perspective-python 5.6.0

Interactive data grid, pivot table and charts for large, real-time and streaming datasets, with a Jupyter widget and WebSocket server.
Documentation 
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
132
133
134
135
136
137
138
139
140
141
142
143
144
145

#  ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
#  ┃ ██████ ██████ ██████       █      █      █      █      █ █▄  ▀███ █       ┃
#  ┃ ▄▄▄▄▄█ █▄▄▄▄▄ ▄▄▄▄▄█  ▀▀▀▀▀█▀▀▀▀▀ █ ▀▀▀▀▀█ ████████▌▐███ ███▄  ▀█ █ ▀▀▀▀▀ ┃
#  ┃ █▀▀▀▀▀ █▀▀▀▀▀ █▀██▀▀ ▄▄▄▄▄ █ ▄▄▄▄▄█ ▄▄▄▄▄█ ████████▌▐███ █████▄   █ ▄▄▄▄▄ ┃
#  ┃ █      ██████ █  ▀█▄       █ ██████      █      ███▌▐███ ███████▄ █       ┃
#  ┣━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┫
#  ┃ Copyright (c) 2017, the Perspective Authors.                              ┃
#  ┃ ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌ ┃
#  ┃ This file is part of the Perspective library, distributed under the terms ┃
#  ┃ of the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). ┃
#  ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛

from perspective import Server

import pytest


def _rows(n, offset=0):
    return [
        {
            "id": i,
            "g": ["a", "b", "c"][i % 3],
            "s": ["Mon", "Tue"][(i // 3) % 2],
            "x": i * 1.5,
            "y": i % 7,
        }
        for i in range(offset, offset + n)
    ]


def _unrolled(view, group_by):
    columns = view.to_columns()
    paths = columns.pop("__ROW_PATH__", [])
    names = list(columns.keys())
    out = []
    for i, path in enumerate(paths):
        row = {
            g: (path[d] if d < len(path) else None)
            for d, g in enumerate(group_by)
        }

        row.update({n: columns[n][i] for n in names})
        out.append(row)

    return out


def _key(row):
    return sorted((k, str(v)) for k, v in row.items())


def _same(a, b):
    return sorted(map(_key, a)) == sorted(map(_key, b))


class TestDerivedTable(object):
    def _source(self):
        client = Server().new_local_client()
        table = client.table(
            {"id": "integer", "g": "string", "s": "string", "x": "float", "y": "integer"},
            index="id",
        )

        table.update(_rows(24))
        return client, table

    def test_group_by_parent_tracks_updates_and_removes(self):
        client, table = self._source()
        view = table.view(
            group_by=["g"], columns=["x", "y"], aggregates={"x": "sum", "y": "mean"}
        )

        derived = client.table(view)
        assert derived.schema() == {
            "g": "string",
            "x": "float",
            "y": "float",
        }

        child = derived.view()
        assert _same(child.to_records(), _unrolled(view, ["g"]))
        for i in range(10):
            table.update([{"id": i, "x": i * 100.0}])

        assert derived.size() == 4
        table.remove([0, 3, 6, 9, 12, 15, 18, 21])
        assert derived.size() == 3
        assert _same(child.to_records(), _unrolled(view, ["g"]))

    def test_split_by_parent(self):
        client, table = self._source()
        view = table.view(
            group_by=["g"], split_by=["s"], columns=["x"], group_rollup_mode="flat"
        )

        derived = client.table(view)
        child = derived.view()
        table.update(_rows(12, 18))
        assert _same(child.to_records(), _unrolled(view, ["g"]))

    def test_flat_parent_follows_filter(self):
        client, table = self._source()
        view = table.view(filter=[["y", ">", 3]])
        derived = client.table(view)
        assert derived.get_index() == "id"
        child = derived.view()
        assert _same(child.to_records(), view.to_records())
        table.update([{"id": 0, "y": 6}, {"id": 4, "y": 0}])
        table.remove([5])
        assert _same(child.to_records(), view.to_records())

    def test_explicit_schema(self):
        client, table = self._source()
        view = table.view(
            group_by=["g"], split_by=["s"], columns=["x"], group_rollup_mode="flat"
        )

        derived = client.table(
            view, schema={"g": "string", "Tue|x": "float", "Wed|x": "float"}
        )

        assert derived.columns() == ["g", "Tue|x", "Wed|x"]
        child = derived.view()
        assert all(v is None for v in child.to_columns()["Wed|x"])
        table.update([{"id": 100, "g": "a", "s": "Wed", "x": 7.0, "y": 1}])
        assert child.to_columns()["Wed|x"].count(7.0) == 1

    def test_read_only(self):
        client, table = self._source()
        view = table.view(group_by=["g"], columns=["x"])
        derived = client.table(view)
        with pytest.raises(Exception):
            derived.update([{"x": 1.0}])

        with pytest.raises(Exception):
            derived.clear()

    def test_index_and_limit_rejected(self):
        client, table = self._source()
        view = table.view(group_by=["g"], columns=["x"])
        with pytest.raises(Exception):
            client.table(view, index="x")

        with pytest.raises(Exception):
            client.table(view, limit=10)