feat: Add BaseWriter, and example NIFTIWriter with notebooks documenting them

config/ruff.toml

@@ -5,6 +5,7 @@ include = [
   "src/readii/loaders.py",
   "src/readii/feature_extraction.py",
   "src/readii/negative_controls_refactor/**.py",
+  "src/readii/io/writers/**.py",
 ]
 
 # extend-exclude is used to exclude directories from the flake8 checks
@@ -15,7 +16,9 @@ extend-exclude = [
   "src/readii/image_processing.py",
   "src/readii/metadata.py",
   "src/readii/negative_controls.py",
-  "src/readii/pipeline.py",]
+  "src/readii/pipeline.py",
+  "notebooks/*",
+]
 
 # Same as Black.
 line-length = 100

notebooks/nifti_writer_example.ipynb

@@ -0,0 +1,178 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from readii.io.writers.nifti_writer import NIFTIWriter\n",
+    "from readii.io.writers.base_writer import BaseWriter\n",
+    "from pathlib import Path\n",
+    "import subprocess\n",
+    "import SimpleITK as sitk\n",
+    "import pandas as pd\n",
+    "import uuid\n",
+    "import random\n",
+    "import sys\n",
+    "from readii.utils import logger\n",
+    "\n",
+    "# copy this writer from the other notebook:\n",
+    "class CSVWriter(BaseWriter): # noqa\n",
+    "\n",
+    "  # The save method is the only method that needs to be implemented for the subclasses of BaseWriter\n",
+    "  def save(self, data: list, **kwargs) -> Path:  # noqa\n",
+    "    output_path = self.resolve_path(**kwargs)\n",
+    "    with output_path.open('w') as f: # noqa\n",
+    "      pd.DataFrame(data).to_csv(f, index=False)\n",
+    "    return output_path\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "TRASH/writer_examples/nifti_writer_examples/\n",
+      "├── PatientID-AliceSmith/\n",
+      "│   └── Study-Study003/\n",
+      "│       ├── CT_SeriesUID-13278.nii.gz\n",
+      "│       ├── CT_SeriesUID-13278_metadata.csv\n",
+      "│       ├── RTSTRUCT_SeriesUID-39256.nii.gz\n",
+      "│       └── RTSTRUCT_SeriesUID-39256_metadata.csv\n",
+      "├── PatientID-JaneDoe/\n",
+      "│   └── Study-Study002/\n",
+      "│       ├── CT_SeriesUID-24592.nii.gz\n",
+      "│       ├── CT_SeriesUID-24592_metadata.csv\n",
+      "│       ├── RTSTRUCT_SeriesUID-42098.nii.gz\n",
+      "│       └── RTSTRUCT_SeriesUID-42098_metadata.csv\n",
+      "└── PatientID-JohnAdams/\n",
+      "    └── Study-Study001/\n",
+      "        ├── CT_SeriesUID-93810.nii.gz\n",
+      "        ├── CT_SeriesUID-93810_metadata.csv\n",
+      "        ├── RTSTRUCT_SeriesUID-46048.nii.gz\n",
+      "        └── RTSTRUCT_SeriesUID-46048_metadata.csv\n",
+      "\n",
+      "7 directories, 12 files\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "ROOT_DIRECTORY = Path(\"TRASH\", \"writer_examples\", \"nifti_writer_examples\")\n",
+    "FILENAME_FORMAT = \"PatientID-{PatientID}/Study-{Study}/{Modality}_SeriesUID-{SeriesUID}\"\n",
+    "\n",
+    "data_sets = []\n",
+    "random.seed(42)  # Set random seed for reproducibility\n",
+    "\n",
+    "random_5d = lambda: random.randint(10000, 99999)\n",
+    "\n",
+    "for MODALITY in [\"CT\", \"RTSTRUCT\"]:\n",
+    "  data_sets.extend([\n",
+    "    {\n",
+    "      \"image\": sitk.Image(10, 10, 10, sitk.sitkInt16),\n",
+    "      \"metadata\": pd.DataFrame({\"PatientID\": [\"JohnAdams\"], \"Study\": [\"Study001\"]}),\n",
+    "      \"PatientID\": \"JohnAdams\",\n",
+    "      \"Study\": \"Study001\",\n",
+    "      \"Modality\": MODALITY,\n",
+    "      \"SeriesUID\": random_5d(),\n",
+    "    },\n",
+    "    {\n",
+    "      \"image\": sitk.Image(20, 20, 20, sitk.sitkInt16),\n",
+    "      \"metadata\": pd.DataFrame({\"PatientID\": [\"JaneDoe\"], \"Study\": [\"Study002\"]}),\n",
+    "      \"PatientID\": \"JaneDoe\",\n",
+    "      \"Study\": \"Study002\",\n",
+    "      \"Modality\": MODALITY,\n",
+    "      \"SeriesUID\": random_5d(),\n",
+    "    },\n",
+    "    {\n",
+    "      \"image\": sitk.Image(30, 30, 30, sitk.sitkInt16),\n",
+    "      \"metadata\": pd.DataFrame({\"PatientID\": [\"AliceSmith\"], \"Study\": [\"Study003\"]}),\n",
+    "      \"PatientID\": \"AliceSmith\",\n",
+    "      \"Study\": \"Study003\",\n",
+    "      \"Modality\": MODALITY,\n",
+    "      \"SeriesUID\": random_5d(),\n",
+    "    }\n",
+    "  ])\n",
+    "\n",
+    "# Create a writer with the specified root directory and filename format\n",
+    "with (\n",
+    "  NIFTIWriter(\n",
+    "    root_directory=ROOT_DIRECTORY, \n",
+    "    filename_format=f\"{FILENAME_FORMAT}.nii.gz\",\n",
+    "    overwrite=True\n",
+    "  ) as nifti_writer,\n",
+    "  CSVWriter(\n",
+    "    root_directory=ROOT_DIRECTORY, \n",
+    "    filename_format=f\"{FILENAME_FORMAT}_metadata.csv\"\n",
+    "  ) as metadata_writer\n",
+    "):\n",
+    "  # Iterate over the data sets and save them\n",
+    "  for data_set in data_sets:\n",
+    "\n",
+    "    # The actual data being saved is image or data, but the rest of the kwargs are \n",
+    "    # only for resolving the filename\n",
+    "    try:\n",
+    "      nifti_writer.save(\n",
+    "        image=data_set[\"image\"],\n",
+    "        PatientID=data_set[\"PatientID\"],\n",
+    "        Study=data_set[\"Study\"],\n",
+    "        Modality=data_set[\"Modality\"],\n",
+    "        SeriesUID=data_set[\"SeriesUID\"]\n",
+    "      )\n",
+    "      metadata_writer.save(\n",
+    "        data=data_set[\"metadata\"],\n",
+    "        PatientID=data_set[\"PatientID\"],\n",
+    "        Study=data_set[\"Study\"],\n",
+    "        Modality=data_set[\"Modality\"],\n",
+    "        SeriesUID=data_set[\"SeriesUID\"]\n",
+    "      )\n",
+    "    except FileExistsError as e:\n",
+    "      logger.exception(f\"Error saving data set: {e}\")\n",
+    "      sys.exit(1)\n",
+    "\n",
+    "output = subprocess.check_output([\"tree\", \"-nF\", ROOT_DIRECTORY])\n",
+    "print(output.decode(\"utf-8\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "dev",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}