Historical feature retrieval e2e test #1067
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,127 @@ | ||
| import os | ||
| import tempfile | ||
| import uuid | ||
| from datetime import datetime, timedelta | ||
| from urllib.parse import urlparse | ||
|
|
||
| import numpy as np | ||
| import pandas as pd | ||
| import pytest | ||
| from google.protobuf.duration_pb2 import Duration | ||
| from pandas._testing import assert_frame_equal | ||
|
|
||
| from feast import Client, Entity, Feature, FeatureTable, FileSource, ValueType | ||
| from feast.data_format import ParquetFormat | ||
| from feast.staging.storage_client import get_staging_client | ||
|
|
||
| np.random.seed(0) | ||
|
|
||
|
|
||
| @pytest.fixture(scope="function") | ||
| def staging_path(pytestconfig, tmp_path): | ||
| if pytestconfig.getoption("env") == "local": | ||
| return f"file://{tmp_path}" | ||
|
|
||
| staging_path = pytestconfig.getoption("staging_path") | ||
| return os.path.join(staging_path, str(uuid.uuid4())) | ||
|
|
||
|
|
||
| def test_historical_features(feast_client: Client, staging_path: str): | ||
| customer_entity = Entity( | ||
| name="customer_id", description="Customer", value_type=ValueType.INT64 | ||
| ) | ||
| feast_client.apply_entity(customer_entity) | ||
|
|
||
| max_age = Duration() | ||
| max_age.FromSeconds(2 * 86400) | ||
|
|
||
| transactions_feature_table = FeatureTable( | ||
| name="transactions", | ||
| entities=["customer_id"], | ||
| features=[ | ||
| Feature("daily_transactions", ValueType.DOUBLE), | ||
| Feature("total_transactions", ValueType.DOUBLE), | ||
| ], | ||
| batch_source=FileSource( | ||
| "event_timestamp", | ||
| "created_timestamp", | ||
| ParquetFormat(), | ||
| os.path.join(staging_path, "transactions"), | ||
| ), | ||
| max_age=max_age, | ||
| ) | ||
|
|
||
| feast_client.apply_feature_table(transactions_feature_table) | ||
|
|
||
| retrieval_date = ( | ||
| datetime.utcnow() | ||
| .replace(hour=0, minute=0, second=0, microsecond=0) | ||
| .replace(tzinfo=None) | ||
| ) | ||
| retrieval_outside_max_age_date = retrieval_date + timedelta(1) | ||
| event_date = retrieval_date - timedelta(2) | ||
| creation_date = retrieval_date - timedelta(1) | ||
|
|
||
| customers = [1001, 1002, 1003, 1004, 1005] | ||
| daily_transactions = [np.random.rand() * 10 for _ in customers] | ||
|
|
||
| total_transactions = [np.random.rand() * 100 for _ in customers] | ||
|
|
||
| transactions_df = pd.DataFrame( | ||
| { | ||
| "event_timestamp": [event_date for _ in customers], | ||
| "created_timestamp": [creation_date for _ in customers], | ||
| "customer_id": customers, | ||
| "daily_transactions": daily_transactions, | ||
| "total_transactions": total_transactions, | ||
| } | ||
| ) | ||
|
|
||
| feast_client.ingest(transactions_feature_table, transactions_df) | ||
|
|
||
| feature_refs = ["transactions:daily_transactions"] | ||
|
|
||
| customer_df = pd.DataFrame( | ||
| { | ||
| "event_timestamp": [retrieval_date for _ in customers] | ||
| + [retrieval_outside_max_age_date for _ in customers], | ||
| "customer_id": customers + customers, | ||
| } | ||
| ) | ||
|
|
||
| with tempfile.TemporaryDirectory() as tempdir: | ||
| df_export_path = os.path.join(tempdir, "customers.parquets") | ||
| customer_df.to_parquet(df_export_path) | ||
| scheme, _, remote_path, _, _, _ = urlparse(staging_path) | ||
| staging_client = get_staging_client(scheme) | ||
| staging_client.upload_file(df_export_path, None, remote_path) | ||
| customer_source = FileSource( | ||
| "event_timestamp", | ||
| "event_timestamp", | ||
| ParquetFormat(), | ||
| os.path.join(staging_path, os.path.basename(df_export_path)), | ||
| ) | ||
|
|
||
| job = feast_client.get_historical_features(feature_refs, customer_source) | ||
| output_dir = job.get_output_file_uri() | ||
|
|
||
| _, _, joined_df_destination_path, _, _, _ = urlparse(output_dir) | ||
| joined_df = pd.read_parquet(joined_df_destination_path) | ||
|
|
||
| expected_joined_df = pd.DataFrame( | ||
| { | ||
| "event_timestamp": [retrieval_date for _ in customers] | ||
|
Member
There was a problem hiding this comment. Are you at all testing the as_of join functionality? Looks like you just have one timestamp in the range? |
||
| + [retrieval_outside_max_age_date for _ in customers], | ||
| "customer_id": customers + customers, | ||
| "transactions__daily_transactions": daily_transactions | ||
| + [None] * len(customers), | ||
| } | ||
| ) | ||
|
|
||
| assert_frame_equal( | ||
| joined_df.sort_values(by=["customer_id", "event_timestamp"]).reset_index( | ||
| drop=True | ||
| ), | ||
| expected_joined_df.sort_values( | ||
| by=["customer_id", "event_timestamp"] | ||
| ).reset_index(drop=True), | ||
| ) | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think we need to change the file source to have named arguments and not positional, even if they are required. The only positional argument should be the path, and it should come first. Otherwise its hard to understand what is being defined here.