Skip to content

Commit 4da309e

Browse files
authored
docs: add snippets for performance optimization doc (#1923)
1 parent 25ab0d5 commit 4da309e

File tree

1 file changed

+52
-0
lines changed

1 file changed

+52
-0
lines changed
Lines changed: 52 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,52 @@
1+
# Copyright 2025 Google LLC
2+
#
3+
# Licensed under the Apache License, Version 2.0 (the "License");
4+
# you may not use this file except in compliance with the License.
5+
# You may obtain a copy of the License at
6+
#
7+
# http://www.apache.org/licenses/LICENSE-2.0
8+
#
9+
# Unless required by applicable law or agreed to in writing, software
10+
# distributed under the License is distributed on an "AS IS" BASIS,
11+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
# See the License for the specific language governing permissions and
13+
# limitations under the License.
14+
15+
16+
def test_performance_optimizations() -> None:
17+
# [START bigquery_bigframes_use_peek_to_preview_data]
18+
import bigframes.pandas as bpd
19+
20+
# Read the "Penguins" table into a dataframe
21+
df = bpd.read_gbq("bigquery-public-data.ml_datasets.penguins")
22+
23+
# Preview 3 random rows
24+
df.peek(3)
25+
# [END bigquery_bigframes_use_peek_to_preview_data]
26+
assert df.peek(3) is not None
27+
28+
import bigframes.pandas as bpd
29+
30+
users = bpd.DataFrame({"user_name": ["John"]})
31+
groups = bpd.DataFrame({"group_id": ["group_1"]})
32+
transactions = bpd.DataFrame({"amount": [3], "completed": [True]})
33+
34+
# [START bigquery_bigframes_use_cache_after_expensive_operations]
35+
# Assume you have 3 large dataframes "users", "group" and "transactions"
36+
37+
# Expensive join operations
38+
final_df = users.join(groups).join(transactions)
39+
final_df.cache()
40+
# Subsequent derived results will reuse the cached join
41+
print(final_df.peek())
42+
print(len(final_df[final_df["completed"]]))
43+
print(final_df.groupby("group_id")["amount"].mean().peek(30))
44+
# [END bigquery_bigframes_use_cache_after_expensive_operations]
45+
assert final_df is not None
46+
47+
# [START bigquery_bigframes_enable_deferred_repr_for_debugging]
48+
import bigframes.pandas as bpd
49+
50+
bpd.options.display.repr_mode = "deferred"
51+
# [END bigquery_bigframes_enable_deferred_repr_for_debugging]
52+
assert bpd.options.display.repr_mode == "deferred"

0 commit comments

Comments
 (0)