'id': 'age',
            'data_type': 'integer',
            'nullable': False,
            'unique': False,
            'required': True,
            'checks': [
                {
                    'name': 'Tailor-made function check: is_between',
                    'error_level': 'warning',
                    'error_msg': 'Age must be between 0 (inclusive) and 150 (exclusive)',
                    'command': is_between,
                    'arg_values': [0, 150],
                },
            ],
        },
    ],
    'ids': [],
    'metadata': {},
    'checks': [],
}

df_age = pl.DataFrame({
    'age': [2, 30, None, -5, 150, 45, 50],
})

validator = Validator.config_from_mapping(config_age)

validator.validate(df_age)

ErrorCollector().get_errors()


ErrorCollector().clear_errors()


config_age = {
    'name': 'Age must be not null, grater than or equal to 0 and less than 150',
    'columns': [
        {
            'id': 'age',
            'data_type': 'integer',
            'nullable': False,
            'unique': False,
            'required': True,
            'checks': [
                    {
                    'check_case': 'conjunction',
                    'expressions': [
                        {
                        'command': 'is_greater_than_or_equal_to',
                        'arg_values': [0]
                        },
                        {
                        'command': 'is_less_than',
                        'arg_values': [150]
                        }
                    ]
                },
                ]
        },
    ],
    'ids': [],
    'metadata': {},
    'checks': [],
}

df_age = pl.DataFrame({
    'age': [2, 30, None, -5, 150, 45, 50],
})

validator = Validator.config_from_mapping(config_age)

validator.validate(df_age)

ErrorCollector().get_errors()