atdata 0.1.2a4__tar.gz → 0.1.2b1__tar.gz

{atdata-0.1.2a4 → atdata-0.1.2b1}/PKG-INFO

@@ -1,13 +1,16 @@
 Metadata-Version: 2.4
 Name: atdata
-Version: 0.1.2a4
+Version: 0.1.2b1
 Summary: A loose federation of distributed, typed datasets
 Author-email: Maxine Levesque <hello@maxine.science>
 License-File: LICENSE
 Requires-Python: >=3.12
+Requires-Dist: fastparquet>=2024.11.0
 Requires-Dist: msgpack>=1.1.2
 Requires-Dist: numpy>=2.3.4
 Requires-Dist: ormsgpack>=1.11.0
+Requires-Dist: pandas>=2.3.3
+Requires-Dist: tqdm>=4.67.1
 Requires-Dist: webdataset>=1.0.2
 Description-Content-Type: text/markdown
 

{atdata-0.1.2a4 → atdata-0.1.2b1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "atdata"
-version = "0.1.2a4"
+version = "0.1.2b1"
 description = "A loose federation of distributed, typed datasets"
 readme = "README.md"
 authors = [
@@ -8,9 +8,12 @@ authors = [
 ]
 requires-python = ">=3.12"
 dependencies = [
+    "fastparquet>=2024.11.0",
     "msgpack>=1.1.2",
     "numpy>=2.3.4",
     "ormsgpack>=1.11.0",
+    "pandas>=2.3.3",
+    "tqdm>=4.67.1",
     "webdataset>=1.0.2",
 ]
 

{atdata-0.1.2a4 → atdata-0.1.2b1}/src/atdata/__init__.py

@@ -10,5 +10,10 @@ from .dataset import (
     packable,
 )
 
+from .lens import (
+    Lens,
+    lens,
+)
+
 
 #

{atdata-0.1.2a4 → atdata-0.1.2b1}/src/atdata/dataset.py

@@ -5,21 +5,29 @@
 
 import webdataset as wds
 
-import functools
-from dataclasses import dataclass
+from pathlib import Path
 import uuid
-
-import numpy as np
-
+import functools
+from dataclasses import (
+    dataclass,
+    asdict,
+)
 from abc import (
     ABC,
     abstractmethod,
 )
+
+from tqdm import tqdm
+import numpy as np
+import pandas as pd
+
 from typing import (
     Any,
     Optional,
     Dict,
     Sequence,
+    Iterable,
+    Callable,
     #
     Self,
     Generic,
@@ -45,9 +53,14 @@ from . import _helpers as eh
 ##
 # Typing help
 
+Pathlike = str | Path
+
 WDSRawSample: TypeAlias = Dict[str, Any]
 WDSRawBatch: TypeAlias = Dict[str, Any]
 
+SampleExportRow: TypeAlias = Dict[str, Any]
+SampleExportMap: TypeAlias = Callable[['PackableSample'], SampleExportRow]
+
 
 ##
 # Main base classes
@@ -94,6 +107,7 @@ def _make_packable( x ):
         return eh.array_to_bytes( x )
     return x
 
+@dataclass
 class PackableSample( ABC ):
     """A sample that can be packed and unpacked with msgpack"""
 
@@ -235,6 +249,7 @@ class Dataset( Generic[ST] ):
     @property
     def sample_type( self ) -> Type:
         """The type of each returned sample from this `Dataset`'s iterator"""
+        # TODO Figure out why linting fails here
         return self.__orig_class__.__args__[0]
     @property
     def batch_type( self ) -> Type:
@@ -286,7 +301,7 @@ class Dataset( Generic[ST] ):
     
     def ordered( self,
                 batch_size: int | None = 1,
-            ) -> wds.DataPipeline:
+            ) -> Iterable[ST]:
         """Iterate over the dataset in order
         
         Args:
@@ -325,7 +340,7 @@ class Dataset( Generic[ST] ):
                 buffer_shards: int = 100,
                 buffer_samples: int = 10_000,
                 batch_size: int | None = 1,
-            ) -> wds.DataPipeline:
+            ) -> Iterable[ST]:
         """Iterate over the dataset in random order
         
         Args:
@@ -366,6 +381,64 @@ class Dataset( Generic[ST] ):
             wds.batched( batch_size ),
             wds.map( self.wrap_batch ),
         )
+    
+    # TODO Rewrite to eliminate `pandas` dependency directly calling
+    # `fastparquet`
+    def to_parquet( self, path: Pathlike,
+                sample_map: Optional[SampleExportMap] = None,
+                maxcount: Optional[int] = None,
+                **kwargs,
+            ):
+        """Save dataset contents to a `parquet` file at `path`
+
+        `kwargs` sent to `pandas.to_parquet`
+        """
+        ##
+
+        # Normalize args
+        path = Path( path )
+        if sample_map is None:
+            sample_map = asdict
+        
+        verbose = kwargs.get( 'verbose', False )
+
+        it = self.ordered( batch_size = None )
+        if verbose:
+            it = tqdm( it )
+
+        #
+
+        if maxcount is None:
+            # Load and save full dataset
+            df = pd.DataFrame( [ sample_map( x )
+                                 for x in self.ordered( batch_size = None ) ] )
+            df.to_parquet( path, **kwargs )
+        
+        else:
+            # Load and save dataset in segments of size `maxcount`
+
+            cur_segment = 0
+            cur_buffer = []
+            path_template = (path.parent / f'{path.stem}-%06d.{path.suffix}').as_posix()
+
+            for x in self.ordered( batch_size = None ):
+                cur_buffer.append( sample_map( x ) )
+                
+                if len( cur_buffer ) >= maxcount:
+                    # Write current segment
+                    cur_path = path_template.format( cur_segment )
+                    df = pd.DataFrame( cur_buffer )
+                    df.to_parquet( cur_path, **kwargs )
+
+                    cur_segment += 1
+                    cur_buffer = []
+                
+            if len( cur_buffer ) > 0:
+                # Write one last segment with remainder
+                cur_path = path_template.format( cur_segment )
+                df = pd.DataFrame( cur_buffer )
+                df.to_parquet( cur_path, **kwargs )
+
 
     # Implemented by specific subclasses
 
@@ -390,18 +463,18 @@ class Dataset( Generic[ST] ):
         
         return self.sample_type.from_bytes( sample['msgpack'] )
     
-        try:
-            assert type( sample ) == dict
-            return cls.sample_class( **{
-                k: v
-                for k, v in sample.items() if k != '__key__'
-            } )
+        # try:
+        #     assert type( sample ) == dict
+        #     return cls.sample_class( **{
+        #         k: v
+        #         for k, v in sample.items() if k != '__key__'
+        #     } )
         
-        except Exception as e:
-            # Sample constructor failed -- revert to default
-            return AnySample(
-                value = sample,
-            )
+        # except Exception as e:
+        #     # Sample constructor failed -- revert to default
+        #     return AnySample(
+        #         value = sample,
+        #     )
 
     def wrap_batch( self, batch: WDSRawBatch ) -> SampleBatch[ST]:
         """Wrap a `batch` of samples into the appropriate dataset-specific type
@@ -449,6 +522,9 @@ def packable( cls ):
     
     ##
 
+    class_name = cls.__name__
+    class_annotations = cls.__annotations__
+
     # Add in dataclass niceness to original class
     as_dataclass = dataclass( cls )
 
@@ -458,8 +534,9 @@ def packable( cls ):
         def __post_init__( self ):
             return PackableSample.__post_init__( self )
     
-    as_packable.__name__ = cls.__name__
-    as_packable.__annotations__ = cls.__annotations__
+    # TODO This doesn't properly carry over the original
+    as_packable.__name__ = class_name
+    as_packable.__annotations__ = class_annotations
 
     ##
 

atdata-0.1.2b1/src/atdata/lens.py

@@ -0,0 +1,122 @@
+"""Lenses between typed datasets"""
+
+##
+# Imports
+
+from .dataset import PackableSample
+
+import functools
+import inspect
+
+from typing import (
+    TypeAlias,
+    Type,
+    TypeVar,
+    Tuple,
+    Dict,
+    Callable,
+    Optional,
+    Generic,
+)
+
+
+##
+# Typing helpers
+
+DatasetType: TypeAlias = Type[PackableSample]
+LensSignature: TypeAlias = Tuple[DatasetType, DatasetType]
+
+S = TypeVar( 'S', bound = PackableSample )
+V = TypeVar( 'V', bound = PackableSample )
+type LensGetter[S, V] = Callable[[S], V]
+type LensPutter[S, V] = Callable[[V, S], S]
+
+
+##
+# Shortcut decorators
+
+class Lens( Generic[S, V] ):
+    """TODO"""
+
+    def __init__( self, get: LensGetter[S, V],
+                put: Optional[LensPutter[S, V]] = None
+            ) -> None:
+        """TODO"""
+        ##
+
+        # Update
+        functools.update_wrapper( self, get )
+
+        # Store the getter
+        self._getter = get
+        
+        # Determine and store the putter
+        if put is None:
+            # Trivial putter does not update the source
+            def _trivial_put( v: V, s: S ) -> S:
+                return s
+            put = _trivial_put
+        
+        self._putter = put
+
+        # Register this lens for this type signature
+    
+        sig = inspect.signature( get )
+        input_types = list( sig.parameters.values() )
+        assert len( input_types ) == 1, \
+            'Wrong number of input args for lens: should only have one'
+        
+        input_type = input_types[0].annotation
+        output_type = sig.return_annotation
+
+        _registered_lenses[(input_type, output_type)] = self
+        print( _registered_lenses )
+    
+    #
+
+    def putter( self, put: LensPutter[S, V] ) -> LensPutter[S, V]:
+        """TODO"""
+        ##
+        self._putter = put
+        return put
+    
+    def put( self, v: V, s: S ) -> S:
+        """TODO"""
+        return self._putter( v, s )
+
+    def get( self, s: S ) -> V:
+        """TODO"""
+        return self( s )
+
+    #
+    
+    def __call__( self, s: S ) -> V:
+        return self._getter( s )
+
+def lens( f: LensGetter[S, V] ) -> Lens[S, V]:
+    """Register the annotated function `f` as the getter of a sample lens"""
+    return Lens[S, V]( f )
+
+
+##
+# Global registration of used lenses
+
+_registered_lenses: Dict[LensSignature, Lens] = dict()
+"""TODO"""
+
+# def lens( f: LensPutter ) -> Lens:
+#     """Register the annotated function `f` as a sample lens"""
+#     ##
+    
+#     sig = inspect.signature( f )
+
+#     input_types = list( sig.parameters.values() )
+#     output_type = sig.return_annotation
+    
+#     _registered_lenses[]
+
+#     f.lens = Lens(
+
+#     )
+
+#     return f

{atdata-0.1.2a4 → atdata-0.1.2b1}/tests/test_dataset.py

@@ -59,6 +59,7 @@ test_cases = [
             'value': 1024.768,
         },
         'sample_wds_stem': 'basic_test',
+        'test_parquet': True,
     },
     {
         'SampleType': NumpyTestSample,
@@ -68,6 +69,7 @@ test_cases = [
             'image': np.random.randn( 1024, 1024 ),
         },
         'sample_wds_stem': 'numpy_test',
+        'test_parquet': False,
     },
     {
         'SampleType': BasicTestSampleDecorated,
@@ -77,6 +79,7 @@ test_cases = [
             'value': 1024.768,
         },
         'sample_wds_stem': 'basic_test_decorated',
+        'test_parquet': True,
     },
     {
         'SampleType': NumpyTestSampleDecorated,
@@ -86,6 +89,7 @@ test_cases = [
             'image': np.random.randn( 1024, 1024 ),
         },
         'sample_wds_stem': 'numpy_test_decorated',
+        'test_parquet': False,
     },
 ]
 
@@ -323,5 +327,117 @@ def test_wds(
     assert iterations_run == n_iterate, \
         "Only found {iterations_run} samples, not {n_iterate}"
 
+#
+
+@pytest.mark.parametrize(
+    ('SampleType', 'sample_data', 'sample_wds_stem', 'test_parquet'),
+    [ (
+        case['SampleType'],
+        case['sample_data'],
+        case['sample_wds_stem'],
+        case['test_parquet']
+      )
+      for case in test_cases ]
+)
+def test_create_sample(
+            SampleType: Type[atdata.PackableSample],
+            sample_data: atds.MsgpackRawSample,
+            sample_wds_stem: str,
+            test_parquet: bool,
+            tmp_path
+        ):
+    """Test our ability to export a dataset to `parquet` format"""
+
+    # Skip irrelevant test cases
+    if not test_parquet:
+        return
+
+    ## Testing hyperparameters
+
+    n_copies_dataset = 1_000
+    n_per_file = 100
+
+    ## Start out by writing tar dataset
+
+    wds_filename = (tmp_path / f'{sample_wds_stem}.tar').as_posix()
+    with wds.TarWriter( wds_filename ) as sink:
+        for _ in range( n_copies_dataset ):
+            new_sample = SampleType.from_data( sample_data )
+            sink.write( new_sample.as_wds )
+    
+    ## Now export to `parquet`
+
+    dataset = atdata.Dataset[SampleType]( wds_filename )
+    parquet_filename = tmp_path / f'{sample_wds_stem}.parquet'
+    dataset.to_parquet( parquet_filename )
+
+    ## Double-check our `parquet` export
+    
+    # TODO
+
+def test_lens():
+    """Test a lens between sample types"""
+
+    # Set up the lens scenario
+
+    @atdata.packable
+    class Source:
+        name: str
+        age: int
+        height: float
+
+    @atdata.packable
+    class View:
+        name: str
+        height: float
+    
+    @atdata.lens
+    def polite( s: Source ) -> View:
+        return View(
+            name = s.name,
+            height = s.height,
+        )
+    
+    @polite.putter
+    def polite_update( v: View, s: Source ) -> Source:
+        return Source(
+            name = v.name,
+            height = v.height,
+            #
+            age = s.age,
+        )
+    
+    # Test with an example sample
+
+    test_source = Source(
+        name = 'Hello World',
+        age = 42,
+        height = 182.9,
+    )
+    correct_view = View(
+        name = test_source.name,
+        height = test_source.height,
+    )
+
+    test_view = polite( test_source )
+    assert test_view == correct_view, \
+        f'Incorrect lens behavior: {test_view}, and not {correct_view}'
+
+    # This lens should be well-behaved
+
+    update_view = View(
+        name = 'Now Taller',
+        height = 192.9,
+    )
+
+    x = polite( polite.put( update_view, test_source ) )
+    assert x == update_view, \
+        f'Violation of GetPut: {x} =/= {update_view}'
+    
+    y = polite.put( polite( test_source ), test_source )
+    assert y == test_source, \
+        f'Violation of PutGet: {y} =/= {test_source}'
+    
+    # TODO Test PutPut
 
 ##