Fix value bug that affects the evaluation service (#222)

* Fix value bug that affects the evaluation service

* Update Changelog

Author: gatli

CHANGELOG.md

@@ -4,7 +4,12 @@ All notable changes to the [Nucleus Python Client](https://github.com/scaleapi/n
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.6.3](https://github.com/scaleapi/nucleus-python-client/releases/tag/v0.6.3) - 2021-02-08
+## [0.6.4](https://github.com/scaleapi/nucleus-python-client/releases/tag/v0.6.4) - 2021-02-16
+
+### Fixes
+- Categorization metrics are patched to run properly on Validate evaluation service
+
+## [0.6.3](https://github.com/scaleapi/nucleus-python-client/releases/tag/v0.6.3) - 2021-02-15
 
 ### Added
 - Add categorization f1 score to metrics

nucleus/metrics/categorization_metrics.py

@@ -40,7 +40,7 @@ def value(self):
         # TODO: Change task.py interface such that we can return label matching
         # NOTE: Returning 1 if all taxonomy labels match else 0
         value = f1_score(
-            annotation_labels, prediction_labels, average=self.f1_method
+            list(annotation_labels), list(prediction_labels), average="macro"
         )
         return value
 

pyproject.toml

@@ -21,7 +21,7 @@ exclude = '''
 
 [tool.poetry]
 name = "scale-nucleus"
-version = "0.6.3"
+version = "0.6.4"
 description = "The official Python client library for Nucleus, the Data Platform for AI"
 license =  "MIT"
 authors = ["Scale AI Nucleus Team <nucleusapi@scaleapi.com>"]