Added mam_ansp_fix tool

pyproject.toml

@@ -3,86 +3,78 @@ requires = ["hatchling"]
 build-backend = "hatchling.build"
 
 [tool.hatch.build.targets.wheel]
-packages = ["src/DD_tools"]
+packages = ["src/TreeOfLife_toolbox"]
 
 [project]
-name = "DD_tools"
+name = "TreeOfLife_toolbox"
 dynamic = ["version"]
 authors = [
     { name = "Andrey Kopanev", email = "kopanev.1@osu.edu" },
     { name = "Elizabeth G. Campolongo", email = "e.campolongo479@gmail.com" },
     { name = "Matthew J. Thompson", email = "thompson.m.j@outlook.com" },
 ]
-description = "A tool for downloading files from a list of URLs in parallel."
+description = "A tool for processing datasets that was downloaded using the distributed-downloader package."
 readme = "README.md"
-requires-python = ">=3.8"
+requires-python = ">=3.10, <3.12"
 classifiers = [
+    "Development Status :: 4 - Beta",
     "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
     "License :: OSI Approved :: MIT License",
     "Operating System :: OS Independent",
 ]
 dependencies = [
     "attrs",
     "brotli",
-    "certifi",
-    "charset-normalizer",
     "cramjam",
     "cython",
-    "exceptiongroup",
     "fsspec",
-    "hatchling",
-    "idna",
     "inflate64",
-    "iniconfig",
-    "mpi4py < 4",
+    "mpi4py",
     "multivolumefile",
-    "numpy",
     "opencv-python",
-    "packaging",
     "pandas",
     "pathspec",
     "pillow",
-    "pip",
-    "pluggy",
     "psutil",
-    "py4j",
     "pyarrow",
     "pybcj",
     "pycryptodomex",
     "pyppmd",
     "pyspark",
-    "pytest",
-    "python-dateutil",
     "python-dotenv",
-    "pytz",
     "pyyaml",
     "pyzstd",
     "requests",
     "setuptools",
-    "six",
     "texttable",
-    "tomli",
     "trove-classifiers",
     "typing-extensions",
-    "tzdata",
-    "urllib3",
     "wheel"
 ]
 
 [project.optional-dependencies]
-dev = ["pytest"]
+dev = [
+    "pytest",
+    "ruff"
+]
 
 keywords = [
     "parallel",
     "distributed",
-    "download",
     "url",
+    "mpi-applications",
+    "dataset-generation",
 ]
 
 [project.urls]
 Homepage = "https://github.com/Imageomics/distributed-downloader"
 Repository = "https://github.com/Imageomics/distributed-downloader.git"
 "Bug Tracker" = "https://github.com/Imageomics/distributed-downloader/issues"
 
+[project.scripts]
+tree_of_life_toolbox = "TreeOfLife_toolbox.main.main:main"
+
 [tool.hatch.version]
-path = "src/DD_tools/main/__about__.py"
+path = "src/TreeOfLife_toolbox/main/__about__.py"

scripts/tools_filter.slurm

@@ -19,11 +19,10 @@ executor_memory="64G"
 module load spark/3.4.1
 module load miniconda3/23.3.1-py310
 source "${REPO_ROOT}/.venv/bin/activate"
-export PYTHONPATH=${PYTHONPATH}:"${REPO_ROOT}/src":"${REPO_ROOT}/distributed-downloader"
 
 pbs-spark-submit \
     --driver-memory $driver_memory \
     --executor-memory $executor_memory \
-    "${REPO_ROOT}/src/distributed_downloader/tools/filter.py" \
+    "${TOOLBOX_PATH}/main/filter.py" \
     "${tool_name}" \
     > "${logs_dir}/tool_filter.log"

scripts/tools_scheduler.slurm

@@ -19,7 +19,6 @@ module load miniconda3/23.3.1-py310
 source "${REPO_ROOT}/.venv/bin/activate"
 export PYARROW_IGNORE_TIMEZONE=1
 export I_MPI_JOB_RESPECT_PROCESS_PLACEMENT=0
-export PYTHONPATH=${PYTHONPATH}:"${REPO_ROOT}/src":"${REPO_ROOT}/distributed-downloader"
 
 srun \
   --mpi=pmi2 \
@@ -28,4 +27,4 @@ srun \
   --cpus-per-task=1 \
   --mem=0 \
   --output="${logs_dir}/tool_scheduler.log" \
-  python "${REPO_ROOT}/src/distributed_downloader/tools/scheduler.py" "${tool_name}"
+  python "${TOOLBOX_PATH}/main/scheduler.py" "${tool_name}"

scripts/tools_verifier.slurm

@@ -19,7 +19,6 @@ module load miniconda3/23.3.1-py310
 source "${REPO_ROOT}/.venv/bin/activate"
 export PYARROW_IGNORE_TIMEZONE=1
 export I_MPI_JOB_RESPECT_PROCESS_PLACEMENT=0
-export PYTHONPATH=${PYTHONPATH}:"${REPO_ROOT}/src":"${REPO_ROOT}/distributed-downloader"
 
 srun \
   --mpi=pmi2 \
@@ -28,4 +27,4 @@ srun \
   --cpus-per-task=1 \
   --mem=0 \
   --output="${logs_dir}/tool_verifier.log" \
-  python "${REPO_ROOT}/src/distributed_downloader/tools/verification.py" "${tool_name}"
+  python "${TOOLBOX_PATH}/main/verification.py" "${tool_name}"

scripts/tools_worker.slurm

@@ -19,7 +19,6 @@ module load miniconda3/23.3.1-py310
 source "${REPO_ROOT}/.venv/bin/activate"
 export PYARROW_IGNORE_TIMEZONE=1
 export I_MPI_JOB_RESPECT_PROCESS_PLACEMENT=0
-export PYTHONPATH=${PYTHONPATH}:"${REPO_ROOT}/src":"${REPO_ROOT}/distributed-downloader"
 
 srun \
   --mpi=pmi2 \
@@ -28,4 +27,4 @@ srun \
   --cpus-per-task="$TOOLS_CPU_PER_WORKER" \
   --mem=0 \
   --output="${logs_dir}/tool_worker-%2t.log" \
-  python "${REPO_ROOT}/src/distributed_downloader/tools/runner.py" "${tool_name}"
+  python "${TOOLBOX_PATH}/main/runner.py" "${tool_name}"

src/TreeOfLife_toolbox/__init__.py

@@ -0,0 +1 @@
+from TreeOfLife_toolbox import mam_ansp_fix

src/DD_tools/main/filter.py → src/TreeOfLife_toolbox/main/filter.py

@@ -1,10 +1,10 @@
 import argparse
 import os
 
-from DD_tools.main.checkpoint import Checkpoint
-from DD_tools.main.config import Config
-from DD_tools.main.registry import ToolsRegistryBase
-from DD_tools.main.utils import init_logger
+from TreeOfLife_toolbox.main.checkpoint import Checkpoint
+from TreeOfLife_toolbox.main.config import Config
+from TreeOfLife_toolbox.main.registry import ToolsRegistryBase
+from TreeOfLife_toolbox.main.utils import init_logger
 
 if __name__ == "__main__":
     config_path = os.environ.get("CONFIG_PATH")

src/DD_tools/main/filters.py → src/TreeOfLife_toolbox/main/filters.py

@@ -7,10 +7,10 @@
 from pyspark.sql import SparkSession
 from pyspark.sql.types import StructType
 
-from DD_tools.main.config import Config
-from DD_tools.main.registry import ToolsBase
-from DD_tools.main.registry import ToolsRegistryBase
-from DD_tools.main.utils import SuccessEntry
+from TreeOfLife_toolbox.main.config import Config
+from TreeOfLife_toolbox.main.registry import ToolsBase
+from TreeOfLife_toolbox.main.registry import ToolsRegistryBase
+from TreeOfLife_toolbox.main.utils import SuccessEntry
 
 FilterRegister = partial(ToolsRegistryBase.register, "filter")
 

src/DD_tools/main/main.py → src/TreeOfLife_toolbox/main/main.py

@@ -1,15 +1,16 @@
 import argparse
 import os
 from logging import Logger
+from pathlib import Path
 from typing import Dict, List, Optional, TextIO, Tuple
 
 import pandas as pd
 from attr import Factory, define, field
 
-from DD_tools.main.checkpoint import Checkpoint
-from DD_tools.main.config import Config
-from DD_tools.main.registry import ToolsRegistryBase
-from DD_tools.main.utils import (
+from TreeOfLife_toolbox.main.checkpoint import Checkpoint
+from TreeOfLife_toolbox.main.config import Config
+from TreeOfLife_toolbox.main.registry import ToolsRegistryBase
+from TreeOfLife_toolbox.main.utils import (
     init_logger,
     ensure_created,
     truncate_paths,
@@ -78,6 +79,7 @@ def __attrs_post_init__(self):
 
     def __init_environment(self) -> None:
         os.environ["CONFIG_PATH"] = self.config.config_path
+        os.environ["TOOLBOX_PATH"] = str(Path(__file__).parent.parent.resolve())
 
         os.environ["ACCOUNT"] = self.config["account"]
         os.environ["PATH_TO_INPUT"] = self.config["path_to_input"]

src/DD_tools/main/registry.py → src/TreeOfLife_toolbox/main/registry.py

@@ -1,7 +1,7 @@
 from typing import Dict, Type, Optional
 
-from DD_tools.main.config import Config
-from DD_tools.main.utils import init_logger
+from TreeOfLife_toolbox.main.config import Config
+from TreeOfLife_toolbox.main.utils import init_logger
 
 
 class ToolsRegistryBase(type):

src/DD_tools/main/runner.py → src/TreeOfLife_toolbox/main/runner.py

@@ -1,10 +1,10 @@
 import argparse
 import os
 
-from DD_tools.main.checkpoint import Checkpoint
-from DD_tools.main.config import Config
-from DD_tools.main.registry import ToolsRegistryBase
-from DD_tools.main.utils import init_logger
+from TreeOfLife_toolbox.main.checkpoint import Checkpoint
+from TreeOfLife_toolbox.main.config import Config
+from TreeOfLife_toolbox.main.registry import ToolsRegistryBase
+from TreeOfLife_toolbox.main.utils import init_logger
 
 if __name__ == "__main__":
     config_path = os.environ.get("CONFIG_PATH")

src/DD_tools/main/runners.py → src/TreeOfLife_toolbox/main/runners.py

@@ -6,8 +6,8 @@
 
 import pandas as pd
 
-from DD_tools.main.config import Config
-from DD_tools.main.registry import ToolsBase, ToolsRegistryBase
+from TreeOfLife_toolbox.main.config import Config
+from TreeOfLife_toolbox.main.registry import ToolsBase, ToolsRegistryBase
 
 RunnerRegister = partial(ToolsRegistryBase.register, "runner")
 

src/DD_tools/main/scheduler.py → src/TreeOfLife_toolbox/main/scheduler.py

@@ -1,10 +1,10 @@
 import argparse
 import os
 
-from DD_tools.main.checkpoint import Checkpoint
-from DD_tools.main.config import Config
-from DD_tools.main.registry import ToolsRegistryBase
-from DD_tools.main.utils import init_logger
+from TreeOfLife_toolbox.main.checkpoint import Checkpoint
+from TreeOfLife_toolbox.main.config import Config
+from TreeOfLife_toolbox.main.registry import ToolsRegistryBase
+from TreeOfLife_toolbox.main.utils import init_logger
 
 if __name__ == "__main__":
     config_path = os.environ.get("CONFIG_PATH")

src/DD_tools/main/schedulers.py → src/TreeOfLife_toolbox/main/schedulers.py

@@ -5,8 +5,8 @@
 
 import pandas as pd
 
-from DD_tools.main.config import Config
-from DD_tools.main.registry import ToolsBase, ToolsRegistryBase
+from TreeOfLife_toolbox.main.config import Config
+from TreeOfLife_toolbox.main.registry import ToolsBase, ToolsRegistryBase
 
 SchedulerRegister = partial(ToolsRegistryBase.register, "scheduler")
 

src/DD_tools/main/verification.py → src/TreeOfLife_toolbox/main/verification.py

@@ -3,11 +3,11 @@
 
 import pandas as pd
 
-from DD_tools.main.checkpoint import Checkpoint
-from DD_tools.main.config import Config
-from DD_tools.main.registry import ToolsRegistryBase
-from DD_tools.main.runners import MPIRunnerTool
-from DD_tools.main.utils import init_logger
+from TreeOfLife_toolbox.main.checkpoint import Checkpoint
+from TreeOfLife_toolbox.main.config import Config
+from TreeOfLife_toolbox.main.registry import ToolsRegistryBase
+from TreeOfLife_toolbox.main.runners import MPIRunnerTool
+from TreeOfLife_toolbox.main.utils import init_logger
 
 if __name__ == "__main__":
     config_path = os.environ.get("CONFIG_PATH")

src/TreeOfLife_toolbox/mam_ansp_fix/README.md

@@ -0,0 +1,39 @@
+# MAM ANSP Duplication Fix Tool
+
+## Overview
+
+This tool addresses a specific duplication issue found in data from the "mam.ansp.org" server (from the GBIF source) in
+the Tree of Life dataset. It identifies, processes, and removes duplicate UUID entries within parquet files, ensuring
+data integrity and consistency.
+
+The tool consists of three main components:
+
+1. **Filter (MamAnspFixFilter)**: Identifies files from the mam.ansp.org server that need deduplication based on a
+   provided UUID table.
+2. **Scheduler (MamAnspFixScheduleCreation)**: Distributes the workload of file processing across available workers.
+3. **Runner (MamAnspFixRunner)**: Performs the actual deduplication process by reading each file, removing duplicate
+   UUIDs, and saving the cleaned data to a specified location.
+
+## Configuration Requirements
+
+The following fields must be included in the configuration file:
+
+* `uuid_table_path`: Path to the CSV file containing the table of UUIDs with information about duplicated entries. This
+  file must include "server" and "path" columns.
+* `save_path_folder`: Directory where the deduplicated parquet files will be saved.
+
+## Prerequisites (Pre-conditions)
+
+Before running this tool, ensure:
+
+- The dataset follows the Tree of Life format structure
+- The UUIDs table contains accurate information about mam.ansp.org server entries
+- The `uuid_table_path` CSV file contains at minimum these columns: "server" and "path"
+
+## Guarantees (Post-conditions)
+
+After successful execution:
+
+- The dataset maintains the Tree Of Life format
+- Duplicate UUID entries in files from mam.ansp.org server have been removed
+- The original files remain untouched

src/TreeOfLife_toolbox/mam_ansp_fix/__init__.py

@@ -0,0 +1 @@
+from .classes import MamAnspFixFilter, MamAnspFixScheduleCreation, MamAnspFixRunner