arthur-common 2.1.59__tar.gz → 2.1.60__tar.gz

{arthur_common-2.1.59 → arthur_common-2.1.60}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: arthur-common
-Version: 2.1.59
+Version: 2.1.60
 Summary: Utility code common to Arthur platform components.
 License: MIT
 Author: Arthur
@@ -43,14 +43,14 @@ pip install arthur-common
 
 ## Requirements
 
-- Python 3.12
+- Python 3.13
 
 ## Development
 
 To set up the development environment, ensure you have [Poetry](https://python-poetry.org/) installed, then run:
 
 ```bash
-poetry env use 3.12
+poetry env use 3.13
 poetry install
 ```
 

{arthur_common-2.1.59 → arthur_common-2.1.60}/README.md

@@ -18,14 +18,14 @@ pip install arthur-common
 
 ## Requirements
 
-- Python 3.12
+- Python 3.13
 
 ## Development
 
 To set up the development environment, ensure you have [Poetry](https://python-poetry.org/) installed, then run:
 
 ```bash
-poetry env use 3.12
+poetry env use 3.13
 poetry install
 ```
 

{arthur_common-2.1.59 → arthur_common-2.1.60}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "arthur-common"
-version = "2.1.59"
+version = "2.1.60"
 description = "Utility code common to Arthur platform components."
 authors = ["Arthur <engineering@arthur.ai>"]
 license = "MIT"

{arthur_common-2.1.59 → arthur_common-2.1.60}/src/arthur_common/aggregations/aggregator.py

@@ -172,7 +172,9 @@ class SketchAggregationFunction(AggregationFunction, ABC):
         groups = data.groupby(dim_columns, dropna=False)
         for _, group in groups:
             calculated_metrics.append(
-                SketchAggregationFunction._group_to_series(group, timestamp_col, dim_columns, value_col),
+                SketchAggregationFunction._group_to_series(
+                    group, timestamp_col, dim_columns, value_col
+                ),
             )
 
         return calculated_metrics

{arthur_common-2.1.59 → arthur_common-2.1.60}/src/arthur_common/tools/duckdb_data_loader.py

@@ -16,6 +16,8 @@ from arthur_common.models.schema_definitions import (
     DType,
 )
 
+MAX_JSON_OBJECT_SIZE = 1024 * 1024 * 1024  # 1GB
+
 
 class ColumnFormat(BaseModel):
     source_name: str
@@ -104,9 +106,9 @@ class DuckDBOperator:
             stringified_schema = ", ".join([f"{kv}" for kv in key_value_pairs])
             stringified_schema = f"{{ {stringified_schema} }}"
 
-            read_stmt = f"read_json('memory://inferences.json', format='array', columns={stringified_schema})"
+            read_stmt = f"read_json('memory://inferences.json', format='array', columns={stringified_schema}, maximum_object_size={MAX_JSON_OBJECT_SIZE})"
         else:
-            read_stmt = "read_json_auto('memory://inferences.json')"
+            read_stmt = f"read_json_auto('memory://inferences.json', maximum_object_size={MAX_JSON_OBJECT_SIZE})"
 
         conn.sql(
             f"CREATE OR REPLACE TEMP TABLE {table_name} AS SELECT * FROM {read_stmt}",