ocean-runner 0.2.13__py3-none-any.whl → 0.2.15__py3-none-any.whl

ocean_runner/config.py

@@ -2,7 +2,7 @@ import os
 from dataclasses import asdict, dataclass, field
 from logging import Logger
 from pathlib import Path
-from typing import Callable, Iterable, TypeVar
+from typing import Iterable, TypeVar
 
 T = TypeVar("T")
 
@@ -43,9 +43,6 @@ class Config:
     custom_input: T | None = None
     """Algorithm's custom input types, must be a dataclass_json"""
 
-    error_callback: Callable[[Exception], None] = None
-    """Callback to execute upon exceptions"""
-
     logger: Logger | None = None
     """Logger to use in the algorithm"""
 
@@ -54,7 +51,5 @@ class Config:
     )
     """Paths that should be included so the code executes correctly"""
 
-    environment: Environment = field(
-        default_factory=lambda: Environment(),
-    )
+    environment: Environment = field(default_factory=lambda: Environment())
     """Mock of environment data"""

ocean_runner/runner.py

@@ -1,10 +1,9 @@
 from __future__ import annotations
 
-import inspect
 from dataclasses import InitVar, asdict, dataclass, field
 from logging import Logger
 from pathlib import Path
-from typing import Callable, Generic, Self, TypeVar
+from typing import Callable, Generic, TypeVar
 
 from oceanprotocol_job_details import JobDetails
 
@@ -14,7 +13,7 @@ JobDetailsT = TypeVar("JobDetailsT")
 ResultT = TypeVar("ResultT")
 
 
-def default_error_callback(_: Algorithm, e: Exception) -> None:
+def default_error_callback(_, e: Exception) -> None:
     raise e
 
 
@@ -32,28 +31,31 @@ def default_save(*, result: ResultT, base: Path, algorithm: Algorithm) -> None:
 
 @dataclass
 class Algorithm(Generic[JobDetailsT, ResultT]):
+    """
+    A configurable algorithm runner that behaves like a FastAPI app:
+      - You register `validate`, `run`, and `save_results` via decorators.
+      - You execute the full pipeline by calling `app()`.
+    """
 
     config: InitVar[Config | None] = None
     logger: Logger = field(init=False)
     _job_details: JobDetails[JobDetailsT] = field(init=False)
     _result: ResultT | None = field(default=None, init=False)
-    error_callback = default_error_callback
+
+    # Decorator-registered callbacks
+    _validate_fn: Callable[[Algorithm], None] | None = field(default=None, init=False)
+    _run_fn: Callable[[Algorithm], ResultT] | None = field(default=None, init=False)
+    _save_fn: Callable[[ResultT, Path, Algorithm], None] | None = field(
+        default=None, init=False
+    )
+    _error_callback: Callable[[Algorithm, Exception], None] = field(
+        default=default_error_callback, init=False
+    )
 
     def __post_init__(self, config: Config | None) -> None:
         config: Config = config or Config()
-        if config.error_callback:
-            self.error_callback = config.error_callback
-
-        self._setup_logger(config)
-        self._load_job_details(config)
-        self._load_user_defined_functions()
-        self._maybe_autorun(config)
-
-    # ---------------------
-    # Setup helpers
-    # ---------------------
 
-    def _setup_logger(self, config: Config) -> None:
+        # Configure logger
         if config.logger:
             self.logger = config.logger
         else:
@@ -66,15 +68,18 @@ class Algorithm(Generic[JobDetailsT, ResultT]):
             )
             self.logger = logging.getLogger("ocean_runner")
 
-    def _load_job_details(self, config: Config) -> None:
+        # Normalize base_dir
         if isinstance(config.environment.base_dir, str):
             config.environment.base_dir = Path(config.environment.base_dir)
+
+        # Extend sys.path for custom imports
         if config.source_paths:
             import sys
 
             sys.path.extend([str(path.absolute()) for path in config.source_paths])
             self.logger.debug(f"Added [{len(config.source_paths)}] entries to PATH")
 
+        # Load job details
         self._job_details = JobDetails.load(
             _type=config.custom_input,
             base_dir=config.environment.base_dir,
@@ -82,49 +87,13 @@ class Algorithm(Generic[JobDetailsT, ResultT]):
             transformation_did=config.environment.transformation_did,
             secret=config.environment.secret,
         )
+
         self.logger.info("Loaded JobDetails")
         self.logger.debug(asdict(self.job_details))
 
-    # ---------------------
-    # Auto-detect functions
-    # ---------------------
-
-    def _load_user_defined_functions(self) -> None:
-        caller = inspect.getmodule(inspect.stack()[2][0])
-        if not caller:
-            return
-
-        for name, default in {
-            "validation": default_validation,
-            "run": None,
-            "save": default_save,
-        }.items():
-            fn = getattr(caller, name, None)
-            if callable(fn):
-                self.logger.debug(f"Found user-defined '{name}' function")
-                setattr(self, f"_user_{name}", fn)
-            elif default:
-                setattr(self, f"_user_{name}", default)
-
-        self._caller_module = caller
-
-    # ---------------------
-    # Auto-run logic
-    # ---------------------
-
-    def _maybe_autorun(self, config) -> None:
-        """Automatically runs if caller has __ocean_runner_autorun__ = True"""
-        if (
-            getattr(self, "_caller_module", None)
-            and getattr(self._caller_module, "__ocean_runner_autorun__", False)
-            and not getattr(config, "_from_test", False)
-        ):
-            self.logger.info("Auto-running algorithm...")
-            self.validate().run().save_results()
-
-    # ---------------------
-    # Main API
-    # ---------------------
+        self.config = config
+
+    class Error(RuntimeError): ...
 
     @property
     def job_details(self) -> JobDetails:
@@ -138,41 +107,66 @@ class Algorithm(Generic[JobDetailsT, ResultT]):
             raise Algorithm.Error("Result missing, run the algorithm first")
         return self._result
 
-    def validate(self, callback: Callable[[Self], None] | None = None) -> Self:
-        callback = callback or getattr(self, "_user_validation", default_validation)
-        self.logger.info("Validating instance...")
-        try:
-            callback(self)
-        except Exception as e:
-            self.error_callback(e)
-        return self
-
-    def run(self, callback: Callable[[Self], ResultT] | None = None) -> Self:
-        callback = callback or getattr(self, "_user_run", None)
-        if callback is None:
-            raise Algorithm.Error("No 'run' function found")
-        self.logger.info("Running algorithm...")
-        try:
-            self._result = callback(self)
-        except Exception as e:
-            self.error_callback(e)
-        return self
-
-    def save_results(
-        self,
-        callback: Callable[[ResultT, Path, Algorithm], None] | None = None,
-        *,
-        override_path: Path | None = None,
-    ) -> None:
-        callback = callback or getattr(self, "_user_save", default_save)
-        self.logger.info("Saving results...")
+    # ---------------------------
+    # Decorators (FastAPI-style)
+    # ---------------------------
+
+    def validate(self, fn: Callable[[], None]) -> Callable[[], None]:
+        self._validate_fn = fn
+        return fn
+
+    def run(self, fn: Callable[[], ResultT]) -> Callable[[], ResultT]:
+        self._run_fn = fn
+        return fn
+
+    def save_results(self, fn: Callable[[ResultT, Path], None]) -> Callable:
+        self._save_fn = fn
+        return fn
+
+    def on_error(self, fn: Callable[[Exception], None]) -> Callable:
+        self._error_callback = fn
+        return fn
+
+    # ---------------------------
+    # Execution Pipeline
+    # ---------------------------
+
+    def __call__(self) -> ResultT | None:
+        """Executes the algorithm pipeline: validate → run → save_results."""
         try:
-            callback(
-                result=self.result,
-                base=override_path or self.job_details.paths.outputs,
-                algorithm=self,
-            )
+            # Validation step
+            if self._validate_fn:
+                self.logger.info("Running custom validation...")
+                self._validate_fn()
+            else:
+                self.logger.info("Running default validation...")
+                self.default_validation(self)
+
+            # Run step
+            if self._run_fn:
+                self.logger.info("Running algorithm...")
+                self._result = self._run_fn()
+            else:
+                self.logger.warning("No run() function defined. Skipping execution.")
+                self._result = None
+
+            # Save step
+            if self._save_fn:
+                self.logger.info("Saving results...")
+                self._save_fn(
+                    self._result,
+                    self.job_details.paths.outputs,
+                )
+            else:
+                self.logger.info("No save_results() defined. Using default.")
+                default_save(
+                    result=self._result,
+                    base=self.job_details.paths.outputs,
+                    algorithm=self,
+                )
+
         except Exception as e:
-            self.error_callback(e)
+            self.logger.exception("Error during algorithm execution")
+            self._error_callback(e)
 
-    class Error(RuntimeError): ...
+        return self._result

{ocean_runner-0.2.13.dist-info → ocean_runner-0.2.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocean-runner
-Version: 0.2.13
+Version: 0.2.15
 Summary: A fluent API for OceanProtocol algorithms
 Project-URL: Homepage, https://github.com/AgrospAI/ocean-runner
 Project-URL: Issues, https://github.com/AgrospAI/ocean-runner/issues
@@ -23,7 +23,7 @@ Description-Content-Type: text/markdown
 
 # ocean-runner
 
-Ocean Runner is a package that brings a fluent API for APP creation and running in the scope of OceanProtocol.
+Ocean Runner is a package that eases algorithm creation in the scope of OceanProtocol.
 
 
 ## Installation
@@ -40,33 +40,40 @@ uv add ocean-runner
 
 ```python
 import random
-from ocean_runner import Algorithm, Config
+from ocean_runner import Algorithm
+
+algorithm = Algorithm()
+
 
+@algorithm.run
+def run():
+    return random.randint()
 
-Algorithm().run(lambda _: random.randint()).save_results()    
+
+if __name__ == "__main__":
+    algorithm()
 ```
 
-To use minimally the API, you can just provide a callback to the run method, defaulting for the rest of behaviours. This code snippet will:
+This code snippet will:
 
-- Read the OceanProtocol JobDetails from the environment variables and use default file paths.
-- Generate a random integer.
-- Store the result in a "result.txt" file within the default outputs path.
+- Read the OceanProtocol JobDetails from the environment variables and use default configuration file paths.
+- Execute the run function.
+- Execute the default saving function, storing the result in a "result.txt" file within the default outputs path.
 
 ### Tuning
 
 #### Application Config
 
-The application configuration can be tweaked by passing a Config instance to its' constructor.
+The application configuration can be tweaked by passing a Config instance to its constructor.
 
 ```python
-Algorithm(
+from ocean_runner import Algorithm, Config
+
+algorithm = Algorithm(
     Config(
         custom_input: ... # dataclass
         # Custom algorithm parameters dataclass.
         
-        error_callback: ... # Callable[[Exception], None]
-        # Callback to run on exceptions.
-        
         logger: ... # type: logging.Logger
         # Custom logger to use.
 
@@ -82,6 +89,8 @@ Algorithm(
 ```python
 import logging
 
+from ocean_runner import Algorithm, Config
+
 
 @dataclass
 class CustomInput:
@@ -91,19 +100,13 @@ class CustomInput:
 logger = logging.getLogger(__name__)
 
 
-Algorithm(
+algorithm = Algorithm(
     Config(
         custom_input: CustomInput,
         """
         Load the Algorithm's Custom Input into a CustomInput dataclass instance.
         """
 
-        error_callback: lambda ex: logger.exception(ex),
-        """
-        Run this callback when an exception is caught
-        NOTE: it's not recommended to catch exceptions this way. Should re-raise and halt the execution.
-        """
-
         source_paths: [Path("/algorithm/src")],
         """
         Source paths to include in the PATH. '/algorithm/src' is the default since our templates place the algorithm source files there.
@@ -143,44 +146,72 @@ Algorithm(
 
 ```
 
-## Default behaviours
+#### Behaviour Config
 
-### Default implementations
-
-As seen in the minimal example, all methods implemented in `Algorithm` have a default implementation which will be commented here.
+To fully configure the behaviour of the algorithm as in the [Minimal Example](#minimal-example), you can do it decorating your defined function as in the following example, which features all the possible algorithm customization.
 
 ```python
+from pathlib import Path
 
-(
-    Algorithm()
-    
-        """
-        Default constructor, will use default values of Config.
-        """
-    
-    .validate()
-    
-        """
-        Will validate the algorithm's job detail instance, checking for the existence of:
-        - `job_details.ddos` 
-        - `job_details.files`
-        """
+import pandas as pd
+from ocean_runner import Algorithm
 
-    .run()
+algorithm = Algorithm()
 
-        """ 
-        Has NO default implementation, must pass a callback that returns a result of any type.
-        """
 
-    .save_results()
+@algorithm.on_error
+def error_callback(ex: Exception):
+    algorithm.logger.exception(ex)
+    raise algorithm.Error() from ex
 
-        """
-        Stores the result of running the algorithm in "outputs/results.txt"
-        """
 
-)
+@algorithm.validate
+def val():
+    assert algorithm.job_details.files, "Empty input dir"
+
+
+@algorithm.run
+def run() -> pd.DataFrame:
+    _, filename = next(algorithm.job_details.next_path())
+    return pd.read_csv(filename).describe(include="all")
+
+
+@algorithm.save_results
+def save(results: pd.DataFrame, path: Path):
+    algorithm.logger.info(f"Descriptive statistics: {results}")
+    results.to_csv(path / "results.csv")
+
+
+if __name__ == "__main__":
+    algorithm()
+```
+
+
+
+### Default implementations
+
+As seen in the minimal example, all methods implemented in `Algorithm` have a default implementation which will be commented here.
+
+```python
+.validate()
+
+    """
+    Will validate the algorithm's job detail instance, checking for the existence of:
+    - `job_details.ddos`
+    - `job_details.files`
+    """
+
+.run()
+
+    """ 
+    Has NO default implementation, must pass a callback that returns a result of any type.
+    """
 
+.save_results()
 
+    """
+    Stores the result of running the algorithm in "outputs/results.txt"
+    """
 ```
 
 ### Job Details
@@ -188,7 +219,7 @@ As seen in the minimal example, all methods implemented in `Algorithm` have a de
 To load the OceanProtocol JobDetails instance, the program will read some environment variables, they can be mocked passing an instance of `Environment` through the configuration of the algorithm.
 
 Environment variables:
-- `DIDS` Input dataset(s) DID's, must have format: `["abc..90"]`
-- `TRANSFORMATION_DID` Algorithm DID, must have format: `abc..90`
-- `SECRET` Algorithm secret.
+- `DIDS` (optional) Input dataset(s) DID's, must have format: `["abc..90"]`. Defaults to reading them automatically from the `DDO` data directory.
+- `TRANSFORMATION_DID` (optional, default="DEFAULT"): Algorithm DID, must have format: `abc..90`.
+- `SECRET` (optional, default="DEFAULT"): Algorithm secret. 
 - `BASE_DIR` (optional, default="/data"): Base path to the OceanProtocol data directories.

ocean_runner-0.2.15.dist-info/RECORD

@@ -0,0 +1,7 @@
+ocean_runner/__init__.py,sha256=awAmE6kZhuwcrD3gT7qFZArdhiuzW-EFTA6tGKhw06k,138
+ocean_runner/config.py,sha256=gyyUotPJ7n8wPPdsJZIBUT4zBlkoNbhV876JDTdPNsY,1398
+ocean_runner/runner.py,sha256=0UbKFCN_tuhanACOJShiPkpOrg3tQhkohuH1QweAbgA,5726
+ocean_runner-0.2.15.dist-info/METADATA,sha256=cr_MIftAYwQbcn3eZwaH_GeM6JdG7mxZLtI4vmTlnoc,6562
+ocean_runner-0.2.15.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+ocean_runner-0.2.15.dist-info/licenses/LICENSE,sha256=_B25KqK4amoADWkMN150tnZFm_Fy7VvZpvIC8ZydWdI,1053
+ocean_runner-0.2.15.dist-info/RECORD,,

ocean_runner-0.2.13.dist-info/RECORD

@@ -1,7 +0,0 @@
-ocean_runner/__init__.py,sha256=awAmE6kZhuwcrD3gT7qFZArdhiuzW-EFTA6tGKhw06k,138
-ocean_runner/config.py,sha256=EgloiUTLBvca4B_pr2eNa8kHYfsyVE73ZxszLCbiDYY,1525
-ocean_runner/runner.py,sha256=-nYH6_TtAEJ9RWv_PWmeDMyfJOhQ1tlrJrNHi7ZmYKo,5941
-ocean_runner-0.2.13.dist-info/METADATA,sha256=orDe6w9hnST2HI33Ta3rU2-kUg9ulFSq9mQhLOhuVxI,5919
-ocean_runner-0.2.13.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-ocean_runner-0.2.13.dist-info/licenses/LICENSE,sha256=_B25KqK4amoADWkMN150tnZFm_Fy7VvZpvIC8ZydWdI,1053
-ocean_runner-0.2.13.dist-info/RECORD,,