#754

Committed 04 Sep 2023 09:54PM UTC coverage: 74.807% (-5.5%) from 80.336%

Build # #754

Build Type

push

circle-ci

Committed by

jiashenC

Commit Message

update case

Run Details

8727 of 11666 relevant lines covered (74.81%)

0.75 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

57.14

/evadb/executor/groupby_executor.py

# coding=utf-8
# Copyright 2018-2023 EvaDB
#
# 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.
import re
from typing import Iterator

import pandas as pd

from evadb.database import EvaDBDatabase
from evadb.executor.abstract_executor import AbstractExecutor
from evadb.models.storage.batch import Batch
from evadb.plan_nodes.groupby_plan import GroupByPlan


class GroupByExecutor(AbstractExecutor):
    """
    Group inputs into 4d segments of length provided in the query
    E.g., "GROUP BY '8 frames'" groups every 8 frames into one segment

    Arguments:
        node (AbstractPlan): The GroupBy Plan

    """

    def __init__(self, db: EvaDBDatabase, node: GroupByPlan):
        super().__init__(db, node)
        numbers_only = re.sub(r"\D", "", node.groupby_clause.value)
        self._segment_length = int(numbers_only)

    def exec(self, *args, **kwargs) -> Iterator[Batch]:
        child_executor = self.children[0]

        buffer = Batch(pd.DataFrame())
        for batch in child_executor.exec(**kwargs):
            new_batch = buffer + batch
            # We assume that all the segments exactly of segment_length size
            # and discard any dangling frames in the end.
            while len(new_batch) >= self._segment_length:
                yield new_batch[: self._segment_length]
                new_batch = new_batch[self._segment_length :]
            buffer = new_batch

1	# coding=utf-8
2	# Copyright 2018-2023 EvaDB
3	#
4	# Licensed under the Apache License, Version 2.0 (the "License");
5	# you may not use this file except in compliance with the License.
6	# You may obtain a copy of the License at
7	#
8	# http://www.apache.org/licenses/LICENSE-2.0
9	#
10	# Unless required by applicable law or agreed to in writing, software
11	# distributed under the License is distributed on an "AS IS" BASIS,
12	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13	# See the License for the specific language governing permissions and
14	# limitations under the License.
15	import re	1✔
16	from typing import Iterator	1✔
17
18	import pandas as pd	1✔
19
20	from evadb.database import EvaDBDatabase	1✔
21	from evadb.executor.abstract_executor import AbstractExecutor	1✔
22	from evadb.models.storage.batch import Batch	1✔
23	from evadb.plan_nodes.groupby_plan import GroupByPlan	1✔
24
25
26	class GroupByExecutor(AbstractExecutor):	1✔
27	"""
28	Group inputs into 4d segments of length provided in the query
29	E.g., "GROUP BY '8 frames'" groups every 8 frames into one segment
30
31	Arguments:
32	node (AbstractPlan): The GroupBy Plan
33
34	"""
35
36	def __init__(self, db: EvaDBDatabase, node: GroupByPlan):	1✔
37	super().__init__(db, node)	1✔
38	numbers_only = re.sub(r"\D", "", node.groupby_clause.value)	1✔
39	self._segment_length = int(numbers_only)	×
40
41	def exec(self, args, *kwargs) -> Iterator[Batch]:	1✔
42	child_executor = self.children[0]	×
43
44	buffer = Batch(pd.DataFrame())	×
45	for batch in child_executor.exec(**kwargs):	×
46	new_batch = buffer + batch	×
47	# We assume that all the segments exactly of segment_length size
48	# and discard any dangling frames in the end.
49	while len(new_batch) >= self._segment_length:	×
50	yield new_batch[: self._segment_length]	×
51	new_batch = new_batch[self._segment_length :]	×
52	buffer = new_batch	×

georgia-tech-db / eva / #754

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous