forked from googleapis/python-bigquery-dataframes
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathschema.py
More file actions
119 lines (96 loc) · 3.58 KB
/
schema.py
File metadata and controls
119 lines (96 loc) · 3.58 KB
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
# Copyright 2024 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import annotations
from dataclasses import dataclass
import functools
import typing
import google.cloud.bigquery
import pyarrow
import bigframes.core.guid
import bigframes.dtypes
ColumnIdentifierType = str
@dataclass(frozen=True)
class SchemaItem:
column: ColumnIdentifierType
dtype: bigframes.dtypes.Dtype
@dataclass(frozen=True)
class ArraySchema:
items: typing.Tuple[SchemaItem, ...]
@classmethod
def from_bq_table(cls, table: google.cloud.bigquery.Table):
items = tuple(
SchemaItem(name, dtype)
for name, dtype in bigframes.dtypes.bf_type_from_type_kind(
table.schema
).items()
)
return ArraySchema(items)
@property
def names(self) -> typing.Tuple[str, ...]:
return tuple(item.column for item in self.items)
@property
def dtypes(self) -> typing.Tuple[bigframes.dtypes.Dtype, ...]:
return tuple(item.dtype for item in self.items)
@functools.cached_property
def _mapping(self) -> typing.Dict[ColumnIdentifierType, bigframes.dtypes.Dtype]:
return {item.column: item.dtype for item in self.items}
def to_bigquery(self) -> typing.Tuple[google.cloud.bigquery.SchemaField, ...]:
return tuple(
bigframes.dtypes.convert_to_schema_field(item.column, item.dtype)
for item in self.items
)
def to_pyarrow(self) -> pyarrow.Schema:
fields = []
for item in self.items:
pa_type = bigframes.dtypes.bigframes_dtype_to_arrow_dtype(item.dtype)
fields.append(
pyarrow.field(
item.column,
pa_type,
nullable=not pyarrow.types.is_list(pa_type),
)
)
return pyarrow.schema(fields)
def drop(self, columns: typing.Iterable[str]) -> ArraySchema:
return ArraySchema(
tuple(item for item in self.items if item.column not in columns)
)
def select(self, columns: typing.Iterable[str]) -> ArraySchema:
return ArraySchema(
tuple(SchemaItem(name, self.get_type(name)) for name in columns)
)
def rename(self, mapping: typing.Mapping[str, str]) -> ArraySchema:
return ArraySchema(
tuple(
SchemaItem(mapping.get(item.column, item.column), item.dtype)
for item in self.items
)
)
def append(self, item: SchemaItem):
return ArraySchema(tuple([*self.items, item]))
def prepend(self, item: SchemaItem):
return ArraySchema(tuple([item, *self.items]))
def update_dtype(
self, id: ColumnIdentifierType, dtype: bigframes.dtypes.Dtype
) -> ArraySchema:
return ArraySchema(
tuple(
SchemaItem(id, dtype) if item.column == id else item
for item in self.items
)
)
def get_type(self, id: ColumnIdentifierType):
return self._mapping[id]
def __len__(self) -> int:
return len(self.items)