CoCalc -- test_describe.py

GitHub Repository: pola-rs/polars
Path: blob/main/py-polars/tests/unit/series/test_describe.py
⁶⁹³⁹ views
1
from datetime import date
2

3
import polars as pl
4
from polars.testing.asserts.frame import assert_frame_equal
5

6

7
def test_series_describe_int() -> None:
8
    s = pl.Series([1, 2, 3])
9
    result = s.describe()
10

11
    stats = {
12
        "count": 3.0,
13
        "null_count": 0.0,
14
        "mean": 2.0,
15
        "std": 1.0,
16
        "min": 1.0,
17
        "25%": 2.0,
18
        "50%": 2.0,
19
        "75%": 3.0,
20
        "max": 3.0,
21
    }
22
    expected = pl.DataFrame({"statistic": stats.keys(), "value": stats.values()})
23
    assert_frame_equal(expected, result)
24

25

26
def test_series_describe_float() -> None:
27
    s = pl.Series([1.3, 4.6, 8.9])
28
    result = s.describe()
29

30
    stats = {
31
        "count": 3.0,
32
        "null_count": 0.0,
33
        "mean": 4.933333333333334,
34
        "std": 3.8109491381194442,
35
        "min": 1.3,
36
        "25%": 4.6,
37
        "50%": 4.6,
38
        "75%": 8.9,
39
        "max": 8.9,
40
    }
41
    expected = pl.DataFrame({"statistic": stats.keys(), "value": stats.values()})
42
    assert_frame_equal(expected, result)
43

44

45
def test_series_describe_string() -> None:
46
    s = pl.Series(["abc", "pqr", "xyz"])
47
    result = s.describe()
48

49
    stats = {
50
        "count": "3",
51
        "null_count": "0",
52
        "min": "abc",
53
        "max": "xyz",
54
    }
55
    expected = pl.DataFrame({"statistic": stats.keys(), "value": stats.values()})
56
    assert_frame_equal(expected, result)
57

58

59
def test_series_describe_boolean() -> None:
60
    s = pl.Series([True, False, None, True, True])
61
    result = s.describe()
62

63
    stats = {
64
        "count": 4,
65
        "null_count": 1,
66
        "mean": 0.75,
67
        "min": False,
68
        "max": True,
69
    }
70
    expected = pl.DataFrame(
71
        data={"statistic": stats.keys(), "value": stats.values()},
72
        schema_overrides={"value": pl.Float64},
73
    )
74
    assert_frame_equal(expected, result)
75

76

77
def test_series_describe_date() -> None:
78
    s = pl.Series([date(1999, 12, 31), date(2011, 3, 11), date(2021, 1, 18)])
79
    result = s.describe(interpolation="linear")
80

81
    stats = {
82
        "count": "3",
83
        "null_count": "0",
84
        "mean": "2010-09-29 16:00:00",
85
        "min": "1999-12-31",
86
        "25%": "2005-08-05",
87
        "50%": "2011-03-11",
88
        "75%": "2016-02-13",
89
        "max": "2021-01-18",
90
    }
91
    expected = pl.DataFrame({"statistic": stats.keys(), "value": stats.values()})
92
    assert_frame_equal(expected, result)
93

94

95
def test_series_describe_empty() -> None:
96
    s = pl.Series(dtype=pl.Float64)
97
    result = s.describe()
98
    stats = {
99
        "count": 0.0,
100
        "null_count": 0.0,
101
    }
102
    expected = pl.DataFrame({"statistic": stats.keys(), "value": stats.values()})
103
    assert_frame_equal(expected, result)
104

105

106
def test_series_describe_null() -> None:
107
    s = pl.Series([None, None], dtype=pl.Null)
108
    result = s.describe()
109
    stats = {
110
        "count": 0.0,
111
        "null_count": 2.0,
112
    }
113
    expected = pl.DataFrame({"statistic": stats.keys(), "value": stats.values()})
114
    assert_frame_equal(expected, result)
115

116

117
def test_series_describe_nested_list() -> None:
118
    s = pl.Series(
119
        values=[[10e10, 10e15], [10e12, 10e13], [10e10, 10e15]],
120
        dtype=pl.List(pl.Float64),
121
    )
122
    result = s.describe()
123
    stats = {
124
        "count": 3.0,
125
        "null_count": 0.0,
126
    }
127
    expected = pl.DataFrame({"statistic": stats.keys(), "value": stats.values()})
128
    assert_frame_equal(expected, result)
129

130
Product

Resources

Company
