fix: Retire the datetime.utcnow(). (#4352)

* fix: Retire the datetime.utcnow(). Signed-off-by: Shuchu Han <shuchu.han@gmail.com> * fix: Remove unnecessary unit test. Signed-off-by: Shuchu Han <shuchu.han@gmail.com> --------- Signed-off-by: Shuchu Han <shuchu.han@gmail.com>
feast-dev · Jul 16, 2024 · a8bc696 · a8bc696
1 parent ce4f09b
commit a8bc696
Show file tree

Hide file tree

Showing 6 changed files with 38 additions and 24 deletions.
diff --git a/sdk/python/feast/driver_test_data.py b/sdk/python/feast/driver_test_data.py
@@ -61,11 +61,11 @@ def create_orders_df(
     df["order_is_success"] = np.random.randint(0, 2, size=order_count).astype(np.int32)
     df[DEFAULT_ENTITY_DF_EVENT_TIMESTAMP_COL] = [
         _convert_event_timestamp(
-            pd.Timestamp(dt, unit="ms", tz="UTC").round("ms"),
+            pd.Timestamp(dt, unit="ms").round("ms"),
             EventTimestampType(idx % 4),
         )
         for idx, dt in enumerate(
-            pd.date_range(start=start_date, end=end_date, periods=order_count)
+            pd.date_range(start=start_date, end=end_date, periods=order_count, tz="UTC")
         )
     ]
     df.sort_values(
@@ -101,9 +101,13 @@ def create_driver_hourly_stats_df(drivers, start_date, end_date) -> pd.DataFrame
     df_hourly = pd.DataFrame(
         {
             "event_timestamp": [
-                pd.Timestamp(dt, unit="ms", tz="UTC").round("ms")
+                pd.Timestamp(dt, unit="ms").round("ms")
                 for dt in pd.date_range(
-                    start=start_date, end=end_date, freq="1h", inclusive="left"
+                    start=start_date,
+                    end=end_date,
+                    freq="1h",
+                    inclusive="left",
+                    tz="UTC",
                 )
             ]
             # include a fixed timestamp for get_historical_features in the quickstart
@@ -162,9 +166,13 @@ def create_customer_daily_profile_df(customers, start_date, end_date) -> pd.Data
     df_daily = pd.DataFrame(
         {
             "event_timestamp": [
-                pd.Timestamp(dt, unit="ms", tz="UTC").round("ms")
+                pd.Timestamp(dt, unit="ms").round("ms")
                 for dt in pd.date_range(
-                    start=start_date, end=end_date, freq="1D", inclusive="left"
+                    start=start_date,
+                    end=end_date,
+                    freq="1D",
+                    inclusive="left",
+                    tz="UTC",
                 )
             ]
         }
@@ -207,9 +215,13 @@ def create_location_stats_df(locations, start_date, end_date) -> pd.DataFrame:
     df_hourly = pd.DataFrame(
         {
             "event_timestamp": [
-                pd.Timestamp(dt, unit="ms", tz="UTC").round("ms")
+                pd.Timestamp(dt, unit="ms").round("ms")
                 for dt in pd.date_range(
-                    start=start_date, end=end_date, freq="1h", inclusive="left"
+                    start=start_date,
+                    end=end_date,
+                    freq="1h",
+                    inclusive="left",
+                    tz="UTC",
                 )
             ]
         }
@@ -254,9 +266,16 @@ def create_global_daily_stats_df(start_date, end_date) -> pd.DataFrame:
     df_daily = pd.DataFrame(
         {
             "event_timestamp": [
-                pd.Timestamp(dt, unit="ms", tz="UTC").round("ms")
+                pd.Timestamp(
+                    dt,
+                    unit="ms",
+                ).round("ms")
                 for dt in pd.date_range(
-                    start=start_date, end=end_date, freq="1D", inclusive="left"
+                    start=start_date,
+                    end=end_date,
+                    freq="1D",
+                    inclusive="left",
+                    tz="UTC",
                 )
             ]
         }
@@ -286,11 +305,11 @@ def create_field_mapping_df(start_date, end_date) -> pd.DataFrame:
     df["column_name"] = np.random.randint(1, 100, size=size).astype(np.int32)
     df[DEFAULT_ENTITY_DF_EVENT_TIMESTAMP_COL] = [
         _convert_event_timestamp(
-            pd.Timestamp(dt, unit="ms", tz="UTC").round("ms"),
+            pd.Timestamp(dt, unit="ms").round("ms"),
             EventTimestampType(idx % 4),
         )
         for idx, dt in enumerate(
-            pd.date_range(start=start_date, end=end_date, periods=size)
+            pd.date_range(start=start_date, end=end_date, periods=size, tz="UTC")
         )
     ]
     df["created"] = pd.to_datetime(pd.Timestamp.now(tz=None).round("ms"))

diff --git a/sdk/python/feast/type_map.py b/sdk/python/feast/type_map.py
@@ -162,7 +162,8 @@ def python_type_to_feast_value_type(
         "timestamp": ValueType.UNIX_TIMESTAMP,
         "datetime": ValueType.UNIX_TIMESTAMP,
         "datetime64[ns]": ValueType.UNIX_TIMESTAMP,
-        "datetime64[ns, tz]": ValueType.UNIX_TIMESTAMP,
+        "datetime64[ns, tz]": ValueType.UNIX_TIMESTAMP,  # special dtype of pandas
+        "datetime64[ns, utc]": ValueType.UNIX_TIMESTAMP,
         "category": ValueType.STRING,
     }
 

diff --git a/sdk/python/feast/utils.py b/sdk/python/feast/utils.py
@@ -5,7 +5,7 @@
 import typing
 import warnings
 from collections import Counter, defaultdict
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import (
     Any,
@@ -1055,4 +1055,4 @@ def tags_str_to_dict(tags: str = "") -> dict[str, str]:
 
 
 def _utc_now() -> datetime:
-    return datetime.utcnow()
+    return datetime.now(tz=timezone.utc)
diff --git a/sdk/python/tests/unit/test_datetime.py b/sdk/python/tests/unit/test_datetime.py
diff --git a/sdk/python/tests/utils/feature_records.py b/sdk/python/tests/utils/feature_records.py
@@ -1,4 +1,4 @@
-from datetime import datetime, timedelta
+from datetime import datetime, timedelta, timezone
 from typing import Any, Dict, List, Optional
 
 import numpy as np
@@ -520,7 +520,7 @@ def get_last_feature_row(df: pd.DataFrame, driver_id, max_date: datetime):
     """Manually extract last feature value from a dataframe for a given driver_id with up to `max_date` date"""
     filtered = df[
         (df["driver_id"] == driver_id)
-        & (df["event_timestamp"] < max_date.replace(tzinfo=utc))
+        & (df["event_timestamp"] < max_date.replace(tzinfo=timezone.utc))
     ]
     max_ts = filtered.loc[filtered["event_timestamp"].idxmax()]["event_timestamp"]
     filtered_by_ts = filtered[filtered["event_timestamp"] == max_ts]

diff --git a/sdk/python/tests/utils/test_log_creator.py b/sdk/python/tests/utils/test_log_creator.py
@@ -117,7 +117,7 @@ def prepare_logs(
                     f"{destination_field}__status"
                 ].mask(
                     logs_df[f"{destination_field}__timestamp"]
-                    < (_utc_now() - view.ttl),
+                    < (_utc_now() - view.ttl).replace(tzinfo=None),
                     FieldStatus.OUTSIDE_MAX_AGE,
                 )