Initial Polars support

python/.pre-commit-config.yaml

@@ -6,10 +6,12 @@ repos:
     hooks:
       - id: black
         exclude: python/whylogs/core/proto/|python/docs/|python/whylogs/viz/html/|java|python/whylogs/api/logger/experimental/logger
+        files: ^(python/whylogs/)
   - repo: https://github.com/pycqa/flake8
     rev: 4.0.1
     hooks:
       - id: flake8
+        files: ^(python/whylogs/)
         args:
           - --max-line-length=160
           - --exclude="""\.tox |
@@ -30,17 +32,24 @@ repos:
     hooks:
       - id: isort
         args: [--filter-files]
+        files: ^(python/whylogs/)
         exclude: python/whylogs/core/proto/|python/docs/|python/whylogs/viz/html/|java|python/whylogs/api/logger/experimental/logger
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v0.942
     hooks:
       - id: mypy
         language: system
-        exclude: ^(python/tests/|python/examples/|python/examples/integration/|python/whylogs/core/proto/|python/docs/|python/whylogs/viz/html/|java|python/whylogs/api/logger/experimental/logger)
+        files: ^(python/whylogs/)
+        exclude: ^(python/.venv/lib/python3.8/site-packages/polars/ml/torch.py|python/tests/|python/examples/|python/examples/integration/|python/whylogs/core/proto/|python/docs/|python/whylogs/viz/html/|java|python/whylogs/api/logger/experimental/logger)
+        verbose: true
+        args:
+          - --exclude python/.venv
+          - -V
   - repo: https://github.com/pre-commit/mirrors-prettier
     rev: v2.5.1
     hooks:
       - id: prettier
+        files: ^(python/whylogs/)
         exclude: python/tests/|python/whylogs/core/proto/|python/docs/|python/whylogs/viz/html/|java
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.1.0

python/Makefile

@@ -165,7 +165,7 @@ telemetry-opt-out: ## create opt out file
 
 install: ## Install all dependencies with poetry.
 	@$(call i, Installing dependencies)
-	poetry install -E "viz s3 spark mlflow image fugue gcs embeddings proc"
+	poetry install -E "viz s3 spark mlflow image fugue gcs embeddings proc polars"
 
 coverage: ## Generate test coverage reports.
 	@$(call i, Generating test coverage)

python/pyproject.toml

@@ -20,6 +20,10 @@ whylabs-client = "^0.6.5"
 requests = "^2.27"
 backoff = "^2.2.1"
 platformdirs = "^3.5.0"
+setuptools = [
+  { version = "<58", python = "<3.8", optional = false },
+  { version = ">=75", python = ">=3.8", optional = false }
+]
 
 # viz module. Everything after this should be optional
 pybars3 = { version = "^0.9", optional = true }
@@ -34,7 +38,11 @@ numpy = [
 ]
 
 # datasets module.
-pandas = { version = "*", optional = true}
+pandas = { version = "*", optional = true }
+
+# Polars module.
+polars = { version = ">=1.8.2", python = ">=3.8", optional = true }
+# TODO: do we want polars-u64-idx ?
 
 # Doc dependencies
 sphinx = { version = "*", optional = true }
@@ -110,6 +118,10 @@ spark = [
 datasets = [
   "pandas",
 ]
+polars = [
+  "polars",
+]
+
 gcs = [
   "google-cloud-storage",
 ]
@@ -148,6 +160,7 @@ all = [
   "boto3",
   "google-cloud-storage",
   "pandas",
+  "polars",
   "pyarrow",
   "pyspark",
   "ipython",