cellarr-array 0.1.0__py3-none-any.whl → 0.2.0__py3-none-any.whl

cellarr_array/utils/mock.py

@@ -0,0 +1,167 @@
+import shutil
+from typing import Dict, Optional
+
+import numpy as np
+import scipy.sparse as sp
+import tiledb
+
+from ..core import DenseCellArray, SparseCellArray
+from ..core.helpers import CellArrConfig, create_cellarray
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+def generate_tiledb_dense_array(
+    uri: str,
+    rows: int,
+    cols: int,
+    attr_name: str = "data",
+    attr_dtype: np.dtype = np.float32,
+    chunk_size: int = 1000,
+    tiledb_config: Optional[Dict] = None,
+):
+    """Generates a dense TileDB array and fills it with random float32 data.
+
+    Args:
+        uri:
+            URI for the new TileDB array.
+
+        rows:
+            Number of rows.
+
+        cols:
+            Number of columns (features).
+
+        attr_name:
+            Name of the attribute.
+
+        attr_dtype:
+            Data type of the attribute.
+
+        chunk_size:
+            Number of rows to write per batch.
+
+        tiledb_config:
+            TileDB context configuration.
+    """
+    if tiledb.array_exists(uri):
+        print(f"Array {uri} already exists. Removing.")
+        shutil.rmtree(uri)
+
+    print(f"Creating dense array at '{uri}' with shape ({rows}, {cols})")
+    cfg = CellArrConfig(ctx_config=tiledb_config if tiledb_config else {})
+
+    create_cellarray(
+        uri=uri,
+        shape=(rows, cols),
+        attr_dtype=attr_dtype,
+        sparse=False,
+        dim_names=["rows", "cols"],
+        attr_name=attr_name,
+        # config=cfg
+    )
+
+    ctx = tiledb.Ctx(cfg.ctx_config) if cfg.ctx_config else None
+    arr_writer = DenseCellArray(uri=uri, attr=attr_name, mode="w", config_or_context=ctx)
+
+    print("shape of writer", arr_writer.shape)
+
+    print(f"Writing data to dense array '{uri}'...")
+    for i in range(0, rows, chunk_size):
+        end_row = min(i + chunk_size, rows)
+        num_chunk_rows = end_row - i
+        data_chunk = np.random.rand(num_chunk_rows, cols).astype(attr_dtype)
+        print(i, end_row, num_chunk_rows, data_chunk.shape)
+        arr_writer.write_batch(data_chunk, start_row=i)
+        if (i // chunk_size) % 10 == 0:
+            print(f"  Dense write: {end_row}/{rows} rows written.")
+
+    print(f"Finished writing to dense array '{uri}'.")
+
+
+def generate_tiledb_sparse_array(
+    uri: str,
+    rows: int,
+    cols: int,
+    density: float = 0.01,
+    attr_name: str = "data",
+    attr_dtype: np.dtype = np.float32,
+    chunk_size: int = 1000,
+    tiledb_config: Optional[Dict] = None,
+    sparse_format_to_write="coo",
+):
+    """Generates a sparse TileDB array and fills it with random float32 data.
+
+    Args:
+        uri:
+            URI for the new TileDB array.
+
+        rows:
+            Number of rows.
+
+        cols:
+            Number of columns (features).
+
+        density:
+            Density of the sparse matrix.
+
+        attr_name:
+            Name of the attribute.
+
+        attr_dtype:
+            Data type of the attribute.
+
+        chunk_size:
+            Number of rows to generate and write per batch.
+
+        tiledb_configs:
+            TileDB context configuration.
+
+        sparse_format_to_write:
+            Scipy sparse format to use for generating chunks ('coo', 'csr', 'csc').
+
+    """
+    if tiledb.array_exists(uri):
+        print(f"Array {uri} already exists. Removing.")
+        shutil.rmtree(uri)
+
+    print(f"Creating sparse array at '{uri}' with shape ({rows}, {cols}), density ~{density}")
+    cfg = CellArrConfig(ctx_config=tiledb_config if tiledb_config else {})
+    create_cellarray(
+        uri=uri,
+        shape=(rows, cols),
+        attr_dtype=attr_dtype,
+        sparse=True,
+        dim_names=["rows", "cols"],
+        attr_name=attr_name,
+        # config=cfg
+    )
+
+    ctx = tiledb.Ctx(cfg.ctx_config) if cfg.ctx_config else None
+    arr_writer = SparseCellArray(
+        uri=uri,
+        attr=attr_name,
+        mode="w",
+        config_or_context=ctx,
+    )
+
+    print(f"Writing data to sparse array '{uri}'...")
+    for i in range(0, rows, chunk_size):
+        end_row = min(i + chunk_size, rows)
+        num_chunk_rows = end_row - i
+        if num_chunk_rows <= 0:
+            continue
+
+        data_chunk_scipy = sp.random(
+            num_chunk_rows, cols, density=density, format=sparse_format_to_write, dtype=attr_dtype
+        )
+
+        if data_chunk_scipy.nnz > 0:
+            arr_writer.write_batch(data_chunk_scipy, start_row=i)
+
+        if (i // chunk_size) % 10 == 0:
+            print(f"  Sparse write: {end_row}/{rows} rows processed for writing.")
+
+    print(f"Finished writing to sparse array '{uri}'.")

{cellarr_array-0.1.0.dist-info → cellarr_array-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cellarr-array
-Version: 0.1.0
+Version: 0.2.0
 Summary: Base class for handling TileDB backed arrays.
 Home-page: https://github.com/cellarr/cellarr-array
 Author: Jayaram Kancherla
@@ -16,10 +16,13 @@ Requires-Dist: importlib-metadata; python_version < "3.8"
 Requires-Dist: tiledb
 Requires-Dist: numpy
 Requires-Dist: scipy
+Provides-Extra: optional
+Requires-Dist: torch; extra == "optional"
 Provides-Extra: testing
 Requires-Dist: setuptools; extra == "testing"
 Requires-Dist: pytest; extra == "testing"
 Requires-Dist: pytest-cov; extra == "testing"
+Requires-Dist: torch; extra == "testing"
 Dynamic: license-file
 
 [![PyPI-Server](https://img.shields.io/pypi/v/cellarr-array.svg)](https://pypi.org/project/cellarr-array/)

cellarr_array-0.2.0.dist-info/RECORD

@@ -0,0 +1,19 @@
+cellarr_array/__init__.py,sha256=coBnoCq1_cv6FnnbowNt6wEIDfVl2GlGTkjnveP-8C4,707
+cellarr_array/core/__init__.py,sha256=fvM-FEiDn8TKDbHxhhzp9FXZFNovFwvIUSY6SpLQRdk,98
+cellarr_array/core/base.py,sha256=3FlhzZSh4ePz3Zm_dU8XNXJ6xgs7rKGi5HgCVWJLhXY,13458
+cellarr_array/core/dense.py,sha256=LODRH4utpKs8xhT79Q2-nRiam_s68_a0qPj0unEM7rg,3940
+cellarr_array/core/helpers.py,sha256=Z_2zRUULFTm7Lo9EpkGvIeRraP6XNDRB-o3rh9ChKQQ,7856
+cellarr_array/core/sparse.py,sha256=XifIWhbTRAQ6qL096th-dCkqscNRwFZuTd7uaRf9aGM,8844
+cellarr_array/dataloaders/__init__.py,sha256=U-MfwC2K84OIXT75in41fe_wvoxjUC5Krb5zICQn_O8,245
+cellarr_array/dataloaders/denseloader.py,sha256=JYJlbuX5My64iIPW_-nlPFkNIezxL3Z3mkwInS3hH9M,7291
+cellarr_array/dataloaders/iterabledataloader.py,sha256=lR2T1YatyBlDM5Sy_75B7_8ORiWfn3cp4q48Oujwf-c,11916
+cellarr_array/dataloaders/sparseloader.py,sha256=V_eKw-Z_CNxHP8c2BN3sOuuv6RPiWBzRfW1BYLhNaQc,7962
+cellarr_array/dataloaders/utils.py,sha256=buJ87x1YBTt5-nZoy_I5j6ko1lVlHdiGpQCusdLoRLI,600
+cellarr_array/utils/__init__.py,sha256=DM5jeUMbxbRzTu2QCjpLlrTQ5uionF887S_7i6_952U,177
+cellarr_array/utils/config.py,sha256=67zBxpYY9N_v6TMdyljUIZmckbwOBcuLC99aJooGmfA,2917
+cellarr_array/utils/mock.py,sha256=7GyCbtM7u94pm7qhjsPRSO2IWYLmd4UrjyvLnQtMMkc,4579
+cellarr_array-0.2.0.dist-info/licenses/LICENSE.txt,sha256=JUlHIfWcRe_MZop18pQvMIPLKSSPz3XQ06ASHuW5Wh8,1076
+cellarr_array-0.2.0.dist-info/METADATA,sha256=NbNM3Gyu4t2f1odp26QiUutfic0IdnagSCnJUn9NLSs,4228
+cellarr_array-0.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cellarr_array-0.2.0.dist-info/top_level.txt,sha256=oErp0D8ABZV-QPtTiXT8_F2z36Ic7ykuDg_1Y84HLZM,14
+cellarr_array-0.2.0.dist-info/RECORD,,

{cellarr_array-0.1.0.dist-info → cellarr_array-0.2.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.7.1)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

cellarr_array-0.1.0.dist-info/RECORD

@@ -1,11 +0,0 @@
-cellarr_array/__init__.py,sha256=iCU5zmXXmTwk-VuwrTdVl5STRAL2xeYpq05fL9_bW6w,781
-cellarr_array/cellarray_base.py,sha256=CSYsA_Ra-RcwsyHzwayL-w10EhpbIC3u7ZAbyQMO6ks,13451
-cellarr_array/cellarray_dense.py,sha256=skunPy_WyOMuS_3SxcAW_gm8d5FiWeV7ZCQp4HLRUUY,3958
-cellarr_array/cellarray_sparse.py,sha256=YYZymvWGDG1c2EeOLMBPP5_u4qM8uhxyWJY6PnFWMVo,9112
-cellarr_array/config.py,sha256=67zBxpYY9N_v6TMdyljUIZmckbwOBcuLC99aJooGmfA,2917
-cellarr_array/helpers.py,sha256=eIeymmvY4KZ-cAiROo3DcYYzP39NQBj-4Nrba9rrEKQ,6491
-cellarr_array-0.1.0.dist-info/licenses/LICENSE.txt,sha256=JUlHIfWcRe_MZop18pQvMIPLKSSPz3XQ06ASHuW5Wh8,1076
-cellarr_array-0.1.0.dist-info/METADATA,sha256=ELBRCXkEyxhPeGHlA62i2QIzz7yYlLUSy7bfOe6aAdE,4120
-cellarr_array-0.1.0.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
-cellarr_array-0.1.0.dist-info/top_level.txt,sha256=oErp0D8ABZV-QPtTiXT8_F2z36Ic7ykuDg_1Y84HLZM,14
-cellarr_array-0.1.0.dist-info/RECORD,,