Merge branch 'master' into development

Steinbeck-Lab · Feb 15, 2024 · 8e2046d · 8e2046d
2 parents 7bd9601 + c990944
commit 8e2046d
Show file tree

Hide file tree

Showing 13 changed files with 630 additions and 615 deletions.
diff --git a/.github/workflows/check_errors_and_test.yml b/.github/workflows/check_errors_and_test.yml
@@ -0,0 +1,47 @@
+# This is a basic workflow to help you get started with Actions
+
+name: Error checking and testing
+
+# Controls when the workflow will run
+on:
+  # Triggers the workflow on push or pull request events but only for the main branch
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+
+# A workflow run is made up of one or more jobs that can run sequentially or in parallel
+jobs:
+
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.10']
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v1
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install basic dependencies
+        run: |
+          python -m pip install --upgrade pip
+      - name: Test with tox
+        run: |
+          pip install -e .
+          pip install tox
+          tox
+
+  release-please:
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - uses: google-github-actions/release-please-action@v3
+        with:
+          release-type: python
+          package-name: release-please-action
+          token: ${{ secrets.RELEASE_PLEASE_TOKEN }}
+          start-version: '1.1.4'
diff --git a/.github/workflows/pypi_release.yml b/.github/workflows/pypi_release.yml
@@ -0,0 +1,25 @@
+name: Publish Python distributions to PyPI
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+jobs:
+  build-n-publish:
+    name: Build and publish Python distributions to PyPI
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@master
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.10'
+    - name: Install pypa/setuptools
+      run: python -m pip install wheel
+    - name: Build a binary wheel
+      run: python setup.py sdist bdist_wheel
+    - name: Publish distribution to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        password: ${{ secrets.PYPI_API_TOKEN }}
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -0,0 +1,78 @@
+# Changelog
+
+## [1.3.0](https://github.com/Kohulan/DECIMER-Image-Segmentation/compare/v1.2.5...v1.3.0) (2023-11-20)
+
+
+### Features
+
+* delete more deprecated mask expansion code ([45e0b97](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/45e0b970f3cf1c0b89421c478bc9a6ce23bd0217))
+* delete tests of deleted functions ([99d1b38](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/99d1b3849aba7abe7588d489486f4862ebd158f4))
+* new seed pixel determination ([2ef9a5e](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/2ef9a5e7e406407b09e1197f1c0defc2be1250bb))
+* remove deprecated expansion code ([1ca862f](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/1ca862f0237134b935d5d32151129d0045057f4c))
+* speed-up scikit-image and avoiding loops ([fd874a3](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/fd874a34ec9045b8ab116c34f1821479397e5e10))
+* Update demonstration notebook ([e648541](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/e6485410fcebe72ef50b26d4a335d151db42de67))
+* update dependencies ([60358c9](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/60358c9f9cc4fd29184d78c84718cb454b8cbfaf))
+* Update link to download new model ([28c3397](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/28c33975d1538f6920321f03cc638d38e96f7dd9))
+
+
+### Bug Fixes
+
+* table line exlusion with connected object detection ([e2f38d7](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/e2f38d7b646fefc39b3401d49fd9a54707ddeb20))
+* tests for mask expansion ([3ec8239](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/3ec8239db46b1d92faa89a15e3e1319462f04502))
+* update model link README.md ([c5b2cd3](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/c5b2cd3d04133aeaee41ee9fb6a0d263154abb7e))
+
+## [1.2.5](https://github.com/Kohulan/DECIMER-Image-Segmentation/compare/v1.2.4...v1.2.5) (2023-10-19)
+
+
+### Bug Fixes
+
+* adapt seed pixel determination test according to changes ([337775d](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/337775d34b536ee79aa63e7b0153aae7c49b229d))
+* do not return empty segments ([f1deb46](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/f1deb4606627fd96c43ec8527c5287e0823f5905))
+* don't use pixels from exclusion mask as seed pixels ([fe96aa9](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/fe96aa91af94c2c8b650ae8d3215a3b497af7469))
+
+## [1.2.4](https://github.com/Kohulan/DECIMER-Image-Segmentation/compare/v1.2.3...v1.2.4) (2023-10-19)
+
+
+### Bug Fixes
+
+* expansion crash when no structures have been detected [#95](https://github.com/Kohulan/DECIMER-Image-Segmentation/issues/95) ([1242a67](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/1242a676de2ba970d074be151b8b1865b608f8d5))
+
+## [1.2.3](https://github.com/Kohulan/DECIMER-Image-Segmentation/compare/v1.2.2...v1.2.3) (2023-09-21)
+
+
+### Bug Fixes
+
+* test-commit ([33fd1b7](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/33fd1b70cc021aac0334e29cf85c312ea50fd42f))
+
+## [1.2.2](https://github.com/Kohulan/DECIMER-Image-Segmentation/compare/v1.2.1...v1.2.2) (2023-09-21)
+
+
+### Bug Fixes
+
+* remove wrong version specification ([b997b43](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/b997b43c7cbb1f581f576a3a6e4fc50fc8aeb2d4))
+* stable version specification for ([22b1a51](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/22b1a51a1e90c0b10848cbddbf03a0852548afc3))
+* trigger pypi release on release ([7b1eb37](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/7b1eb37efe32473e4268205953aa82d3c3e5518f))
+
+## [1.2.1](https://github.com/Kohulan/DECIMER-Image-Segmentation/compare/v1.2.0...v1.2.1) (2023-09-21)
+
+
+### Bug Fixes
+
+* GH action for pypi releases ([ce4c3b9](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/ce4c3b940d4c9763f6fb352c7cc4bf5895185d2a))
+
+## [1.2.0](https://github.com/Kohulan/DECIMER-Image-Segmentation/compare/1.1.4...v1.2.0) (2023-09-19)
+
+
+### Features
+
+* adaptive line kernel based on structure size ([2f2fe8e](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/2f2fe8e350b6f88eeda2fa9d2c20967283ef0bb6))
+* function to get mean size from bboxes ([70a5b2b](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/70a5b2b66a29dda2e63308e0c24b57093eaefb76))
+* GH Action for automated Pypi releases ([dbc55f6](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/dbc55f64ba91899b542ffe5e007ae23ba570d892))
+
+
+### Bug Fixes
+
+* formatted with black ([b7c7417](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/b7c74173fa62f7f5a880fe85069a7942783d296a))
+* linter appeasement ([79c89ca](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/79c89ca4898edca0ad0552ae6681d379198fa426))
+* lower relative threshold for kernel for line detection ([1aa4deb](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/1aa4debe8557e8ef379db0b52823e8f5d0dd1ed8))
+* max instead of mean structure size for line kernels ([227c452](https://github.com/Kohulan/DECIMER-Image-Segmentation/commit/227c4527cfeb5407daa7b041eb221ff5913420f8))
diff --git a/CITATION.cff b/CITATION.cff
@@ -19,7 +19,7 @@ authors:
 
 
 title: "DECIMER-Image-Segmentation"
-version: 1.1.1
+version: 1.3.0
 doi: 10.5281/zenodo.7299334
 date-released: 2021-05-03
 url: "https://github.com/OBrink/DECIMER-Image-Segmentation"

diff --git a/DECIMER_Segmentation_notebook.ipynb b/DECIMER_Segmentation_notebook.ipynb
diff --git a/README.md b/README.md
@@ -41,7 +41,7 @@ $ conda install -c conda-forge poppler
 $ pip install decimer-segmentation
 ```
 
-### The Mask-RCNN Model is available at: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.7228583.svg)](https://doi.org/10.5281/zenodo.7228583)
+### The Mask-RCNN Model is available at: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.10142866.svg)](https://doi.org/10.5281/zenodo.10142866)
 
 ## How to use DECIMER-Segmentation
 - The repository contains a script that can be used for the segmentation of chemical structures from an image of a scanned page or from a pdf document:

diff --git a/Validation/visualization.ipynb b/Validation/visualization.ipynb
@@ -131,47 +131,67 @@
     "def weighted_average(array, weights):\n",
     "    average = 0\n",
     "    for n in range(len(array)):\n",
-    "        average += array[n]*weights[n]/sum(weights)\n",
+    "        average += array[n] * weights[n] / sum(weights)\n",
     "    return average\n",
-    "        \n",
+    "\n",
+    "\n",
     "journals = np.array([\"Molecules\", \"Phytochemistry\", \"J. Nat. Prod\"])\n",
-    "sum_of_all_structures = np.array([396+33, 182+29, 306+24]) # real amount of structures\n",
+    "sum_of_all_structures = np.array(\n",
+    "    [396 + 33, 182 + 29, 306 + 24]\n",
+    ")  # real amount of structures\n",
     "complete_structures_only_model = np.array([321, 152, 250])\n",
     "complete_structures = np.array([396, 182, 306])\n",
     "recognized_structures = np.array([398, 182, 306])\n",
     "too_much_only_model = [44, 10, 29]\n",
     "too_much = [50, 21, 29]\n",
     "\n",
-    "recognized_structure_proportions = recognized_structures/sum_of_all_structures\n",
-    "complete_structures_only_model_proportions = complete_structures_only_model/recognized_structures\n",
-    "complete_structures_proportions = complete_structures/recognized_structures\n",
+    "recognized_structure_proportions = recognized_structures / sum_of_all_structures\n",
+    "complete_structures_only_model_proportions = (\n",
+    "    complete_structures_only_model / recognized_structures\n",
+    ")\n",
+    "complete_structures_proportions = complete_structures / recognized_structures\n",
     "too_much_only_model_proportions = too_much_only_model / recognized_structures\n",
     "too_much_proportions = too_much / recognized_structures\n",
     "\n",
     "\n",
-    "df_array= np.array([journals, \n",
-    "                    recognized_structure_proportions,\n",
-    "                   complete_structures_only_model_proportions,\n",
-    "                   complete_structures_proportions,\n",
-    "                   too_much_only_model_proportions,\n",
-    "                   too_much_proportions])\n",
+    "df_array = np.array(\n",
+    "    [\n",
+    "        journals,\n",
+    "        recognized_structure_proportions,\n",
+    "        complete_structures_only_model_proportions,\n",
+    "        complete_structures_proportions,\n",
+    "        too_much_only_model_proportions,\n",
+    "        too_much_proportions,\n",
+    "    ]\n",
+    ")\n",
     "\n",
-    "labels = np.array([[\"Journals\"],\n",
-    "                   [\"Proportion of recognized structures\"], \n",
-    "                    [\"Complete structures (only model) (proportions)\"],\n",
-    "                   [\"Complete structures (proportions)\"],\n",
-    "                  [\"too much (only model) (proportions)\"],\n",
-    "                  [\"too much (proportions)\"]])\n",
+    "labels = np.array(\n",
+    "    [\n",
+    "        [\"Journals\"],\n",
+    "        [\"Proportion of recognized structures\"],\n",
+    "        [\"Complete structures (only model) (proportions)\"],\n",
+    "        [\"Complete structures (proportions)\"],\n",
+    "        [\"too much (only model) (proportions)\"],\n",
+    "        [\"too much (proportions)\"],\n",
+    "    ]\n",
+    ")\n",
     "\n",
-    "weighted_averages = np.array([[\"Weighted average\"],\n",
-    "                             [weighted_average(recognized_structure_proportions, sum_of_all_structures)],\n",
-    "                             [weighted_average(complete_structures_only_model_proportions, recognized_structures)],\n",
-    "                             [weighted_average(complete_structures_proportions, recognized_structures)],\n",
-    "                             [weighted_average(too_much_only_model_proportions, recognized_structures)],\n",
-    "                             [weighted_average(too_much_proportions, recognized_structures)]])\n",
+    "weighted_averages = np.array(\n",
+    "    [\n",
+    "        [\"Weighted average\"],\n",
+    "        [weighted_average(recognized_structure_proportions, sum_of_all_structures)],\n",
+    "        [\n",
+    "            weighted_average(\n",
+    "                complete_structures_only_model_proportions, recognized_structures\n",
+    "            )\n",
+    "        ],\n",
+    "        [weighted_average(complete_structures_proportions, recognized_structures)],\n",
+    "        [weighted_average(too_much_only_model_proportions, recognized_structures)],\n",
+    "        [weighted_average(too_much_proportions, recognized_structures)],\n",
+    "    ]\n",
+    ")\n",
     "\n",
-    "pd.DataFrame(np.concatenate((labels, df_array, weighted_averages), axis = 1)).round(1)\n",
-    "\n"
+    "pd.DataFrame(np.concatenate((labels, df_array, weighted_averages), axis=1)).round(1)"
    ]
   },
   {
@@ -193,35 +213,57 @@
     }
    ],
    "source": [
-    "# This plot has been created according to the tutorial on \n",
+    "# This plot has been created according to the tutorial on\n",
     "# https://matplotlib.org/gallery/lines_bars_and_markers/barchart.html#sphx-glr-gallery-lines-bars-and-markers-barchart-py\n",
-    "#height = [306*100/331, 295*100/306, 183*100/206, 177*100/183, 398*100/403, 387*100/398]\n",
-    "labels = ('Molecules', 'Phytochemistry', 'J. Nat. Prod.')\n",
+    "# height = [306*100/331, 295*100/306, 183*100/206, 177*100/183, 398*100/403, 387*100/398]\n",
+    "labels = (\"Molecules\", \"Phytochemistry\", \"J. Nat. Prod.\")\n",
     "x = np.arange(len(labels))  # label locations\n",
     "width = 0.25  # width of the bars\n",
     "\n",
     "fig, ax = plt.subplots()\n",
-    "rects1 = ax.bar(x - width, complete_structures_proportions*100, width, label=\"Proportion of segments with complete chemical structures        \", color = \"#D7FA64\")\n",
-    "rects2 = ax.bar(x, recognized_structure_proportions*100, width, label=\"Proportion of recognized structure depictions\", color = \"#7DAFFA\")\n",
-    "rects3 = ax.bar(x + width, too_much_proportions*100, width, label=\"Proportion of segments with additional elements\", color = \"#F27D6D\")\n",
+    "rects1 = ax.bar(\n",
+    "    x - width,\n",
+    "    complete_structures_proportions * 100,\n",
+    "    width,\n",
+    "    label=\"Proportion of segments with complete chemical structures        \",\n",
+    "    color=\"#D7FA64\",\n",
+    ")\n",
+    "rects2 = ax.bar(\n",
+    "    x,\n",
+    "    recognized_structure_proportions * 100,\n",
+    "    width,\n",
+    "    label=\"Proportion of recognized structure depictions\",\n",
+    "    color=\"#7DAFFA\",\n",
+    ")\n",
+    "rects3 = ax.bar(\n",
+    "    x + width,\n",
+    "    too_much_proportions * 100,\n",
+    "    width,\n",
+    "    label=\"Proportion of segments with additional elements\",\n",
+    "    color=\"#F27D6D\",\n",
+    ")\n",
     "\n",
     "# Add some text for labels, title and custom x-axis tick labels, etc.\n",
-    "ax.set_ylabel('Percentage (%)')\n",
+    "ax.set_ylabel(\"Percentage (%)\")\n",
     "ax.set_xticks(x)\n",
     "ax.set_xticklabels(labels)\n",
     "ax.legend()\n",
-    "ax.set_ylim(0,140)\n",
+    "ax.set_ylim(0, 140)\n",
+    "\n",
     "\n",
     "def autolabel(rects):\n",
     "    \"\"\"Attach a text label above each bar in *rects*, displaying its height.\"\"\"\n",
     "    for rect in rects:\n",
     "        height = rect.get_height()\n",
     "        height = round(height, 1)\n",
-    "        ax.annotate('{}'.format(height),\n",
-    "                    xy=(rect.get_x() + rect.get_width() / 2, height),\n",
-    "                    xytext=(0, 3),  # 3 points vertical offset\n",
-    "                    textcoords=\"offset points\",\n",
-    "                    ha='center', va='bottom')\n",
+    "        ax.annotate(\n",
+    "            \"{}\".format(height),\n",
+    "            xy=(rect.get_x() + rect.get_width() / 2, height),\n",
+    "            xytext=(0, 3),  # 3 points vertical offset\n",
+    "            textcoords=\"offset points\",\n",
+    "            ha=\"center\",\n",
+    "            va=\"bottom\",\n",
+    "        )\n",
     "\n",
     "\n",
     "autolabel(rects1)\n",

diff --git a/decimer_segmentation/__init__.py b/decimer_segmentation/__init__.py
@@ -7,10 +7,10 @@
 
 
 For comments, bug reports or feature requests,
-please raise a issue on our Github repository.
+please raise an issue on our GitHub repository.
 """
 
-__version__ = "1.1.3"
+__version__ = "1.3.0"
 
 __all__ = [
     "decimer_segmentation",