Internal bugfix.

PiperOrigin-RevId: 630890157

.github/workflows/publish_to_pypi.yml

@@ -0,0 +1,25 @@
+name: Publish to PyPi
+
+# Only trigger the workflow manually (e.g. when deps changes)
+on: workflow_dispatch
+
+jobs:
+ # Publish when version is increased
+ publish-job:
+ # Only try to publish if:
+ # * Repo is self (prevents running from forks)
+ # * Branch is `main`
+ if: |
+ github.repository == 'google-research/spade_anomaly_detection'
+ && github.ref == 'refs/heads/main'
+ runs-on: ubuntu-latest
+ permissions:
+ contents: write
+ timeout-minutes: 30
+
+ steps:
+ # Publish the package (if local `__version__` > pip version)
+ - uses: etils-actions/[email protected]
+ with:
+ pypi-token: ${{ secrets.PYPI_API_TOKEN }}
+ parse-changelog: true

.github/workflows/pytest_and_autopublish.yml

@@ -50,5 +50,4 @@ jobs:
  - uses: etils-actions/[email protected]
  with:
  pypi-token: ${{ secrets.PYPI_API_TOKEN }}
- gh-token: ${{ secrets.GITHUB_TOKEN }}
  parse-changelog: true

pyproject.toml

@@ -17,13 +17,13 @@ keywords = ["anomaly detection", "ensemble model", "one class classifiers"]
 # pip dependencies of the project
 # Installed locally with `pip install -e .`
 dependencies = [
- "absl-py==1.0.0",
+ "absl-py==1.4.0",
  "frozendict==2.3.2",
- "joblib==1.1.0",
+ "joblib==1.2.0",
  "pandas==1.3.5",
- "pyarrow==10.0.0",
+ "pyarrow==14.0.1",
  "retry==0.9.2",
- "scikit-learn",
+ "scikit-learn==1.4.2",
  "parameterized==0.8.1",
  "pytest==7.1.2",
  "fastavro[codecs]==1.4.12",

spade_anomaly_detection/data_loader.py

@@ -54,8 +54,7 @@
 
 import tensorflow as tf
 
-
-_DATA_ROOT = 'third_party/py/spade_anomaly_detection/example_data/'
+_DATA_ROOT = 'spade_anomaly_detection/example_data/'
 
 
 def load_dataframe(

spade_anomaly_detection/data_loader_test.py

@@ -38,6 +38,8 @@
 import numpy as np
 import pandas as pd
 
+import pytest
+
 from spade_anomaly_detection import data_loader
 from spade_anomaly_detection import parameters
 from spade_anomaly_detection.data_utils import bq_dataset
@@ -634,6 +636,7 @@ def test_get_bigquery_job_config(self):
  self.assertEqual(job_config.write_disposition, 'WRITE_TRUNCATE')
  self.assertEqual(job_config.source_format, bigquery.SourceFormat.PARQUET)
 
+ @pytest.mark.skip(reason="create_tempdir is broken in pytest")
  def test_construct_file_paths_for_gcs(self):
  data_loader_object = data_loader.DataLoader(self.runner_parameters)
  local_folder = 'test_folder'
@@ -658,6 +661,7 @@ def test_construct_file_paths_for_gcs(self):
  ('use_parquet', True),
  ('use_csv', False),
  )
+ @pytest.mark.skip(reason="create_tempdir is broken in pytest")
  def test_upload_data_to_local_disk(self, use_parquet: bool):
  data_loader_object = data_loader.DataLoader(self.runner_parameters)
  data_loader_object.input_feature_metadata = self._get_feature_metadata()

spade_anomaly_detection/requirements.txt

@@ -1,12 +1,12 @@
-absl-py==1.0.0
+absl-py==1.4.0
 frozendict==2.3.2
 joblib==1.2.0
 pandas==1.3.5
 pyarrow==14.0.1
 retry==0.9.2
-scikit-learn
+scikit-learn==1.4.2
 parameterized==0.8.1
-# These are test dependencies and should be added as part of a seperate layer
+# These are test dependencies and should be added as part of a separate layer
 # in the container that isn't included in the base container.
 pytest==7.1.2
 # These are nested dependencies.