From c2b84e2655b73fd6efbee8bebb012aa246b74c45 Mon Sep 17 00:00:00 2001
From: hamshkhawar <hamdahshafqat@hotmail.com>
Date: Thu, 18 Jan 2024 07:50:32 -0600
Subject: [PATCH] created plugin structure

---
 .../package-release.sh                        |  16 ++
 .../feature-subsetting-plugin/run-docker.sh   |  23 +++
 .../clustering/feature_subsetting/__init__.py |   2 +
 .../clustering/feature_subsetting/__main__.py | 156 ++++++++++++++++++
 .../feature_subsetting/feature_subset.py}     |   1 +
 .../tests/__init__.py                         |   0
 .../tests/conftest.py                         |   0
 .../tests/test_cli.py                         |   0
 .../tests/test_feature_subsetting.py          |   0
 9 files changed, 198 insertions(+)
 create mode 100644 clustering/feature-subsetting-plugin/src/polus/plugins/clustering/feature_subsetting/__init__.py
 create mode 100644 clustering/feature-subsetting-plugin/src/polus/plugins/clustering/feature_subsetting/__main__.py
 rename clustering/feature-subsetting-plugin/src/{main.py => polus/plugins/clustering/feature_subsetting/feature_subset.py} (99%)
 create mode 100644 clustering/feature-subsetting-plugin/tests/__init__.py
 create mode 100644 clustering/feature-subsetting-plugin/tests/conftest.py
 create mode 100644 clustering/feature-subsetting-plugin/tests/test_cli.py
 create mode 100644 clustering/feature-subsetting-plugin/tests/test_feature_subsetting.py

diff --git a/clustering/feature-subsetting-plugin/package-release.sh b/clustering/feature-subsetting-plugin/package-release.sh
index e69de29bb..8e53414b9 100644
--- a/clustering/feature-subsetting-plugin/package-release.sh
+++ b/clustering/feature-subsetting-plugin/package-release.sh
@@ -0,0 +1,16 @@
+# This script is designed to help package a new version of a plugin
+
+# Get the new version
+version=$(<VERSION)
+
+# Bump the version
+bump2version --config-file bumpversion.cfg --new-version ${version} --allow-dirty part
+
+# Build the container
+./build-docker.sh
+
+# Push to dockerhub
+docker push polusai/feature-subsetting-plugin:${version}
+
+# Run pytests
+python -m pytest -s tests
\ No newline at end of file
diff --git a/clustering/feature-subsetting-plugin/run-docker.sh b/clustering/feature-subsetting-plugin/run-docker.sh
index e69de29bb..ced143837 100644
--- a/clustering/feature-subsetting-plugin/run-docker.sh
+++ b/clustering/feature-subsetting-plugin/run-docker.sh
@@ -0,0 +1,23 @@
+#!/bin/bash
+
+version=$(<VERSION)
+datapath=$(readlink --canonicalize data)
+echo ${datapath}
+
+# Inputs
+inpDir=${datapath}/input
+filePattern=".*.csv"
+groupingPattern="\w+$"
+labelCol="species"
+minClusterSize=3
+outDir=${datapath}/output
+
+docker run -v ${datapath}:${datapath} \
+            polusai/hdbscan-clustering-plugin:${version} \
+            --inpDir ${inpDir} \
+            --filePattern ${filePattern} \
+            --groupingPattern ${groupingPattern} \
+            --labelCol ${labelCol} \
+            --minClusterSize ${minClusterSize} \
+            --incrementOutlierId \
+            --outDir ${outDir} 
\ No newline at end of file
diff --git a/clustering/feature-subsetting-plugin/src/polus/plugins/clustering/feature_subsetting/__init__.py b/clustering/feature-subsetting-plugin/src/polus/plugins/clustering/feature_subsetting/__init__.py
new file mode 100644
index 000000000..90db17247
--- /dev/null
+++ b/clustering/feature-subsetting-plugin/src/polus/plugins/clustering/feature_subsetting/__init__.py
@@ -0,0 +1,2 @@
+"""Feature Subsetting Plugin."""
+__version__ = "0.2.0-dev"
\ No newline at end of file
diff --git a/clustering/feature-subsetting-plugin/src/polus/plugins/clustering/feature_subsetting/__main__.py b/clustering/feature-subsetting-plugin/src/polus/plugins/clustering/feature_subsetting/__main__.py
new file mode 100644
index 000000000..4402091d6
--- /dev/null
+++ b/clustering/feature-subsetting-plugin/src/polus/plugins/clustering/feature_subsetting/__main__.py
@@ -0,0 +1,156 @@
+"""Hdbscan Clustering Plugin."""
+
+import json
+import logging
+from multiprocessing import cpu_count
+from pathlib import Path
+from typing import Any
+from typing import Optional
+
+import filepattern as fp
+import polus.plugins.clustering.feature_subsetting.feature_subset as fs
+import preadator
+import typer
+from tqdm import tqdm
+
+app = typer.Typer()
+
+# Initialize the logger
+logging.basicConfig(
+    format="%(asctime)s - %(name)-8s - %(levelname)-8s - %(message)s",
+    datefmt="%d-%b-%y %H:%M:%S",
+)
+logger = logging.getLogger("polus.plugins.clustering.feature_subsetting")
+logger.setLevel(logging.INFO)
+
+
+@app.command()
+def main(  # noqa: PLR0913
+    inp_dir: Path = typer.Option(
+        ...,
+        "--inpDir",
+        "-i",
+        help="Path to folder with tabular files",
+    ),
+    file_pattern: Optional[str] = typer.Option(
+        ".*",
+        "--filePattern",
+        "-f",
+        help="Pattern use to parse filenames",
+    ),
+    grouping_pattern: Optional[str] = typer.Option(
+        None,
+        "--groupingPattern",
+        "-g",
+        help="Regular expression to group rows to capture groups.",
+    ),
+    average_groups: Optional[bool] = typer.Option(
+        False,
+        "--averageGroups",
+        "-a",
+        help="Whether to average data across groups. Requires capture groups.",
+    ),
+    label_col: Optional[str] = typer.Option(
+        None,
+        "--labelCol",
+        "-l",
+        help="Name of column containing labels. Required only for grouping operations.",
+    ),
+    min_cluster_size: int = typer.Option(
+        ...,
+        "--minClusterSize",
+        "-m",
+        help="Minimum cluster size.",
+    ),
+    increment_outlier_id: Optional[bool] = typer.Option(
+        False,
+        "--incrementOutlierId",
+        "-io",
+        help="Increments outlier ID to 1.",
+    ),
+    out_dir: Path = typer.Option(
+        ...,
+        "--outDir",
+        "-o",
+        help="Output directory",
+    ),
+    preview: Optional[bool] = typer.Option(
+        False,
+        "--preview",
+        help="Output a JSON preview of files",
+    ),
+) -> None:
+    """Cluster data using HDBSCAN."""
+    logger.info(f"--inpDir = {inp_dir}")
+    logger.info(f"--filePattern = {file_pattern}")
+    # Regular expression for grouping.
+    logger.info(f"--groupingPattern = {grouping_pattern}")
+    # Whether to average data for each group.
+    logger.info(f"--averageGroups = {average_groups}")
+    # Name of column to use for grouping.
+    logger.info(f"--labelCol = {label_col}")
+    # Minimum cluster size for clustering using HDBSCAN.
+    logger.info(f"--minClusterSize = {min_cluster_size}")
+    # Set outlier cluster id as 1.
+    logger.info(f"--incrementOutlierId = {increment_outlier_id}")
+    logger.info(f"--outDir = {out_dir}")
+
+    inp_dir = inp_dir.resolve()
+    out_dir = out_dir.resolve()
+
+    assert inp_dir.exists(), f"{inp_dir} does not exist!! Please check input path again"
+    assert (
+        out_dir.exists()
+    ), f"{out_dir} does not exist!! Please check output path again"
+
+    num_workers = max([cpu_count(), 2])
+
+    files = fp.FilePattern(inp_dir, file_pattern)
+
+    if files is None:
+        msg = f"No tabular files found. Please check {file_pattern} again"
+        raise ValueError(msg)
+
+    if preview:
+        with Path.open(Path(out_dir, "preview.json"), "w") as jfile:
+            out_json: dict[str, Any] = {
+                "filepattern": file_pattern,
+                "outDir": [],
+            }
+            for file in files():
+                out_name = file[1][0].name.replace(
+                    "".join(file[1][0].suffixes),
+                    f"_hdbscan{hd.POLUS_TAB_EXT}",
+                )
+                out_json["outDir"].append(out_name)
+            json.dump(out_json, jfile, indent=2)
+    else:
+        with preadator.ProcessManager(
+            name="Cluster data using HDBSCAN",
+            num_processes=num_workers,
+            threads_per_process=2,
+        ) as pm:
+            for file in tqdm(
+                files(),
+                total=len(files()),
+                desc="Clustering data",
+                mininterval=5,
+                initial=0,
+                unit_scale=True,
+                colour="cyan",
+            ):
+                pm.submit_process(
+                    hd.hdbscan_clustering,
+                    file[1][0],
+                    min_cluster_size,
+                    out_dir,
+                    grouping_pattern,
+                    label_col,
+                    average_groups,
+                    increment_outlier_id,
+                )
+            pm.join_processes()
+
+
+if __name__ == "__main__":
+    app()
\ No newline at end of file
diff --git a/clustering/feature-subsetting-plugin/src/main.py b/clustering/feature-subsetting-plugin/src/polus/plugins/clustering/feature_subsetting/feature_subset.py
similarity index 99%
rename from clustering/feature-subsetting-plugin/src/main.py
rename to clustering/feature-subsetting-plugin/src/polus/plugins/clustering/feature_subsetting/feature_subset.py
index a942d67c2..ccc179e74 100644
--- a/clustering/feature-subsetting-plugin/src/main.py
+++ b/clustering/feature-subsetting-plugin/src/polus/plugins/clustering/feature_subsetting/feature_subset.py
@@ -1,3 +1,4 @@
+"""Feature Subsetting Plugin."""
 import argparse, logging, subprocess, time, multiprocessing, sys
 import os
 import filepattern
diff --git a/clustering/feature-subsetting-plugin/tests/__init__.py b/clustering/feature-subsetting-plugin/tests/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/clustering/feature-subsetting-plugin/tests/conftest.py b/clustering/feature-subsetting-plugin/tests/conftest.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/clustering/feature-subsetting-plugin/tests/test_cli.py b/clustering/feature-subsetting-plugin/tests/test_cli.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/clustering/feature-subsetting-plugin/tests/test_feature_subsetting.py b/clustering/feature-subsetting-plugin/tests/test_feature_subsetting.py
new file mode 100644
index 000000000..e69de29bb