batch-analytics 0.2.3__tar.gz → 0.2.4__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (28) hide show
  1. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/PKG-INFO +1 -1
  2. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/pyproject.toml +1 -1
  3. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/job_runner.py +5 -3
  4. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics.egg-info/PKG-INFO +1 -1
  5. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/README.md +0 -0
  6. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/setup.cfg +0 -0
  7. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/__init__.py +0 -0
  8. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/__main__.py +0 -0
  9. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/analytics/__init__.py +0 -0
  10. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/analytics/correlation.py +0 -0
  11. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/analytics/linear_regression.py +0 -0
  12. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/analytics/pca_clustering.py +0 -0
  13. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/analytics/t_test.py +0 -0
  14. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/config.py +0 -0
  15. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/extract.py +0 -0
  16. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/log.py +0 -0
  17. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/modules.py +0 -0
  18. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/output/__init__.py +0 -0
  19. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/output/base.py +0 -0
  20. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/output/clickhouse.py +0 -0
  21. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/output/local.py +0 -0
  22. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/output/s3.py +0 -0
  23. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics/transform.py +0 -0
  24. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics.egg-info/SOURCES.txt +0 -0
  25. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics.egg-info/dependency_links.txt +0 -0
  26. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics.egg-info/entry_points.txt +0 -0
  27. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics.egg-info/requires.txt +0 -0
  28. {batch_analytics-0.2.3 → batch_analytics-0.2.4}/src/batch_analytics.egg-info/top_level.txt +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: batch-analytics
3
- Version: 0.2.3
3
+ Version: 0.2.4
4
4
  Summary: PySpark batch analytics: Extract, Transform, Stage, and analytical modules (linear regression, correlation, PCA, t-test).
5
5
  Author: Litewave Analytics Team
6
6
  License: MIT
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "batch-analytics"
7
- version = "0.2.3"
7
+ version = "0.2.4"
8
8
  description = "PySpark batch analytics: Extract, Transform, Stage, and analytical modules (linear regression, correlation, PCA, t-test)."
9
9
  readme = "README.md"
10
10
  requires-python = ">=3.8"
@@ -140,13 +140,15 @@ def run_pipeline(
140
140
  run_id = str(uuid.uuid4())[:8]
141
141
 
142
142
  if spark is None:
143
- # Native format("clickhouse") needs clickhouse-spark-runtime; JDBC fallback needs clickhouse-jdbc.
144
- # Override: BATCH_SPARK_CLICKHOUSE_PACKAGES=maven coords (comma-sep) or "" to use only SPARK_JARS.
143
+ # Native format("clickhouse") needs clickhouse-spark-runtime; JDBC needs shaded clickhouse-jdbc (*-all),
144
+ # not the thin Maven artifact: thin JAR lacks HttpClient 5 (ClassicHttpRequest).
145
+ # Override: BATCH_SPARK_CLICKHOUSE_PACKAGES=maven coords / https jar URLs (comma-sep) or "" for SPARK_JARS only.
145
146
  _raw_ch = os.environ.get("BATCH_SPARK_CLICKHOUSE_PACKAGES")
146
147
  if _raw_ch is None:
147
148
  ch_pkgs = (
148
149
  "com.clickhouse.spark:clickhouse-spark-runtime-3.5_2.12:0.8.0,"
149
- "com.clickhouse:clickhouse-jdbc:0.6.2"
150
+ "https://repo1.maven.org/maven2/com/clickhouse/clickhouse-jdbc/0.6.2/"
151
+ "clickhouse-jdbc-0.6.2-all.jar"
150
152
  )
151
153
  elif not _raw_ch.strip():
152
154
  ch_pkgs = None
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: batch-analytics
3
- Version: 0.2.3
3
+ Version: 0.2.4
4
4
  Summary: PySpark batch analytics: Extract, Transform, Stage, and analytical modules (linear regression, correlation, PCA, t-test).
5
5
  Author: Litewave Analytics Team
6
6
  License: MIT