Merge remote-tracking branch 'origin/main' into v1_feature_branch

.github/workflows/benchmark.yml

@@ -34,7 +34,10 @@ jobs:
       - name: Install project dependencies
         run: poetry install
 
-      # Run benchmakrs
+      - name: Install project dependencies
+        run: poetry install
+
+      # Run benchmarks
       - name: Run benchmarks on python 3.8
         run: |
           poetry run pytest --full-trace --show-capture=no -sv benchmarks/benchmark_*.py

.github/workflows/linting.yml

@@ -22,15 +22,22 @@ jobs:
           python-version: 3.9
           poetry-version: 1.8.3
 
-      # Linting steps, excute all linters even if one fails
+      # Linting steps, execute all linters even if one fails
       - name: ruff
         run:
           poetry run ruff sed tests
-      - name: ruff formating
+      - name: ruff formatting
         if: ${{ always() }}
         run:
           poetry run ruff format --check sed tests
       - name: mypy
         if: ${{ always() }}
         run:
           poetry run mypy sed tests
+      - name: spellcheck
+        if: ${{ always() }}
+        uses: streetsidesoftware/cspell-action@v6
+        with:
+          check_dot_files: false
+          incremental_files_only: false
+          config: './cspell.json'

.github/workflows/update_dependencies.yml

@@ -1,4 +1,4 @@
-name: Update depencies in poetry lockfile
+name: Update dependencies in poetry lockfile
 
 on:
   schedule:

.pre-commit-config.yaml

@@ -42,3 +42,7 @@ repos:
     rev: 0.6.0
     hooks:
     -   id: nbstripout
+-   repo: https://github.com/streetsidesoftware/cspell-cli
+    rev: v6.31.1
+    hooks:
+      - id: cspell

benchmarks/Binning Benchmarks.ipynb

@@ -10,7 +10,7 @@
    "source": [
     "# 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",
+    "We showcase the binning method, first on a simple single table using the bin_partition method and then in the distributed method 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."
    ]
   },
@@ -200,7 +200,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "data_path = '../../' # Put in Path to a storage of at least 20 Gbyte free space.\n",
+    "data_path = '../../' # Put in Path to a storage of at least 20 GByte free space.\n",
     "if not os.path.exists(data_path + \"/WSe2.zip\"):\n",
     "    os.system(f\"curl --output {data_path}/WSe2.zip https://zenodo.org/record/6369728/files/WSe2.zip\")\n",
     "if not os.path.isdir(data_path + \"/Scan049_1\") or not os.path.isdir(data_path + \"energycal_2019_01_08/\"):\n",

benchmarks/mpes_sed_benchmarks.ipynb

@@ -48,7 +48,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dataPath = '../../' # Put in Path to a storage of at least 20 Gbyte free space.\n",
+    "dataPath = '../../' # Put in Path to a storage of at least 20 GByte free space.\n",
     "if not os.path.exists(dataPath + \"/WSe2.zip\"):\n",
     "    os.system(f\"curl --output {dataPath}/WSe2.zip https://zenodo.org/record/6369728/files/WSe2.zip\")\n",
     "if not os.path.isdir(dataPath + \"/Scan049_1\") or not os.path.isdir(dataPath + \"energycal_2019_01_08/\"):\n",
@@ -106,7 +106,7 @@
    "metadata": {},
    "source": [
     "## compute distributed binning on the partitioned dask dataframe\n",
-    "We generated 100 dataframe partiions from the 100 files in the dataset, which we will bin parallelly with the dataframe binning function into a 3D grid"
+    "We generated 100 dataframe partitions from the 100 files in the dataset, which we will bin parallelly with the dataframe binning function into a 3D grid"
    ]
   },
   {

cspell.json

@@ -0,0 +1,22 @@
+{
+    "version": "0.2",
+    "ignorePaths": [
+        "./tests/data/*",
+        "*.toml",
+        "Makefile",
+        "*.bat"
+    ],
+    "dictionaryDefinitions": [
+        {
+            "name": "custom-dictionary",
+            "path": "./.cspell/custom-dictionary.txt",
+            "addWords": true
+        }
+    ],
+    "dictionaries": [  "custom-dictionary"
+    ],
+    "words": [],
+    "ignoreWords": [],
+    "import": [],
+    "language": "en-GB, en-US"
+}

sed/config/flash_example_config.yaml

@@ -132,7 +132,7 @@ dataframe:
       dataset_key: "/uncategorised/FLASH.EXP/HEXTOF.DAQ/DLD1/value"
       slice: 3
 
-    # The auxillary channel has a special structure where the group further contains
+    # The auxiliary channel has a special structure where the group further contains
     # a multidimensional structure so further aliases are defined below
     dldAux:
       format: per_pulse

sed/loader/sxp/loader.py

@@ -444,15 +444,15 @@ def create_dataframe_per_pulse(
             DataFrame: The pandas DataFrame for the channel's data.
 
         Notes:
-            - For auxillary channels, the macrobunch resolved data is repeated 499 times to be
-              compared to electron resolved data for each auxillary channel. The data is then
+            - For auxiliary channels, the macrobunch resolved data is repeated 499 times to be
+              compared to electron resolved data for each auxiliary channel. The data is then
               converted to a multicolumn DataFrame.
             - For all other pulse resolved channels, the macrobunch resolved data is exploded
               to a DataFrame and the MultiIndex is set.
 
         """
 
-        # Special case for auxillary channels
+        # Special case for auxiliary channels
         if channel == "dldAux":
             # Checks the channel dictionary for correct slices and creates a multicolumn DataFrame
             data_frames = (

tests/data/loader/flash/config.yaml

@@ -106,8 +106,8 @@ dataframe:
       slice: 3
       dtype: uint32
 
-    # The auxillary channel has a special structure where the group further contains
-    # a multidim structure so further aliases are defined below
+    # The auxiliary channel has a special structure where the group further contains
+    # a multidimensional structure so further aliases are defined below
     dldAux:
       format: per_train
       index_key: "/uncategorised/FLASH.EXP/HEXTOF.DAQ/DLD1/index"

tests/test_processor.py

@@ -999,12 +999,12 @@ def test_get_normalization_histogram() -> None:
 
 metadata: dict[Any, Any] = {}
 metadata["entry_title"] = "Title"
-# User
+# user
 metadata["user0"] = {}
 metadata["user0"]["name"] = "Name"
 metadata["user0"]["email"] = "email"
 metadata["user0"]["affiliation"] = "affiliation"
-# Instrument
+# instrument
 metadata["instrument"] = {}
 # analyzer
 metadata["instrument"]["analyzer"] = {}

tutorial/6_binning_with_time-stamped_data.ipynb

@@ -328,7 +328,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "sed-ugcuzRKD-py3.9",
+   "display_name": "python3",
    "language": "python",
    "name": "python3"
   },