[Data] Move logging configuration to python dictionary from yaml (#48093)

## Why are these changes needed?
We currently have our default logging configuration as a YAML file that
we then load as a python dictionary. This forces us to include the yaml
in the ray wheel. This inlines the configuration into a python
dictionary to be included in `logging.py`.

## Related issue number

## Checks

- [x] I've signed off every commit(by using the -s flag, i.e., `git
commit -s`) in this PR.
- [x] I've run `scripts/format.sh` to lint the changes in this PR.
- [ ] I've included any doc changes needed for
https://docs.ray.io/en/master/.
- [ ] I've added any new APIs to the API Reference. For example, if I
added a
method in Tune, I've added it in `doc/source/tune/api/` under the
           corresponding `.rst` file.
- [ ] I've made sure the tests are passing. Note that there might be a
few flaky tests, see the recent failures at https://flakey-tests.ray.io/
- Testing Strategy
   - [x] Unit tests
   - [ ] Release tests
   - [ ] This PR is not tested :(

Signed-off-by: Matthew Owen <[email protected]>

Author: omatthew98

python/ray/data/_internal/logging.py

@@ -7,9 +7,53 @@
 
 import ray
 
-DEFAULT_CONFIG_PATH = os.path.abspath(
-    os.path.join(os.path.dirname(__file__), "logging.yaml")
-)
+DEFAULT_CONFIG = {
+    "version": 1,
+    "disable_existing_loggers": False,
+    "formatters": {
+        "ray": {
+            "format": "%(asctime)s\t%(levelname)s %(filename)s:%(lineno)s -- %(message)s"  # noqa: E501
+        },
+        "ray_json": {"class": "ray._private.ray_logging.formatters.JSONFormatter"},
+    },
+    "filters": {
+        "console_filter": {"()": "ray.data._internal.logging.HiddenRecordFilter"},
+        "core_context_filter": {
+            "()": "ray._private.ray_logging.filters.CoreContextFilter"
+        },
+    },
+    "handlers": {
+        "file": {
+            "class": "ray.data._internal.logging.SessionFileHandler",
+            "formatter": "ray",
+            "filename": "ray-data.log",
+        },
+        "file_json": {
+            "class": "ray.data._internal.logging.SessionFileHandler",
+            "formatter": "ray_json",
+            "filename": "ray-data.log",
+            "filters": ["core_context_filter"],
+        },
+        "console": {
+            "class": "ray._private.log.PlainRayHandler",
+            "formatter": "ray",
+            "level": "INFO",
+            "filters": ["console_filter"],
+        },
+    },
+    "loggers": {
+        "ray.data": {
+            "level": "DEBUG",
+            "handlers": ["file", "console"],
+            "propagate": False,
+        },
+        "ray.air.util.tensor_extensions": {
+            "level": "DEBUG",
+            "handlers": ["file", "console"],
+            "propagate": False,
+        },
+    },
+}
 
 # Dictionary of substitutions to be performed when using JSON mode. Handlers with names
 # corresponding to keys will be replaced by those corresponding to values.
@@ -119,7 +163,7 @@ def _load_logging_config(config_path: str):
     if config_path is not None:
         config = _load_logging_config(config_path)
     else:
-        config = _load_logging_config(DEFAULT_CONFIG_PATH)
+        config = DEFAULT_CONFIG
         if log_encoding is not None and log_encoding.upper() == "JSON":
             for logger in config["loggers"].values():
                 for (

python/ray/data/_internal/logging.yaml

@@ -809,7 +809,7 @@ def has_ext_modules(self):
         ]
     },
     package_data={
-        "ray": ["includes/*.pxd", "*.pxd", "data/_internal/logging.yaml"],
+        "ray": ["includes/*.pxd", "*.pxd"],
     },
     include_package_data=True,
     exclude_package_data={