CytoTable 0.0.5__py3-none-any.whl → 0.0.7__py3-none-any.whl

cytotable/__init__.py

@@ -3,7 +3,7 @@ __init__.py for cytotable
 """
 
 # note: version data is maintained by poetry-dynamic-versioning (do not edit)
-__version__ = "0.0.5"
+__version__ = "0.0.7"
 
 from .convert import convert
 from .exceptions import (

cytotable/convert.py

@@ -2,7 +2,6 @@
 CytoTable: convert - transforming data for use with pyctyominer.
 """
 
-
 import itertools
 import logging
 import uuid
@@ -349,6 +348,8 @@ def _source_chunk_to_parquet(
                 table=ddb_reader.execute(
                     f"""
                     {base_query}
+                    /* order by all columns for deterministic output */
+                    ORDER BY ALL
                     LIMIT {chunk_size} OFFSET {offset}
                     """
                 ).arrow(),
@@ -751,6 +752,7 @@ def _join_source_chunk(
         result = ddb_reader.execute(
             f"""
                 {joins}
+                {"ORDER BY ALL" if "ORDER BY" not in joins.upper() else ""}
                 LIMIT {chunk_size} OFFSET {offset}
                 """
         ).arrow()
@@ -841,19 +843,6 @@ def _concat_join_sources(
     if pathlib.Path(dest_path).is_dir():
         shutil.rmtree(path=dest_path)
 
-    # write the concatted result as a parquet file
-    _write_parquet_table_with_metadata(
-        table=pa.concat_tables(
-            tables=[
-                parquet.read_table(
-                    table_path, memory_map=CYTOTABLE_ARROW_USE_MEMORY_MAPPING
-                )
-                for table_path in join_sources
-            ]
-        ),
-        where=dest_path,
-    )
-
     # build a parquet file writer which will be used to append files
     # as a single concatted parquet file, referencing the first file's schema
     # (all must be the same schema)

cytotable/presets.py

@@ -39,15 +39,15 @@ config = {
             SELECT
                 *
             FROM
-                Image_Filtered AS image
-            LEFT JOIN read_parquet('cytoplasm.parquet') AS cytoplasm ON
-                cytoplasm.Metadata_ImageNumber = image.Metadata_ImageNumber
+                read_parquet('cytoplasm.parquet') AS cytoplasm
             LEFT JOIN read_parquet('cells.parquet') AS cells ON
                 cells.Metadata_ImageNumber = cytoplasm.Metadata_ImageNumber
                 AND cells.Metadata_ObjectNumber = cytoplasm.Metadata_Cytoplasm_Parent_Cells
             LEFT JOIN read_parquet('nuclei.parquet') AS nuclei ON
                 nuclei.Metadata_ImageNumber = cytoplasm.Metadata_ImageNumber
                 AND nuclei.Metadata_ObjectNumber = cytoplasm.Metadata_Cytoplasm_Parent_Nuclei
+            LEFT JOIN Image_Filtered AS image ON
+                image.Metadata_ImageNumber = cytoplasm.Metadata_ImageNumber
             """,
     },
     "cellprofiler_sqlite": {
@@ -85,15 +85,15 @@ config = {
             SELECT
                 *
             FROM
-                Per_Image_Filtered AS per_image
-            LEFT JOIN read_parquet('per_cytoplasm.parquet') AS per_cytoplasm ON
-                per_cytoplasm.Metadata_ImageNumber = per_image.Metadata_ImageNumber
+                read_parquet('per_cytoplasm.parquet') AS per_cytoplasm
             LEFT JOIN read_parquet('per_cells.parquet') AS per_cells ON
                 per_cells.Metadata_ImageNumber = per_cytoplasm.Metadata_ImageNumber
                 AND per_cells.Cells_Number_Object_Number = per_cytoplasm.Cytoplasm_Parent_Cells
             LEFT JOIN read_parquet('per_nuclei.parquet') AS per_nuclei ON
                 per_nuclei.Metadata_ImageNumber = per_cytoplasm.Metadata_ImageNumber
                 AND per_nuclei.Nuclei_Number_Object_Number = per_cytoplasm.Cytoplasm_Parent_Nuclei
+            LEFT JOIN  Per_Image_Filtered AS per_image ON
+                per_image.Metadata_ImageNumber = per_cytoplasm.Metadata_ImageNumber
             """,
     },
     "cellprofiler_sqlite_pycytominer": {
@@ -136,15 +136,15 @@ config = {
             SELECT
                 *
             FROM
-                Per_Image_Filtered AS per_image
-            LEFT JOIN read_parquet('per_cytoplasm.parquet') AS per_cytoplasm ON
-                per_cytoplasm.Metadata_ImageNumber = per_image.Metadata_ImageNumber
+                read_parquet('per_cytoplasm.parquet') AS per_cytoplasm
             LEFT JOIN read_parquet('per_cells.parquet') AS per_cells ON
                 per_cells.Metadata_ImageNumber = per_cytoplasm.Metadata_ImageNumber
                 AND per_cells.Metadata_Cells_Number_Object_Number = per_cytoplasm.Metadata_Cytoplasm_Parent_Cells
             LEFT JOIN read_parquet('per_nuclei.parquet') AS per_nuclei ON
                 per_nuclei.Metadata_ImageNumber = per_cytoplasm.Metadata_ImageNumber
                 AND per_nuclei.Metadata_Nuclei_Number_Object_Number = per_cytoplasm.Metadata_Cytoplasm_Parent_Nuclei
+            LEFT JOIN Per_Image_Filtered AS per_image ON
+                per_image.Metadata_ImageNumber = per_cytoplasm.Metadata_ImageNumber
             """,
     },
     "cell-health-cellprofiler-to-cytominer-database": {
@@ -190,10 +190,7 @@ config = {
             SELECT
                 *
             FROM
-                Image_Filtered AS image
-            LEFT JOIN read_parquet('cytoplasm.parquet') AS cytoplasm ON
-                cytoplasm.Metadata_TableNumber = image.Metadata_TableNumber
-                AND cytoplasm.Metadata_ImageNumber = image.Metadata_ImageNumber
+                read_parquet('cytoplasm.parquet') AS cytoplasm
             LEFT JOIN read_parquet('cells.parquet') AS cells ON
                 cells.Metadata_TableNumber = cytoplasm.Metadata_TableNumber
                 AND cells.Metadata_ImageNumber = cytoplasm.Metadata_ImageNumber
@@ -202,6 +199,9 @@ config = {
                 nuclei.Metadata_TableNumber = cytoplasm.Metadata_TableNumber
                 AND nuclei.Metadata_ImageNumber = cytoplasm.Metadata_ImageNumber
                 AND nuclei.Nuclei_ObjectNumber = cytoplasm.Metadata_Cytoplasm_Parent_Nuclei
+            LEFT JOIN  Image_Filtered AS image ON
+                image.Metadata_TableNumber = cytoplasm.Metadata_TableNumber
+                AND image.Metadata_ImageNumber = cytoplasm.Metadata_ImageNumber
         """,
     },
     "in-carta": {

cytotable/utils.py

@@ -257,7 +257,12 @@ def _sqlite_mixed_type_query_to_parquet(
 
         # perform the select using the cases built above and using chunksize + offset
         cursor.execute(
-            f'SELECT {", ".join(query_parts)} FROM {table_name} LIMIT {chunk_size} OFFSET {offset};'
+            f"""
+            SELECT {', '.join(query_parts)}
+            FROM {table_name}
+            ORDER BY {', '.join([col['column_name'] for col in column_info])}
+            LIMIT {chunk_size} OFFSET {offset};
+            """
         )
         # collect the results and include the column name with values
         results = [

{cytotable-0.0.5.dist-info → cytotable-0.0.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: CytoTable
-Version: 0.0.5
+Version: 0.0.7
 Summary: Transform CellProfiler and DeepProfiler data for processing image-based profiling readouts with Pycytominer and other Cytomining tools.
 Home-page: https://github.com/cytomining/CytoTable
 License: BSD-3-Clause License
@@ -14,10 +14,14 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Dist: cloudpathlib[all] (>=0.15.0,<0.16.0)
-Requires-Dist: duckdb (>=0.8.0,<0.10.0)
+Requires-Dist: cloudpathlib[all] (>=0.18.0,<0.19.0)
+Requires-Dist: duckdb (>=0.10.1)
+Requires-Dist: numpy (<=1.24.4) ; python_version < "3.12"
+Requires-Dist: numpy (>=1.26.0) ; python_version >= "3.12"
 Requires-Dist: parsl (>=2023.9.25)
 Requires-Dist: pyarrow (>=13.0.0)
+Requires-Dist: scipy (<1.12.0) ; python_version < "3.9"
+Requires-Dist: scipy (>=1.12.0,<2.0.0) ; python_version >= "3.9"
 Project-URL: Documentation, https://cytomining.github.io/CytoTable/
 Project-URL: Repository, https://github.com/cytomining/CytoTable
 Description-Content-Type: text/markdown

cytotable-0.0.7.dist-info/RECORD

@@ -0,0 +1,11 @@
+cytotable/__init__.py,sha256=3xspHDpARY8WLv1EQOR-RWnqpadANuo2uK_MMKnFD8k,315
+cytotable/constants.py,sha256=w_AUm_fKKXeZjnZxbHf-dxq7NN7BkvCWbkGK24sfzLw,1872
+cytotable/convert.py,sha256=EjEZpWvm3oPgDx1dKlfHETgs52blL79dBzfhcPOOK6o,51771
+cytotable/exceptions.py,sha256=NhkMswjCB0HeVHqlLXzBlyHunQIp_4eBFmyAPu0Nf30,482
+cytotable/presets.py,sha256=HSrINU0XzF4i4zxjNMMw9F0rRxgr6mm3V7Gh_Wb-uFI,10773
+cytotable/sources.py,sha256=zvkYMJOTBJVgFFSbkfpjFMwlOu4ifhxYALh71NGKEuM,11283
+cytotable/utils.py,sha256=E5r1Vk3eaCB42JFquQHpGQXdAy97kGl-YiapmOkURwA,14476
+cytotable-0.0.7.dist-info/LICENSE,sha256=lPK3PtUMP-f1EOFMUr8h3FvuMh89x249Hvm4lchTsv0,1528
+cytotable-0.0.7.dist-info/METADATA,sha256=U1kwsaRSVKB8iwlSw3iP3tLDO2LeKT9xjG1ctiWnHg0,3420
+cytotable-0.0.7.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+cytotable-0.0.7.dist-info/RECORD,,

cytotable-0.0.5.dist-info/RECORD

@@ -1,11 +0,0 @@
-cytotable/__init__.py,sha256=4iHTG5PYcCA4HGgbNkccsTb-3iDCVMeY1UymUHz221w,315
-cytotable/constants.py,sha256=w_AUm_fKKXeZjnZxbHf-dxq7NN7BkvCWbkGK24sfzLw,1872
-cytotable/convert.py,sha256=ORn2MmDmBUBEHDelDHc_j4J3LQgCEflXyzLouvf5h6Y,51971
-cytotable/exceptions.py,sha256=NhkMswjCB0HeVHqlLXzBlyHunQIp_4eBFmyAPu0Nf30,482
-cytotable/presets.py,sha256=SYZXh0-eK-2VRRd8I30GCQcZ4wDMmhGes8KdDsxpFqg,10771
-cytotable/sources.py,sha256=zvkYMJOTBJVgFFSbkfpjFMwlOu4ifhxYALh71NGKEuM,11283
-cytotable/utils.py,sha256=9zqLf_95-phH6IdsDgpK3g3NkDG4odx0NUWogQDs31k,14344
-cytotable-0.0.5.dist-info/LICENSE,sha256=lPK3PtUMP-f1EOFMUr8h3FvuMh89x249Hvm4lchTsv0,1528
-cytotable-0.0.5.dist-info/METADATA,sha256=dQG8qhDjbrPSk0k-KWZjngaUB1Ry2kzOnb_ndtXW2qE,3189
-cytotable-0.0.5.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-cytotable-0.0.5.dist-info/RECORD,,