CytoTable 0.0.8__py3-none-any.whl → 0.0.9__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__ = "0.0.8"
+__version__ = "0.0.9"
 
 from .convert import convert
 from .exceptions import (

cytotable/convert.py

@@ -46,11 +46,12 @@ def _get_table_columns_and_types(
     import pathlib
 
     import duckdb
+    from cloudpathlib import AnyPath
 
     from cytotable.utils import _duckdb_reader, _sqlite_mixed_type_query_to_parquet
 
     source_path = source["source_path"]
-    source_type = str(pathlib.Path(source_path).suffix).lower()
+    source_type = str(source_path.suffix).lower()
 
     # prepare the data source in the form of a duckdb query
     select_source = (
@@ -209,7 +210,7 @@ def _get_table_chunk_offsets(
     import pathlib
 
     import duckdb
-    from cloudpathlib import AnyPath
+    from cloudpathlib import AnyPath, CloudPath
 
     from cytotable.exceptions import NoInputDataException
     from cytotable.utils import _duckdb_reader
@@ -219,18 +220,9 @@ def _get_table_chunk_offsets(
     if source is not None:
         table_name = source["table_name"] if "table_name" in source.keys() else None
         source_path = source["source_path"]
-        source_type = str(pathlib.Path(source_path).suffix).lower()
+        source_type = str(source_path.suffix).lower()
 
         try:
-            # for csv's, check that we have more than one row (a header and data values)
-            if (
-                source_type == ".csv"
-                and sum(1 for _ in AnyPath(source_path).open("r")) <= 1
-            ):
-                raise NoInputDataException(
-                    f"Data file has 0 rows of values. Error in file: {source_path}"
-                )
-
             # gather the total rowcount from csv or sqlite data input sources
             with _duckdb_reader() as ddb_reader:
                 rowcount = int(
@@ -322,8 +314,8 @@ def _source_chunk_to_parquet(
 
     # attempt to build dest_path
     source_dest_path = (
-        f"{dest_path}/{str(pathlib.Path(source_group_name).stem).lower()}/"
-        f"{str(pathlib.Path(source['source_path']).parent.name).lower()}"
+        f"{dest_path}/{str(AnyPath(source_group_name).stem).lower()}/"
+        f"{str(source['source_path'].parent.name).lower()}"
     )
     pathlib.Path(source_dest_path).mkdir(parents=True, exist_ok=True)
 
@@ -364,11 +356,11 @@ def _source_chunk_to_parquet(
 
     # build output query and filepath base
     # (chunked output will append offset to keep output paths unique)
-    if str(AnyPath(source["source_path"]).suffix).lower() == ".csv":
+    if str(source["source_path"].suffix).lower() == ".csv":
         base_query = f"SELECT {select_columns} FROM read_csv_auto('{str(source['source_path'])}', header=TRUE, delim=',')"
         result_filepath_base = f"{source_dest_path}/{str(source['source_path'].stem)}"
 
-    elif str(AnyPath(source["source_path"]).suffix).lower() == ".sqlite":
+    elif str(source["source_path"].suffix).lower() == ".sqlite":
         base_query = f"SELECT {select_columns} FROM sqlite_scan('{str(source['source_path'])}', '{str(source['table_name'])}')"
         result_filepath_base = f"{source_dest_path}/{str(source['source_path'].stem)}.{source['table_name']}"
 
@@ -405,7 +397,7 @@ def _source_chunk_to_parquet(
         # to handle the mixed types
         if (
             "Mismatch Type Error" in str(e)
-            and str(AnyPath(source["source_path"]).suffix).lower() == ".sqlite"
+            and str(source["source_path"].suffix).lower() == ".sqlite"
         ):
             _write_parquet_table_with_metadata(
                 # here we use sqlite instead of duckdb to extract
@@ -817,6 +809,7 @@ def _join_source_chunk(
     exclude_meta_cols = [
         f"c NOT LIKE '{col}%'" for col in list(CYOTABLE_META_COLUMN_TYPES.keys())
     ]
+
     with _duckdb_reader() as ddb_reader:
         result = ddb_reader.execute(
             f"""
@@ -1114,7 +1107,7 @@ def _to_parquet(  # pylint: disable=too-many-arguments, too-many-locals
             else []
         ),
         **kwargs,
-    ).result()
+    )
 
     # expand the destination path
     expanded_dest_path = _expand_path(path=dest_path)

cytotable/presets.py

@@ -85,6 +85,54 @@ config = {
                 AND per_nuclei.Nuclei_Number_Object_Number = per_cytoplasm.Cytoplasm_Parent_Nuclei
             """,
     },
+    "cellprofiler_sqlite_cpg0016_jump": {
+        # version specifications using related references
+        "CONFIG_SOURCE_VERSION": {
+            "cellprofiler": "v4.0.0",
+        },
+        # names of source table compartments (for ex. cells.csv, etc.)
+        "CONFIG_NAMES_COMPARTMENTS": ("cells", "nuclei", "cytoplasm"),
+        # names of source table metadata (for ex. image.csv, etc.)
+        "CONFIG_NAMES_METADATA": ("image",),
+        # column names in any compartment or metadata tables which contain
+        # unique names to avoid renaming
+        "CONFIG_IDENTIFYING_COLUMNS": (
+            "ImageNumber",
+            "ObjectNumber",
+            "Metadata_Well",
+            "Metadata_Plate",
+            "Parent_Cells",
+            "Parent_Nuclei",
+        ),
+        # chunk size to use for join operations to help with possible performance issues
+        # note: this number is an estimate and is may need changes contingent on data
+        # and system used by this library.
+        "CONFIG_CHUNK_SIZE": 1000,
+        # compartment and metadata joins performed using DuckDB SQL
+        # and modified at runtime as needed
+        "CONFIG_JOINS": """
+            SELECT
+                image.Image_TableNumber,
+                image.Metadata_ImageNumber,
+                image.Metadata_Plate,
+                image.Metadata_Well,
+                image.Image_Metadata_Site,
+                image.Image_Metadata_Row,
+                cytoplasm.* EXCLUDE (Metadata_ImageNumber),
+                cells.* EXCLUDE (Metadata_ImageNumber),
+                nuclei.* EXCLUDE (Metadata_ImageNumber)
+            FROM
+                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.Cytoplasm_Parent_Cells
+            LEFT JOIN read_parquet('nuclei.parquet') AS nuclei ON
+                nuclei.Metadata_ImageNumber = cytoplasm.Metadata_ImageNumber
+                AND nuclei.Metadata_ObjectNumber = cytoplasm.Cytoplasm_Parent_Nuclei
+            LEFT JOIN read_parquet('image.parquet') AS image ON
+                image.Metadata_ImageNumber = cytoplasm.Metadata_ImageNumber
+            """,
+    },
     "cellprofiler_sqlite_pycytominer": {
         # version specifications using related references
         "CONFIG_SOURCE_VERSION": {

cytotable/sources.py

@@ -7,13 +7,11 @@ import pathlib
 from typing import Any, Dict, List, Optional, Union
 
 from cloudpathlib import AnyPath
-from parsl.app.app import join_app, python_app
 
+from cytotable.exceptions import NoInputDataException
 
-@python_app
-def _build_path(
-    path: Union[str, pathlib.Path, AnyPath], **kwargs
-) -> Union[pathlib.Path, AnyPath]:
+
+def _build_path(path: str, **kwargs) -> Union[pathlib.Path, AnyPath]:
     """
     Build a path client or return local path.
 
@@ -43,10 +41,9 @@ def _build_path(
     return processed_path
 
 
-@python_app
 def _get_source_filepaths(
     path: Union[pathlib.Path, AnyPath],
-    targets: List[str],
+    targets: Optional[List[str]] = None,
     source_datatype: Optional[str] = None,
 ) -> Dict[str, List[Dict[str, Any]]]:
     """
@@ -75,7 +72,7 @@ def _get_source_filepaths(
 
     if (targets is None or targets == []) and source_datatype is None:
         raise DatatypeException(
-            f"A source_datatype must be specified when using undefined compartments and metadata names."
+            "A source_datatype must be specified when using undefined compartments and metadata names."
         )
 
     # gathers files from provided path using compartments + metadata as a filter
@@ -87,9 +84,9 @@ def _get_source_filepaths(
         for subpath in (
             (path,)
             # used if the source path is a single file
-            if AnyPath(path).is_file()
+            if path.is_file()
             # iterates through a source directory
-            else (x for x in AnyPath(path).glob("**/*") if AnyPath(x).is_file())
+            else (x for x in path.glob("**/*") if x.is_file())
         )
         # ensure the subpaths meet certain specifications
         if (
@@ -129,7 +126,8 @@ def _get_source_filepaths(
                     .arrow()["table_name"]
                     .to_pylist()
                     # make sure the table names match with compartment + metadata names
-                    if any(target.lower() in table_name.lower() for target in targets)
+                    if targets is not None
+                    and any(target.lower() in table_name.lower() for target in targets)
                 ]
             else:
                 # if we don't have sqlite source, append the existing element
@@ -181,7 +179,6 @@ def _get_source_filepaths(
     return grouped_sources
 
 
-@python_app
 def _infer_source_datatype(
     sources: Dict[str, List[Dict[str, Any]]], source_datatype: Optional[str] = None
 ) -> str:
@@ -230,7 +227,6 @@ def _infer_source_datatype(
     return source_datatype
 
 
-@python_app
 def _filter_source_filepaths(
     sources: Dict[str, List[Dict[str, Any]]], source_datatype: str
 ) -> Dict[str, List[Dict[str, Any]]]:
@@ -260,12 +256,45 @@ def _filter_source_filepaths(
             if file["source_path"].stat().st_size > 0
             # ensure the datatype matches the source datatype
             and file["source_path"].suffix == f".{source_datatype}"
+            and _file_is_more_than_one_line(path=file["source_path"])
         ]
         for filegroup, files in sources.items()
     }
 
 
-@join_app
+def _file_is_more_than_one_line(path: Union[pathlib.Path, AnyPath]) -> bool:
+    """
+    Check if the file has more than one line.
+
+    Args:
+        path (Union[pathlib.Path, AnyPath]):
+            The path to the file.
+
+    Returns:
+        bool:
+            True if the file has more than one line, False otherwise.
+
+    Raises:
+        NoInputDataException: If the file has zero lines.
+    """
+
+    # if we don't have a sqlite file
+    # (we can't check sqlite files for lines)
+    if path.suffix.lower() != ".sqlite":
+        with path.open("r") as f:
+            try:
+                # read two lines, if the second is empty return false
+                return bool(f.readline() and f.readline())
+
+            except StopIteration:
+                # If we encounter the end of the file, it has only one line
+                raise NoInputDataException(
+                    f"Data file has 0 rows of values. Error in file: {path}"
+                )
+    else:
+        return True
+
+
 def _gather_sources(
     source_path: str,
     source_datatype: Optional[str] = None,
@@ -295,11 +324,11 @@ def _gather_sources(
         _infer_source_datatype,
     )
 
-    source_path = _build_path(path=source_path, **kwargs)
+    built_path = _build_path(path=source_path, **kwargs)
 
     # gather filepaths which will be used as the basis for this work
     sources = _get_source_filepaths(
-        path=source_path, targets=targets, source_datatype=source_datatype
+        path=built_path, targets=targets, source_datatype=source_datatype
     )
 
     # infer or validate the source datatype based on source filepaths

cytotable/utils.py

@@ -149,6 +149,10 @@ def _duckdb_reader() -> duckdb.DuckDBPyConnection:
         INSTALL sqlite_scanner;
         LOAD sqlite_scanner;
 
+        /* Install httpfs plugin to avoid error
+        https://github.com/duckdb/duckdb/issues/3243 */
+        INSTALL httpfs;
+
         /*
         Set threads available to duckdb
         See the following for more information:
@@ -322,7 +326,7 @@ def _sqlite_mixed_type_query_to_parquet(
     return pa.Table.from_pylist(results)
 
 
-def _cache_cloudpath_to_local(path: Union[str, AnyPath]) -> pathlib.Path:
+def _cache_cloudpath_to_local(path: AnyPath) -> pathlib.Path:
     """
     Takes a cloudpath and uses cache to convert to a local copy
     for use in scenarios where remote work is not possible (sqlite).
@@ -337,24 +341,25 @@ def _cache_cloudpath_to_local(path: Union[str, AnyPath]) -> pathlib.Path:
             A local pathlib.Path to cached version of cloudpath file.
     """
 
-    candidate_path = AnyPath(path)
-
     # check that the path is a file (caching won't work with a dir)
     # and check that the file is of sqlite type
     # (other file types will be handled remotely in cloud)
-    if candidate_path.is_file() and candidate_path.suffix.lower() == ".sqlite":
+    if (
+        isinstance(path, CloudPath)
+        and path.is_file()
+        and path.suffix.lower() == ".sqlite"
+    ):
         try:
             # update the path to be the local filepath for reference in CytoTable ops
             # note: incurs a data read which will trigger caching of the file
-            path = CloudPath(path).fspath
+            path = pathlib.Path(path.fspath)
         except InvalidPrefixError:
             # share information about not finding a cloud path
             logger.info(
                 "Did not detect a cloud path based on prefix. Defaulting to use local path operations."
             )
 
-    # cast the result as a pathlib.Path
-    return pathlib.Path(path)
+    return path
 
 
 def _arrow_type_cast_if_specified(

{cytotable-0.0.8.dist-info → cytotable-0.0.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: CytoTable
-Version: 0.0.8
+Version: 0.0.9
 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
@@ -14,7 +14,7 @@ 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] (>=0.18.0,<0.19.0)
+Requires-Dist: cloudpathlib[all,s3] (>=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"

cytotable-0.0.9.dist-info/RECORD

@@ -0,0 +1,11 @@
+cytotable/__init__.py,sha256=OK8rwVqJ4PSMukLgdhGEOGAtSc-NHp-dtOln2ER83iE,315
+cytotable/constants.py,sha256=5ndA_0fNL66O1Mt6HPkuZGgK2VSUiBF839c7dV_w8EY,2097
+cytotable/convert.py,sha256=TDPWMYCXrLReaixxS-aLQfK22ZfzvQ0Qsc4RmyHQd-Y,54458
+cytotable/exceptions.py,sha256=NhkMswjCB0HeVHqlLXzBlyHunQIp_4eBFmyAPu0Nf30,482
+cytotable/presets.py,sha256=iiTzOj6AyYr7kJXspbN7N-6YIhCD7kmV-vQErwNm3U0,12405
+cytotable/sources.py,sha256=TY4dkbwh1PDCNapmMHE09Ey7QPYPhmp5DeErh3Wp4rw,12283
+cytotable/utils.py,sha256=Asy-hfZWZ4mGRE0zi7PYLqaShtvLM2qJoHCOaHjHOWo,19431
+cytotable-0.0.9.dist-info/LICENSE,sha256=lPK3PtUMP-f1EOFMUr8h3FvuMh89x249Hvm4lchTsv0,1528
+cytotable-0.0.9.dist-info/METADATA,sha256=yUED1TmK-FWe8zIL2T2nRDey6ygHlqt9dXKyRo9QFhY,3423
+cytotable-0.0.9.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+cytotable-0.0.9.dist-info/RECORD,,

cytotable-0.0.8.dist-info/RECORD

@@ -1,11 +0,0 @@
-cytotable/__init__.py,sha256=hBU893kcWONEc1iC3OoKg5hGyjWso3EzPpFAQocofU8,315
-cytotable/constants.py,sha256=5ndA_0fNL66O1Mt6HPkuZGgK2VSUiBF839c7dV_w8EY,2097
-cytotable/convert.py,sha256=LncoO0UQj5RDgJYoMVBP7aQ2b9qNI4FaqCCP7IbuESg,54870
-cytotable/exceptions.py,sha256=NhkMswjCB0HeVHqlLXzBlyHunQIp_4eBFmyAPu0Nf30,482
-cytotable/presets.py,sha256=YgxCsCLfbOK91Kebo4ZxI9t-WE-nHENITCC6JXmOV9I,10105
-cytotable/sources.py,sha256=zvkYMJOTBJVgFFSbkfpjFMwlOu4ifhxYALh71NGKEuM,11283
-cytotable/utils.py,sha256=JIvmNe9uD71MeUx0t5gMvUNVWpoSYNugtXNjsknjmu0,19357
-cytotable-0.0.8.dist-info/LICENSE,sha256=lPK3PtUMP-f1EOFMUr8h3FvuMh89x249Hvm4lchTsv0,1528
-cytotable-0.0.8.dist-info/METADATA,sha256=qBqn3Vhmg-X7Y6N0yISwQtXNcj1qWe_JSUcx9XSt0y0,3420
-cytotable-0.0.8.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-cytotable-0.0.8.dist-info/RECORD,,