Merge branch 'master' into release/1.4.2

.checklist.yaml

@@ -0,0 +1,30 @@
+apiVersion: quintoandar.com.br/checklist/v2
+kind: ServiceChecklist
+metadata:
+  name: butterfree
+spec:
+  description: >-
+    A solution for Feature Stores.
+
+  costCenter: C055
+  department: engineering
+  lifecycle: production
+  docs: true
+
+  ownership:
+    team: data_products_mlops
+    line: tech_platform
+    owner: otavio.cals@quintoandar.com.br
+
+  libraries:
+    - name: butterfree
+      type: common-usage
+      path: https://quintoandar.github.io/python-package-server/
+      description: A lib to build Feature Stores.
+      registries:
+      - github-packages
+      tier: T0
+
+  channels:
+    squad: 'mlops'
+    alerts: 'data-products-reports'

.github/workflows/skip_lint.yml

@@ -0,0 +1,17 @@
+# This step is used only because we want to mark the runner-linter check as required
+# for PRs to develop, but not for the merge queue to merge into develop,
+# github does not have this functionality yet
+
+name: 'Skip github-actions/runner-linter check at merge queue'
+
+on:
+  merge_group:
+
+jobs:
+  empty_job:
+    name: 'github-actions/runner-linter'
+    runs-on: github-actions-developers-runner
+    steps:
+      - name: Skip github-actions/runner-linter check at merge queue
+        run: |
+          echo "Done"

CHANGELOG.md

@@ -5,6 +5,12 @@ Preferably use **Added**, **Changed**, **Removed** and **Fixed** topics in each
 
 ## [Unreleased]
 
+## [1.4.1](https://github.com/quintoandar/butterfree/releases/tag/1.4.1)
+* Performance Improvements ([#374](https://github.com/quintoandar/butterfree/pull/374))
+
+## [1.4.0](https://github.com/quintoandar/butterfree/releases/tag/1.4.0)
+* Add Delta support ([#370](https://github.com/quintoandar/butterfree/pull/370))
+
 ## [1.3.5](https://github.com/quintoandar/butterfree/releases/tag/1.3.5)
 * Auto create feature sets ([#368](https://github.com/quintoandar/butterfree/pull/368))
 

butterfree/transform/aggregated_feature_set.py

@@ -642,6 +642,7 @@ def construct(
         output_df = output_df.select(*self.columns).replace(  # type: ignore
             float("nan"), None
         )
+
         if not output_df.isStreaming and self.deduplicate_rows:
             output_df = self._filter_duplicated_rows(output_df)