From 3bf3388af41faa7fad4700f671d7a7fe3868b896 Mon Sep 17 00:00:00 2001
From: Andrey170170 <andrey24122004@gmail.com>
Date: Sun, 16 Feb 2025 16:07:06 -0500
Subject: [PATCH 1/5] Added lila_bc_filtering tool

---
 src/DD_tools/lila_bc_filtering/__init__.py |  0
 src/DD_tools/lila_bc_filtering/classes.py  | 52 ++++++++++++++++++++++
 2 files changed, 52 insertions(+)
 create mode 100644 src/DD_tools/lila_bc_filtering/__init__.py
 create mode 100644 src/DD_tools/lila_bc_filtering/classes.py

diff --git a/src/DD_tools/lila_bc_filtering/__init__.py b/src/DD_tools/lila_bc_filtering/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/DD_tools/lila_bc_filtering/classes.py b/src/DD_tools/lila_bc_filtering/classes.py
new file mode 100644
index 0000000..a807058
--- /dev/null
+++ b/src/DD_tools/lila_bc_filtering/classes.py
@@ -0,0 +1,52 @@
+import pyspark.sql as ps
+from pyspark.sql import SparkSession
+
+from DD_tools.main.config import Config
+from DD_tools.main.filters import FilterRegister, SparkFilterToolBase
+from DD_tools.main.runners import RunnerRegister, FilterRunnerTool
+from DD_tools.main.schedulers import DefaultScheduler, SchedulerRegister
+
+
+@FilterRegister("lila_bc_filtering")
+class LilaBCFilter(SparkFilterToolBase):
+    path_to_excluding_labels = (
+        "/fs/scratch/PAS2136/gbif/processed/lilabc/distinct_labels/labels_to_remove.csv"
+    )
+
+    def __init__(self, cfg: Config, spark: SparkSession = None):
+        super().__init__(cfg, spark)
+        self.filter_name: str = "lila_bc_filtering"
+
+    def run(self):
+        successes_df: ps.DataFrame = self.load_data_parquet()
+        data_df = self.spark.read.parquet(self.urls_path).select(
+            "uuid", "original_label"
+        )
+        labels_to_exclude_df = self.spark.read.csv(
+            self.path_to_excluding_labels, header=True
+        )
+
+        merged_df = successes_df.join(data_df, on="uuid", how="inner")
+        filtered_df = merged_df.join(
+            labels_to_exclude_df, on="original_label", how="inner"
+        ).select("uuid", "source_id", "server_name", "partition_id")
+
+        self.save_filter(filtered_df)
+
+        self.logger.info(f"Images to filter out: {filtered_df.count()}")
+
+
+@SchedulerRegister("lila_bc_filtering")
+class LilaBCScheduleCreation(DefaultScheduler):
+    def __init__(self, cfg: Config):
+        super().__init__(cfg)
+
+        self.filter_name: str = "lila_bc_filtering"
+
+
+@RunnerRegister("lila_bc_filtering")
+class LilaBCRunner(FilterRunnerTool):
+    def __init__(self, cfg: Config):
+        super().__init__(cfg)
+
+        self.filter_name: str = "lila_bc_filtering"

From f41119261d8b8b6a8a7da29ce0cfbe37b604b389 Mon Sep 17 00:00:00 2001
From: Andrey170170 <andrey24122004@gmail.com>
Date: Mon, 12 May 2025 02:29:05 -0400
Subject: [PATCH 2/5] Rename project from 'DD_tools' to 'TreeOfLife_toolbox'.

Updated package structure, filenames, and references to reflect the new name. Adjusted `pyproject.toml` to rename the project, update dependencies, and modify supported Python versions. These changes ensure consistency and alignment with the new project branding.
---
 pyproject.toml                                | 28 ++++---------------
 .../__init__.py                               |  0
 .../main/__about__.py                         |  0
 .../main/checkpoint.py                        |  0
 .../main/config.py                            |  0
 .../main/config_templates/tools.yaml          |  0
 .../main/filter.py                            |  0
 .../main/filters.py                           |  0
 .../main/main.py                              |  0
 .../main/registry.py                          |  0
 .../main/runner.py                            |  0
 .../main/runners.py                           |  0
 .../main/scheduler.py                         |  0
 .../main/schedulers.py                        |  0
 .../main/utils.py                             |  0
 .../main/verification.py                      |  0
 16 files changed, 5 insertions(+), 23 deletions(-)
 rename src/{DD_tools => TreeOfLife_toolbox}/__init__.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/__about__.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/checkpoint.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/config.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/config_templates/tools.yaml (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/filter.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/filters.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/main.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/registry.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/runner.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/runners.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/scheduler.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/schedulers.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/utils.py (100%)
 rename src/{DD_tools => TreeOfLife_toolbox}/main/verification.py (100%)

diff --git a/pyproject.toml b/pyproject.toml
index 17be78f..cb76174 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -3,10 +3,10 @@ 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" },
@@ -15,7 +15,7 @@ authors = [
 ]
 description = "A tool for downloading files from a list of URLs in parallel."
 readme = "README.md"
-requires-python = ">=3.8"
+requires-python = ">=3.10, <3.12"
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: MIT License",
@@ -24,48 +24,30 @@ classifiers = [
 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"
 ]
 
@@ -85,4 +67,4 @@ Repository = "https://github.com/Imageomics/distributed-downloader.git"
 "Bug Tracker" = "https://github.com/Imageomics/distributed-downloader/issues"
 
 [tool.hatch.version]
-path = "src/DD_tools/main/__about__.py"
+path = "src/TreeOfLife_toolbox/main/__about__.py"
diff --git a/src/DD_tools/__init__.py b/src/TreeOfLife_toolbox/__init__.py
similarity index 100%
rename from src/DD_tools/__init__.py
rename to src/TreeOfLife_toolbox/__init__.py
diff --git a/src/DD_tools/main/__about__.py b/src/TreeOfLife_toolbox/main/__about__.py
similarity index 100%
rename from src/DD_tools/main/__about__.py
rename to src/TreeOfLife_toolbox/main/__about__.py
diff --git a/src/DD_tools/main/checkpoint.py b/src/TreeOfLife_toolbox/main/checkpoint.py
similarity index 100%
rename from src/DD_tools/main/checkpoint.py
rename to src/TreeOfLife_toolbox/main/checkpoint.py
diff --git a/src/DD_tools/main/config.py b/src/TreeOfLife_toolbox/main/config.py
similarity index 100%
rename from src/DD_tools/main/config.py
rename to src/TreeOfLife_toolbox/main/config.py
diff --git a/src/DD_tools/main/config_templates/tools.yaml b/src/TreeOfLife_toolbox/main/config_templates/tools.yaml
similarity index 100%
rename from src/DD_tools/main/config_templates/tools.yaml
rename to src/TreeOfLife_toolbox/main/config_templates/tools.yaml
diff --git a/src/DD_tools/main/filter.py b/src/TreeOfLife_toolbox/main/filter.py
similarity index 100%
rename from src/DD_tools/main/filter.py
rename to src/TreeOfLife_toolbox/main/filter.py
diff --git a/src/DD_tools/main/filters.py b/src/TreeOfLife_toolbox/main/filters.py
similarity index 100%
rename from src/DD_tools/main/filters.py
rename to src/TreeOfLife_toolbox/main/filters.py
diff --git a/src/DD_tools/main/main.py b/src/TreeOfLife_toolbox/main/main.py
similarity index 100%
rename from src/DD_tools/main/main.py
rename to src/TreeOfLife_toolbox/main/main.py
diff --git a/src/DD_tools/main/registry.py b/src/TreeOfLife_toolbox/main/registry.py
similarity index 100%
rename from src/DD_tools/main/registry.py
rename to src/TreeOfLife_toolbox/main/registry.py
diff --git a/src/DD_tools/main/runner.py b/src/TreeOfLife_toolbox/main/runner.py
similarity index 100%
rename from src/DD_tools/main/runner.py
rename to src/TreeOfLife_toolbox/main/runner.py
diff --git a/src/DD_tools/main/runners.py b/src/TreeOfLife_toolbox/main/runners.py
similarity index 100%
rename from src/DD_tools/main/runners.py
rename to src/TreeOfLife_toolbox/main/runners.py
diff --git a/src/DD_tools/main/scheduler.py b/src/TreeOfLife_toolbox/main/scheduler.py
similarity index 100%
rename from src/DD_tools/main/scheduler.py
rename to src/TreeOfLife_toolbox/main/scheduler.py
diff --git a/src/DD_tools/main/schedulers.py b/src/TreeOfLife_toolbox/main/schedulers.py
similarity index 100%
rename from src/DD_tools/main/schedulers.py
rename to src/TreeOfLife_toolbox/main/schedulers.py
diff --git a/src/DD_tools/main/utils.py b/src/TreeOfLife_toolbox/main/utils.py
similarity index 100%
rename from src/DD_tools/main/utils.py
rename to src/TreeOfLife_toolbox/main/utils.py
diff --git a/src/DD_tools/main/verification.py b/src/TreeOfLife_toolbox/main/verification.py
similarity index 100%
rename from src/DD_tools/main/verification.py
rename to src/TreeOfLife_toolbox/main/verification.py

From 4a982dd82b03ab2bd8e9a8fc1a7ea270e51b6f53 Mon Sep 17 00:00:00 2001
From: Andrey170170 <andrey24122004@gmail.com>
Date: Mon, 12 May 2025 02:34:30 -0400
Subject: [PATCH 3/5] Refactor import paths to use TreeOfLife_toolbox module.

Updated all import statements to reference TreeOfLife_toolbox instead of DD_tools for consistency and clarity. Adjusted slurm scripts to align with the new module structure and standardized environment variables for toolbox path configuration.
---
 scripts/tools_filter.slurm                  |  3 +--
 scripts/tools_scheduler.slurm               |  3 +--
 scripts/tools_verifier.slurm                |  3 +--
 scripts/tools_worker.slurm                  |  3 +--
 src/TreeOfLife_toolbox/main/filter.py       |  8 ++++----
 src/TreeOfLife_toolbox/main/filters.py      |  8 ++++----
 src/TreeOfLife_toolbox/main/main.py         | 10 ++++++----
 src/TreeOfLife_toolbox/main/registry.py     |  4 ++--
 src/TreeOfLife_toolbox/main/runner.py       |  8 ++++----
 src/TreeOfLife_toolbox/main/runners.py      |  4 ++--
 src/TreeOfLife_toolbox/main/scheduler.py    |  8 ++++----
 src/TreeOfLife_toolbox/main/schedulers.py   |  4 ++--
 src/TreeOfLife_toolbox/main/verification.py | 10 +++++-----
 13 files changed, 37 insertions(+), 39 deletions(-)

diff --git a/scripts/tools_filter.slurm b/scripts/tools_filter.slurm
index 4642e34..6aee3f6 100644
--- a/scripts/tools_filter.slurm
+++ b/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}" \
     > "${logs_dir}/tool_filter.log"
diff --git a/scripts/tools_scheduler.slurm b/scripts/tools_scheduler.slurm
index e4fb6a2..ea35a32 100644
--- a/scripts/tools_scheduler.slurm
+++ b/scripts/tools_scheduler.slurm
@@ -19,7 +19,6 @@ module load miniconda3/23.3.1-py310
 source "${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" "${tool_name}"
diff --git a/scripts/tools_verifier.slurm b/scripts/tools_verifier.slurm
index 98ca024..6a3b75e 100644
--- a/scripts/tools_verifier.slurm
+++ b/scripts/tools_verifier.slurm
@@ -19,7 +19,6 @@ module load miniconda3/23.3.1-py310
 source "${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" "${tool_name}"
diff --git a/scripts/tools_worker.slurm b/scripts/tools_worker.slurm
index 2ee2662..4856e62 100644
--- a/scripts/tools_worker.slurm
+++ b/scripts/tools_worker.slurm
@@ -19,7 +19,6 @@ module load miniconda3/23.3.1-py310
 source "${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}"
diff --git a/src/TreeOfLife_toolbox/main/filter.py b/src/TreeOfLife_toolbox/main/filter.py
index 080e1a2..ed526c5 100644
--- a/src/TreeOfLife_toolbox/main/filter.py
+++ b/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")
diff --git a/src/TreeOfLife_toolbox/main/filters.py b/src/TreeOfLife_toolbox/main/filters.py
index 11c9426..385f18e 100644
--- a/src/TreeOfLife_toolbox/main/filters.py
+++ b/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")
 
diff --git a/src/TreeOfLife_toolbox/main/main.py b/src/TreeOfLife_toolbox/main/main.py
index b3d5732..5272354 100644
--- a/src/TreeOfLife_toolbox/main/main.py
+++ b/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"]
diff --git a/src/TreeOfLife_toolbox/main/registry.py b/src/TreeOfLife_toolbox/main/registry.py
index 12774dd..03cf9d6 100644
--- a/src/TreeOfLife_toolbox/main/registry.py
+++ b/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):
diff --git a/src/TreeOfLife_toolbox/main/runner.py b/src/TreeOfLife_toolbox/main/runner.py
index 214237e..77dcefa 100644
--- a/src/TreeOfLife_toolbox/main/runner.py
+++ b/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")
diff --git a/src/TreeOfLife_toolbox/main/runners.py b/src/TreeOfLife_toolbox/main/runners.py
index cd875d3..bfb5d5e 100644
--- a/src/TreeOfLife_toolbox/main/runners.py
+++ b/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")
 
diff --git a/src/TreeOfLife_toolbox/main/scheduler.py b/src/TreeOfLife_toolbox/main/scheduler.py
index 707b656..d686ae6 100644
--- a/src/TreeOfLife_toolbox/main/scheduler.py
+++ b/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")
diff --git a/src/TreeOfLife_toolbox/main/schedulers.py b/src/TreeOfLife_toolbox/main/schedulers.py
index ed70a9c..6b2c6e2 100644
--- a/src/TreeOfLife_toolbox/main/schedulers.py
+++ b/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")
 
diff --git a/src/TreeOfLife_toolbox/main/verification.py b/src/TreeOfLife_toolbox/main/verification.py
index 742bb86..31d2561 100644
--- a/src/TreeOfLife_toolbox/main/verification.py
+++ b/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")

From 99ca3b016b14c27482d7152bba47d6db71b46334 Mon Sep 17 00:00:00 2001
From: Andrey170170 <andrey24122004@gmail.com>
Date: Mon, 12 May 2025 02:39:08 -0400
Subject: [PATCH 4/5] Update metadata and dependencies in pyproject.toml

Revised the project description, added programming language classifiers, and enhanced optional dependencies with 'ruff'. Introduced new keywords and added a script entry point for better usability.
---
 pyproject.toml | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index cb76174..b3e3a5c 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -13,11 +13,14 @@ authors = [
     { 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 = ">=3.10, <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",
 ]
@@ -52,13 +55,17 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
-dev = ["pytest"]
+dev = [
+    "pytest",
+    "ruff"
+]
 
 keywords = [
     "parallel",
     "distributed",
-    "download",
     "url",
+    "mpi-applications",
+    "dataset-generation",
 ]
 
 [project.urls]
@@ -66,5 +73,8 @@ 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/TreeOfLife_toolbox/main/__about__.py"

From c17e2668313d9a107db803af0c36a20fa82b3a97 Mon Sep 17 00:00:00 2001
From: Andrey170170 <andrey24122004@gmail.com>
Date: Wed, 14 May 2025 02:08:44 -0400
Subject: [PATCH 5/5] Rename and enhance LILA BC filtering tool.

Refactored the LILA Biodiversity Catalog filtering tool by renaming modules under `TreeOfLife_toolbox`, updating imports, and adding extensive documentation. Implemented clear class structures and attributes for filtering, scheduling, and running tasks, improving usability and modularity.
---
 src/DD_tools/lila_bc_filtering/__init__.py    |   0
 src/DD_tools/lila_bc_filtering/classes.py     |  52 --------
 src/TreeOfLife_toolbox/__init__.py            |   1 +
 .../lila_bc_filtering/README.md               |  68 +++++++++++
 .../lila_bc_filtering/__init__.py             |   1 +
 .../lila_bc_filtering/classes.py              | 114 ++++++++++++++++++
 6 files changed, 184 insertions(+), 52 deletions(-)
 delete mode 100644 src/DD_tools/lila_bc_filtering/__init__.py
 delete mode 100644 src/DD_tools/lila_bc_filtering/classes.py
 create mode 100644 src/TreeOfLife_toolbox/lila_bc_filtering/README.md
 create mode 100644 src/TreeOfLife_toolbox/lila_bc_filtering/__init__.py
 create mode 100644 src/TreeOfLife_toolbox/lila_bc_filtering/classes.py

diff --git a/src/DD_tools/lila_bc_filtering/__init__.py b/src/DD_tools/lila_bc_filtering/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/src/DD_tools/lila_bc_filtering/classes.py b/src/DD_tools/lila_bc_filtering/classes.py
deleted file mode 100644
index a807058..0000000
--- a/src/DD_tools/lila_bc_filtering/classes.py
+++ /dev/null
@@ -1,52 +0,0 @@
-import pyspark.sql as ps
-from pyspark.sql import SparkSession
-
-from DD_tools.main.config import Config
-from DD_tools.main.filters import FilterRegister, SparkFilterToolBase
-from DD_tools.main.runners import RunnerRegister, FilterRunnerTool
-from DD_tools.main.schedulers import DefaultScheduler, SchedulerRegister
-
-
-@FilterRegister("lila_bc_filtering")
-class LilaBCFilter(SparkFilterToolBase):
-    path_to_excluding_labels = (
-        "/fs/scratch/PAS2136/gbif/processed/lilabc/distinct_labels/labels_to_remove.csv"
-    )
-
-    def __init__(self, cfg: Config, spark: SparkSession = None):
-        super().__init__(cfg, spark)
-        self.filter_name: str = "lila_bc_filtering"
-
-    def run(self):
-        successes_df: ps.DataFrame = self.load_data_parquet()
-        data_df = self.spark.read.parquet(self.urls_path).select(
-            "uuid", "original_label"
-        )
-        labels_to_exclude_df = self.spark.read.csv(
-            self.path_to_excluding_labels, header=True
-        )
-
-        merged_df = successes_df.join(data_df, on="uuid", how="inner")
-        filtered_df = merged_df.join(
-            labels_to_exclude_df, on="original_label", how="inner"
-        ).select("uuid", "source_id", "server_name", "partition_id")
-
-        self.save_filter(filtered_df)
-
-        self.logger.info(f"Images to filter out: {filtered_df.count()}")
-
-
-@SchedulerRegister("lila_bc_filtering")
-class LilaBCScheduleCreation(DefaultScheduler):
-    def __init__(self, cfg: Config):
-        super().__init__(cfg)
-
-        self.filter_name: str = "lila_bc_filtering"
-
-
-@RunnerRegister("lila_bc_filtering")
-class LilaBCRunner(FilterRunnerTool):
-    def __init__(self, cfg: Config):
-        super().__init__(cfg)
-
-        self.filter_name: str = "lila_bc_filtering"
diff --git a/src/TreeOfLife_toolbox/__init__.py b/src/TreeOfLife_toolbox/__init__.py
index e69de29..8d9b8aa 100644
--- a/src/TreeOfLife_toolbox/__init__.py
+++ b/src/TreeOfLife_toolbox/__init__.py
@@ -0,0 +1 @@
+from TreeOfLife_toolbox import lila_bc_filtering
diff --git a/src/TreeOfLife_toolbox/lila_bc_filtering/README.md b/src/TreeOfLife_toolbox/lila_bc_filtering/README.md
new file mode 100644
index 0000000..7329502
--- /dev/null
+++ b/src/TreeOfLife_toolbox/lila_bc_filtering/README.md
@@ -0,0 +1,68 @@
+# LILA Biodiversity Catalog Filtering Tool
+
+## Overview
+
+The LILA BC Filtering tool is a specialized component of the TreeOfLife toolbox designed to filter out images from a
+dataset based on their labels. Specifically, it removes images whose original labels match those specified in an
+exclusion list. This tool is primarily built to work with the LILA (Labeled Information Library of Alexandria)
+Biodiversity Catalog dataset, but can be applied to any dataset adhering to the proper format requirements.
+
+## How It Works
+
+The tool operates in three sequential stages:
+
+1. **Filtering (LilaBCFilter)**:
+    - Loads image data from parquet files
+    - Loads original labels from the URLs table
+    - Identifies images with labels matching the exclusion list
+    - Creates a filter table containing UUIDs of images to be removed
+
+2. **Scheduling (LilaBCScheduleCreation)**:
+    - Creates a work distribution schedule for parallel processing
+    - Assigns batches of images to different workers
+
+3. **Running (LilaBCRunner)**:
+    - Executes the actual filtering operation using MPI
+    - Removes matched images from the dataset
+    - Retains the same directory structure and filenames
+
+## Required Configuration
+
+### Mandatory Config Fields
+
+- `path_to_excluding_labels`: Path to a CSV file containing the labels to be excluded from the dataset
+
+## Prerequisites
+
+### Pre-conditions
+
+- The dataset must follow the `distributed-downloader` format structure
+- The dataset's URL table must contain a column named `original_label`
+- The CSV file specified in `path_to_excluding_labels` must exist with proper headers
+- The exclusion labels CSV must have a column that matches the 'original_label' values in the dataset
+
+### Input Format
+
+- The exclusion labels file should be a CSV file with column headers
+- At minimum, it must contain an 'original_label' column with the labels to exclude
+
+## Outcomes
+
+### Post-conditions
+
+- The dataset will be filtered to exclude all images with labels matching those in the exclusion list
+- Original parquet files will be replaced with filtered versions (retaining the same paths and names)
+- The tool will maintain a record of all filtered images
+- The filtering process is idempotent - running it multiple times will not cause additional data loss
+
+### Output Files
+
+- Filtered parquet files in the original dataset structure
+- Filtering logs and statistics in the tools directory
+- Verification files to confirm successful processing of each partition
+
+## Notes
+
+- In theory, this tool can be used for any dataset, as long as the original dataset contains an `original_label` column.
+- The filtering process is performed in-place, so make backups if you need to preserve the original data.
+- The tool is designed to run efficiently on distributed systems using MPI.
diff --git a/src/TreeOfLife_toolbox/lila_bc_filtering/__init__.py b/src/TreeOfLife_toolbox/lila_bc_filtering/__init__.py
new file mode 100644
index 0000000..c40f7f9
--- /dev/null
+++ b/src/TreeOfLife_toolbox/lila_bc_filtering/__init__.py
@@ -0,0 +1 @@
+from .classes import LilaBCFilter, LilaBCScheduleCreation, LilaBCRunner
diff --git a/src/TreeOfLife_toolbox/lila_bc_filtering/classes.py b/src/TreeOfLife_toolbox/lila_bc_filtering/classes.py
new file mode 100644
index 0000000..a0c4613
--- /dev/null
+++ b/src/TreeOfLife_toolbox/lila_bc_filtering/classes.py
@@ -0,0 +1,114 @@
+import pyspark.sql as ps
+from pyspark.sql import SparkSession
+
+from TreeOfLife_toolbox.main.config import Config
+from TreeOfLife_toolbox.main.filters import FilterRegister, SparkFilterToolBase
+from TreeOfLife_toolbox.main.runners import RunnerRegister, FilterRunnerTool
+from TreeOfLife_toolbox.main.schedulers import DefaultScheduler, SchedulerRegister
+
+
+@FilterRegister("lila_bc_filtering")
+class LilaBCFilter(SparkFilterToolBase):
+    """
+    Filter class for filtering out images from LILA Biodiversity Catalog based on specified labels.
+    
+    This class identifies images that have labels matching those in the excluding labels file
+    and creates a filter table containing UUIDs of those images. These images will later
+    be removed from the dataset by the runner.
+    
+    Attributes:
+        filter_name (str): Name of the filter tool, used for folder structure.
+        path_to_excluding_labels (str): Path to CSV containing labels to be excluded.
+    """
+
+    def __init__(self, cfg: Config, spark: SparkSession = None):
+        """
+        Initialize the LILA BC filter with configuration.
+        
+        Args:
+            cfg (Config): Configuration object containing paths and settings.
+            spark (SparkSession, optional): Existing SparkSession. If None, a new one will be created.
+        """
+        super().__init__(cfg, spark)
+        self.filter_name: str = "lila_bc_filtering"
+        self.path_to_excluding_labels = cfg["path_to_excluding_labels"]
+
+    def run(self):
+        """
+        Execute the filtering process.
+        
+        This method:
+        1. Loads the image data from the parquet files
+        2. Loads the original labels from URLs table
+        3. Loads the labels to be excluded
+        4. Joins the datasets to identify images with labels to exclude
+        5. Saves the filter table for later processing by the runner
+        
+        Returns:
+            None
+        """
+        successes_df: ps.DataFrame = self.load_data_parquet()
+        data_df = self.spark.read.parquet(self.urls_path).select(
+            "uuid", "original_label"
+        )
+        labels_to_exclude_df = self.spark.read.csv(
+            self.path_to_excluding_labels, header=True
+        )
+
+        merged_df = successes_df.join(data_df, on="uuid", how="inner")
+        filtered_df = merged_df.join(
+            labels_to_exclude_df, on="original_label", how="inner"
+        ).select("uuid", "source_id", "server_name", "partition_id")
+
+        self.save_filter(filtered_df)
+
+        self.logger.info(f"Images to filter out: {filtered_df.count()}")
+
+
+@SchedulerRegister("lila_bc_filtering")
+class LilaBCScheduleCreation(DefaultScheduler):
+    """
+    Scheduler for LILA BC filtering tool.
+    
+    This class creates a schedule for parallel processing of the filtering task.
+    It inherits from DefaultScheduler which manages the distribution of work
+    across available workers.
+    
+    Attributes:
+        filter_name (str): Name of the filter tool, used for folder structure.
+    """
+    def __init__(self, cfg: Config):
+        """
+        Initialize the LILA BC scheduler.
+        
+        Args:
+            cfg (Config): Configuration object containing paths and settings.
+        """
+        super().__init__(cfg)
+
+        self.filter_name: str = "lila_bc_filtering"
+
+
+@RunnerRegister("lila_bc_filtering")
+class LilaBCRunner(FilterRunnerTool):
+    """
+    Runner for LILA BC filtering tool.
+    
+    This class executes the actual filtering operation by removing images 
+    with specified labels. It uses MPI to distribute work across multiple nodes.
+    Inherits from FilterRunnerTool which provides common functionality for
+    filtering operations on downloaded images.
+    
+    Attributes:
+        filter_name (str): Name of the filter tool, used for folder structure.
+    """
+    def __init__(self, cfg: Config):
+        """
+        Initialize the LILA BC runner.
+        
+        Args:
+            cfg (Config): Configuration object containing paths and settings.
+        """
+        super().__init__(cfg)
+
+        self.filter_name: str = "lila_bc_filtering"