Merge pull request #370 from OpenCOMPES/notebook_rework

Fix documentation and update workflows

.github/workflows/benchmark.yml

@@ -5,6 +5,8 @@ on:
     workflow_dispatch:
     push:
         branches: [ main, create-pull-request/patch ]
+        paths-ignore:
+          pyproject.toml
 
 jobs:
   benchmark:

.github/workflows/documentation.yml

@@ -99,10 +99,10 @@ jobs:
         run: poetry run sphinx-build -b html $GITHUB_WORKSPACE/docs $GITHUB_WORKSPACE/_build
 
       - name: Setup Pages
-        uses: actions/configure-pages@v3
+        uses: actions/configure-pages@v4
 
       - name: Upload artifact
-        uses: actions/upload-pages-artifact@v2
+        uses: actions/upload-pages-artifact@v3
         with:
           path: '_build'
 
@@ -116,4 +116,4 @@ jobs:
     steps:
       - name: Deploy to GitHub Pages
         id: deployment
-        uses: actions/deploy-pages@v2
+        uses: actions/deploy-pages@v4

.github/workflows/linting.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       # Check out repo and set up Python
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           lfs: true
 

.github/workflows/release.yml

@@ -25,7 +25,7 @@ jobs:
     outputs:
       version: ${{ steps.version.outputs.version }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           lfs: true
           path: 'sed-processor'
@@ -68,7 +68,7 @@ jobs:
     outputs:
       version: ${{ steps.version.outputs.version }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           lfs: true
           path: 'sed-processor'
@@ -120,11 +120,11 @@ jobs:
 
     steps:
       - name: Download a single artifact
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: dist
 
-      - name: Publish package distributions to PyPI Test
+      - name: Publish package distributions to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           packages-dir: .
@@ -141,13 +141,13 @@ jobs:
           app-id: ${{ secrets.APP_ID }}
           private-key: ${{ secrets.APP_PRIVATE_KEY }}
 
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           lfs: true
           token: ${{ steps.generate_token.outputs.token }}
 
       - name: Download pyproject.toml
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: pyproject
 

.github/workflows/update_dependencies.yml

@@ -14,7 +14,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       # Check out repo and set up Python
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           lfs: true
 

.gitignore

@@ -7,7 +7,7 @@
 *.nx
 *.nxs
 *.zip
-**/parquet/*
+**/processed/*
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

docs/build_flash_parquets.py

@@ -24,7 +24,7 @@
     "core": {
         "paths": {
             "data_raw_dir": data_path + "/flash_data/",
-            "data_parquet_dir": data_path + "/parquet/",
+            "data_parquet_dir": data_path + "/processed/",
         },
     },
 }

tutorial/1_binning_fake_data.ipynb

@@ -7,7 +7,7 @@
     "tags": []
    },
    "source": [
-    "### Binning demonstration on locally generated fake data\n",
+    "# Binning demonstration on locally generated fake data\n",
     "In this example, we generate a table with random data simulating a single event dataset.\n",
     "We showcase the binning method, first on a simple single table using the bin_partition method and then in the distributed mehthod bin_dataframe, using daks dataframes.\n",
     "The first method is never really called directly, as it is simply the function called by the bin_dataframe on each partition of the dask dataframe."
@@ -136,7 +136,7 @@
    "id": "01066d40-010a-490b-9033-7339e5a21b26",
    "metadata": {},
    "source": [
-    "## compute distributed binning on the partitioned dask dataframe\n",
+    "## Compute distributed binning on the partitioned dask dataframe\n",
     "In this example, the small dataset does not give significant improvement over the pandas implementation, at least using this number of partitions.\n",
     "A single partition would be faster (you can try...) but we use multiple for demonstration purpouses."
    ]

tutorial/2_conversion_pipeline_for_example_time-resolved_ARPES_data.ipynb

@@ -286,7 +286,7 @@
    "id": "1a3697b1",
    "metadata": {},
    "source": [
-    "##### Optional (Step 1a): \n",
+    "#### Optional (Step 1a): \n",
     "Save momentum calibration parameters to configuration file in current data folder: "
    ]
   },
@@ -359,7 +359,7 @@
    "id": "e43fbf33",
    "metadata": {},
    "source": [
-    "##### Optional (Step 1a): \n",
+    "#### Optional (Step 1a): \n",
     "Save energy correction parameters to configuration file in current data folder: "
    ]
   },
@@ -489,7 +489,7 @@
    "id": "df63c6c7",
    "metadata": {},
    "source": [
-    "##### Optional (Step 3a): \n",
+    "#### Optional (Step 3a): \n",
     "Save energy calibration parameters to configuration file in current data folder: "
    ]
   },

tutorial/4_hextof_workflow.ipynb

@@ -130,7 +130,6 @@
     "config_override['core']['paths']['data_parquet_dir'] = \"/asap3/flash/gpfs/pg2/2023/data/11019101/processed\"\n",
     "# So we write to user space\n",
     "config_override['core']['paths']['data_parquet_dir'] = \"./processed\"\n",
-    "os.mkdir(config_override['core']['paths']['data_parquet_dir'])\n",
     "# If you didn't download data and are using maxwell, don't use this line\n",
     "config_override['core']['paths']['data_raw_dir'] = \"./flash_data/\""
    ]
@@ -975,9 +974,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "sed_poetry",
+   "display_name": ".pyenv",
    "language": "python",
-   "name": "sed_poetry"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -989,7 +988,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.6"
+   "version": "3.8.12"
   }
  },
  "nbformat": 4,