source: df: Added docstring and doctestable example

Fixes: #671

Signed-off-by: sakshamarora1 <[email protected]>

Author: sakshamarora1

CHANGELOG.md

@@ -6,6 +6,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 ### Added
+- Docstrings and doctestable example for DataFlowSource
 - XGBoost Regression Model
 - Pre-Trained PyTorch torchvision Models
 - Spacy model for NER

dffml/source/df.py

@@ -66,6 +66,67 @@ async def __aexit__(self, exc_type, exc_value, traceback):
 
 @entrypoint("df")
 class DataFlowSource(BaseSource):
+    """
+    >>> import asyncio
+    >>> from dffml import *
+    >>>
+    >>> records = [
+    ...     Record(
+    ...         "0",
+    ...         data={
+    ...             "features": {
+    ...                 "Years": 1,
+    ...                 "Expertise": 3,
+    ...                 "Trust": 0.2,
+    ...                 "Salary": 20,
+    ...             }
+    ...         },
+    ...     ),
+    ... ]
+    >>>
+    >>> features = Features(
+    ...     Feature("Years", int, 1),
+    ...     Feature("Expertise", int, 1),
+    ...     Feature("Trust", float, 1),
+    ...     Feature("Salary", int, 1),
+    ... )
+    >>>
+    >>> dataflow = DataFlow(multiply, AssociateDefinition)
+    >>> dataflow.flow["multiply"].inputs["multiplicand"] = [
+    ...     {"seed": ["Years", "Expertise", "Trust", "Salary"]}
+    ... ]
+    >>> dataflow.seed = [
+    ...     Input(
+    ...         value={
+    ...             feature.name: multiply.op.outputs["product"].name
+    ...             for feature in features
+    ...         },
+    ...         definition=AssociateDefinition.op.inputs["spec"],
+    ...     ),
+    ...     Input(value=10, definition=multiply.op.inputs["multiplier"],),
+    ... ]
+    >>>
+    >>>
+    >>> memory_source = Sources(MemorySource(MemorySourceConfig(records=records)))
+    >>>
+    >>> source = DataFlowSource(
+    ...     DataFlowSourceConfig(
+    ...         source=memory_source, dataflow=dataflow, features=features,
+    ...     )
+    ... )
+    >>>
+    >>>
+    >>> async def main():
+    ...     async with source as src:
+    ...         async with src() as sctx:
+    ...             async for record in sctx.records():
+    ...                 print(record.features())
+    ...
+    >>>
+    >>> asyncio.run(main())
+    {'Years': 10, 'Expertise': 30, 'Trust': 2.0, 'Salary': 200}
+    """
+
     CONFIG = DataFlowSourceConfig
     CONTEXT = DataFlowSourceContext