Refactor: Streamline Verb Core Functions, Package Exports (microsoft#747

)

python/datashaper/.semversioner/next-release/major-20240509015515758041.json → python/datashaper/.semversioner/next-release/patch-20240509015515758041.json

@@ -1,4 +1,4 @@
 {
-  "type": "major",
+  "type": "patch",
   "description": "schema changes"
 }

python/datashaper/.semversioner/next-release/major-20240530233724204309.json → python/datashaper/.semversioner/next-release/patch-20240530233724204309.json

@@ -1,4 +1,4 @@
 {
-  "type": "major",
+  "type": "patch",
   "description": "Schema cleanup"
 }

python/datashaper/.semversioner/next-release/patch-20240603225052778224.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "split verbs from execution-graph boilerplate"
+}

python/datashaper/datashaper/__init__.py

@@ -1,98 +1,70 @@
 """DataShaper is a library for declarative data manipulation and transformation."""
-from .engine import (
-    AsyncType,
+
+from .tables import (
+    DataTable,
+    DiskCacheTableStore,
+    InMemoryTableStore,
+    ParserOptions,
+    TableStore,
+    TypeHints,
+    load_csv_table,
+    load_json_table,
+    load_table,
+)
+from .utils.parallelization import AsyncStrategy, derive_from_rows
+from .utils.progress import (
+    Progress,
+    ProgressHandler,
+    ProgressTicker,
+    progress_callback,
+    progress_iterable,
+    progress_ticker,
+)
+from .verbs import (
     Bin,
     BinStrategy,
     BooleanComparisonOperator,
     BooleanLogicalOperator,
     Category,
+    ColumnMetadata,
+    ColumnStats,
     ComparisonStrategy,
     DataType,
     FieldAggregateOperation,
-    FileType,
+    FileFormat,
     FilterArgs,
     InputColumnArgs,
     JoinStrategy,
     MathOperator,
     MergeStrategy,
+    NoopVerbCallbacks,
     NumericComparisonOperator,
     OrderByInstruction,
+    ParallelizationMode,
     ParseType,
     SetOp,
     SortDirection,
-    Step,
     StringComparisonOperator,
+    Table,
+    TableContainer,
+    TableMetadata,
+    VerbCallbacks,
     VerbDetails,
     VerbInput,
     VerbManager,
+    VerbResult,
     WindowFunction,
-    aggregate_operation_mapping,
-    boolean_function_map,
-    filter_df,
-    get_operator,
+    inputs,
     load_verbs,
-    new_row,
     parallel_verb,
     verb,
 )
-from .errors import (
-    InvalidVerbInputError,
-    NodeNotVisitedError,
-    NoVerbInputsProvidedError,
-    UnsupportedComparisonOperatorError,
-    VerbAlreadyRegisteredError,
-    VerbError,
-    VerbHasMultipleDefaultInputsError,
-    VerbHasMultipleDefaultOthersError,
-    VerbOperationNotSupportedError,
-    VerbParallelizationError,
-    WorkflowError,
-    WorkflowInvalidInputError,
-    WorkflowMissingInputError,
-    WorkflowOutputNotReadyError,
-    WorkflowVerbNotFoundError,
-)
-from .execution import (
-    ExecutionNode,
-    VerbDefinitions,
-    derive_from_rows,
-    derive_from_rows_asyncio,
-    derive_from_rows_asyncio_threads,
-    parallelize,
-)
-from .progress import (
-    Progress,
-    ProgressHandler,
-    ProgressTicker,
-    progress_callback,
-    progress_iterable,
-    progress_ticker,
-)
-from .table_store.types import (
-    ColumnMetadata,
-    ColumnStats,
-    Table,
-    TableContainer,
-    TableMetadata,
-    VerbResult,
-    create_verb_result,
-)
-from .tables import (
-    DataTable,
-    ParserOptions,
-    TypeHints,
-    load_csv_table,
-    load_json_table,
-    load_table,
-)
 from .workflow import (
     DEFAULT_INPUT_NAME,
-    DelegatingVerbCallbacks,
+    ExecutionNode,
     MemoryProfile,
-    NoopVerbCallbacks,
     NoopWorkflowCallbacks,
     PandasDtypeBackend,
-    VerbCallbacks,
     VerbTiming,
     Workflow,
     WorkflowCallbacks,
@@ -101,34 +73,67 @@
 )
 
 __all__ = [
-    "AsyncType",
-    "derive_from_rows",
-    "derive_from_rows_asyncio",
-    "derive_from_rows_asyncio_threads",
-    "parallelize",
-    "VerbDefinitions",
+    # Workflow Exports
+    "Workflow",
+    "DEFAULT_INPUT_NAME",
+    "WorkflowRunResult",
+    "VerbTiming",
+    "MemoryProfile",
+    "WorkflowCallbacks",
+    "NoopWorkflowCallbacks",
+    "WorkflowCallbacksManager",
+    "PandasDtypeBackend",
     "ExecutionNode",
-    # Verb Exports
+    # table utilities
+    "DataTable",
+    "ParserOptions",
+    "TypeHints",
+    "load_csv_table",
+    "load_json_table",
+    "load_table",
+    "DiskCacheTableStore",
+    "InMemoryTableStore",
+    "TableStore",
+    # Progress Utils
+    "progress_callback",
+    "progress_iterable",
+    "progress_ticker",
+    "ProgressHandler",
+    "ProgressTicker",
+    "Progress",
+    # Parallelization Utils
+    "derive_from_rows",
+    "AsyncStrategy",
+    # Verb Types
+    "Table",
+    "TableContainer",
+    "TableMetadata",
+    "ColumnMetadata",
+    "ColumnStats",
+    "DataType",
+    "Bin",
+    "Category",
     "VerbInput",
-    "VerbDetails",
-    "verb",
     "VerbManager",
     "load_verbs",
+    "verb",
+    "inputs",
     "parallel_verb",
-    "new_row",
-    # Verb Parameters
-    "BinStrategy",
+    "ParallelizationMode",
+    "VerbDetails",
+    "VerbResult",
     "Bin",
+    "BinStrategy",
     "BooleanComparisonOperator",
     "BooleanLogicalOperator",
     "Category",
+    "ComparisonStrategy",
+    "DataType",
     "FieldAggregateOperation",
-    "FileType",
+    "FileFormat",
     "FilterArgs",
-    "ComparisonStrategy",
     "InputColumnArgs",
     "JoinStrategy",
-    "DataType",
     "MathOperator",
     "MergeStrategy",
     "NumericComparisonOperator",
@@ -138,60 +143,11 @@
     "SortDirection",
     "StringComparisonOperator",
     "WindowFunction",
-    "Step",
-    "aggregate_operation_mapping",
-    "boolean_function_map",
-    "filter_df",
-    "get_operator",
-    # Workflow Exports
-    "Workflow",
-    "DEFAULT_INPUT_NAME",
-    "WorkflowRunResult",
-    "VerbTiming",
-    "MemoryProfile",
-    "VerbCallbacks",
-    "DelegatingVerbCallbacks",
-    "NoopVerbCallbacks",
-    "WorkflowCallbacks",
-    "NoopWorkflowCallbacks",
-    "WorkflowCallbacksManager",
-    "PandasDtypeBackend",
-    # Tablestore Exports
-    "ColumnStats",
+    "Table",
     "ColumnMetadata",
-    "TableMetadata",
+    "ColumnStats",
     "TableContainer",
-    "Table",
-    "VerbResult",
-    "create_verb_result",
-    # table utilities
-    "DataTable",
-    "ParserOptions",
-    "TypeHints",
-    "load_csv_table",
-    "load_json_table",
-    "load_table",
-    # Progress Exports
-    "progress_callback",
-    "progress_iterable",
-    "progress_ticker",
-    "ProgressHandler",
-    "ProgressTicker",
-    "Progress",
-    # Errors
-    "UnsupportedComparisonOperatorError",
-    "InvalidVerbInputError",
-    "VerbError",
-    "WorkflowMissingInputError",
-    "WorkflowOutputNotReadyError",
-    "WorkflowVerbNotFoundError",
-    "VerbAlreadyRegisteredError",
-    "VerbParallelizationError",
-    "WorkflowError",
-    "NoVerbInputsProvidedError",
-    "VerbHasMultipleDefaultInputsError",
-    "VerbHasMultipleDefaultOthersError",
-    "VerbOperationNotSupportedError",
-    "NodeNotVisitedError",
-    "WorkflowInvalidInputError",
+    "TableMetadata",
+    "NoopVerbCallbacks",
+    "VerbCallbacks",
 ]

python/datashaper/datashaper/constants.py

@@ -0,0 +1,8 @@
+#
+# Copyright (c) Microsoft. All rights reserved.
+# Licensed under the MIT license. See LICENSE file in the project.
+#
+"""Datashaper constants."""
+
+DEFAULT_INPUT_NAME = "source"
+DEFAULT_OUTPUT_NAME = "result"