Skip to content

fix: Fix Spark template to work correctly on feast init -t spark #2393

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
feast-ci-bot merged 1 commit into from
Mar 9, 2022
Merged

fix: Fix Spark template to work correctly on feast init -t spark #2393

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
63 changes: 25 additions & 38 deletions sdk/python/feast/templates/spark/bootstrap.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,48 +1,35 @@
from datetime import datetime, timedelta
from pathlib import Path

from pyspark.sql import SparkSession

from feast.driver_test_data import (
create_customer_daily_profile_df,
create_driver_hourly_stats_df,
)

CURRENT_DIR = Path(__file__).parent
DRIVER_ENTITIES = [1001, 1002, 1003]
CUSTOMER_ENTITIES = [201, 202, 203]
START_DATE = datetime.strptime("2022-01-01", "%Y-%m-%d")
END_DATE = START_DATE + timedelta(days=7)


def bootstrap():
# Bootstrap() will automatically be called from the init_repo() during `feast init`
generate_example_data(
spark_session=SparkSession.builder.getOrCreate(), base_dir=str(CURRENT_DIR),
)

import pathlib
from datetime import datetime, timedelta

def example_data_exists(base_dir: str) -> bool:
for path in [
Path(base_dir) / "data" / "driver_hourly_stats",
Path(base_dir) / "data" / "customer_daily_profile",
]:
if not path.exists():
return False
return True
from feast.driver_test_data import (
create_customer_daily_profile_df,
create_driver_hourly_stats_df,
)

repo_path = pathlib.Path(__file__).parent.absolute()
data_path = repo_path / "data"
data_path.mkdir(exist_ok=True)

def generate_example_data(spark_session: SparkSession, base_dir: str) -> None:
spark_session.createDataFrame(
data=create_driver_hourly_stats_df(DRIVER_ENTITIES, START_DATE, END_DATE)
).write.parquet(
path=str(Path(base_dir) / "data" / "driver_hourly_stats"), mode="overwrite",
driver_entities = [1001, 1002, 1003]
end_date = datetime.now().replace(microsecond=0, second=0, minute=0)
start_date = end_date - timedelta(days=15)
driver_stats_df = create_driver_hourly_stats_df(
driver_entities, start_date, end_date
)
driver_stats_df.to_parquet(
path=str(data_path / "driver_hourly_stats.parquet"),
allow_truncated_timestamps=True,
)

spark_session.createDataFrame(
data=create_customer_daily_profile_df(CUSTOMER_ENTITIES, START_DATE, END_DATE)
).write.parquet(
path=str(Path(base_dir) / "data" / "customer_daily_profile"), mode="overwrite",
customer_entities = [201, 202, 203]
customer_profile_df = create_customer_daily_profile_df(
customer_entities, start_date, end_date
)
customer_profile_df.to_parquet(
path=str(data_path / "customer_daily_profile.parquet"),
allow_truncated_timestamps=True,
)


Expand Down
4 changes: 2 additions & 2 deletions sdk/python/feast/templates/spark/example.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,14 +24,14 @@
# Sources
driver_hourly_stats = SparkSource(
name="driver_hourly_stats",
path=f"{CURRENT_DIR}/data/driver_hourly_stats",
path=f"{CURRENT_DIR}/data/driver_hourly_stats.parquet",
file_format="parquet",
event_timestamp_column="event_timestamp",
created_timestamp_column="created",
)
customer_daily_profile = SparkSource(
name="customer_daily_profile",
path=f"{CURRENT_DIR}/data/customer_daily_profile",
path=f"{CURRENT_DIR}/data/customer_daily_profile.parquet",
file_format="parquet",
event_timestamp_column="event_timestamp",
created_timestamp_column="created",
Expand Down