Merge branch 'master' into dev

.github/workflows/build.yml

@@ -13,13 +13,13 @@ jobs:
       - uses: actions/checkout@main
       - uses: actions/setup-python@main
         with:
-          python-version: '3.x'
+          python-version: "3.x"
       - uses: actions/cache@main
         with:
           path: ${{ env.pythonLocation }}
           key: build-${{ runner.os }}-${{ env.pythonLocation }}-${{ hashFiles('pyproject.toml', 'setup.*') }}
       - run: pip wheel . --no-deps -w dist
-      - uses: pypa/gh-action-pypi-publish@master
+      - uses: pypa/gh-action-pypi-publish@release/v1
         with:
           user: __token__
           password: ${{ secrets.PYPI_TOKEN }}

.github/workflows/install_from_pypi.yml

@@ -0,0 +1,38 @@
+name: "Test installation from PyPI"
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "4 5 * * *" # Every day at 05:04
+
+jobs:
+  test_pypi_installation:
+    name: test PyPI installation
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        include:
+          - os: "ubuntu-latest"
+            python: "3.12"
+    steps:
+      - uses: actions/checkout@main
+      - uses: actions/setup-python@main
+        with:
+          python-version: ${{ matrix.python }}
+      # Debug
+      - run: type -a python
+      - run: python --version
+      - run: python -m pip --version
+      - run: python -m pip cache info
+      # Install the package from pypi
+      - run: python -m pip install searvey
+      - run: python -m pip freeze
+      # Checkout the version of code that got installed from PyPI
+      - run: git fetch --tags
+      - run: git checkout v$(python -c 'import importlib.metadata; print(importlib.metadata.version("searvey"))')
+      # Install test dependencies
+      - run: pip install -U $(cat requirements/requirements-dev.txt| grep --extended-regexp 'pytest=|pytest-recording=|urllib3=' | cut -d ';' -f1)
+      # Remove the source code (just to be sure that it is not being used)
+      - run: rm -rf searvey
+      # Run the tests
+      - run: make test

.pre-commit-config.yaml

@@ -41,7 +41,7 @@ repos:
       - id: "shellcheck"
 
   - repo: "https://github.com/python-jsonschema/check-jsonschema"
-    rev: "0.28.5"
+    rev: "0.28.6"
     hooks:
       - id: "check-github-workflows"
       - id: "check-readthedocs"
@@ -60,7 +60,7 @@ repos:
 
   - repo: "https://github.com/charliermarsh/ruff-pre-commit"
     # Ruff version.
-    rev: 'v0.4.9'
+    rev: 'v0.4.10'
     hooks:
       - id: "ruff"
 

Makefile

@@ -27,7 +27,7 @@ clean_notebooks:
 	pre-commit run nbstripout -a
 
 exec_notebooks:
-	pytest --nbmake --nbmake-timeout=60 --nbmake-kernel=python3 $$(git ls-files | grep ipynb)
+	pytest --ff --nbmake --nbmake-timeout=90 --nbmake-kernel=python3 $$(git ls-files | grep ipynb)
 
 docs:
 	make -C docs html

examples/IOC_data.ipynb

@@ -30,7 +30,7 @@
    "source": [
     "## Retrieve Station Metadata\n",
     "\n",
-    "In order to retrieve station metadata we need to use the `get_ioc_stations()` function:"
+    "In order to retrieve station metadata we need to use the `get_ioc_stations()` function which returns a `geopandas.GeoDataFrame`:"
    ]
   },
   {
@@ -55,7 +55,7 @@
    },
    "outputs": [],
    "source": [
-    "ioc_stations.sample(3).sort_index()"
+    "ioc_stations.columns"
    ]
   },
   {
@@ -67,7 +67,8 @@
    },
    "outputs": [],
    "source": [
-    "ioc_stations.columns"
+    "with pd.option_context('display.max_columns', None):\n",
+    "    ioc_stations.sample(3).sort_index()"
    ]
   },
   {
@@ -105,8 +106,8 @@
    "outputs": [],
    "source": [
     "east_coast = shapely.geometry.box(-85, 25, -65, 45)\n",
-    "east_stations = searvey.get_ioc_stations(region=east_coast)\n",
-    "len(east_stations)"
+    "east_coast_stations = searvey.get_ioc_stations(region=east_coast)\n",
+    "len(east_coast_stations)"
    ]
   },
   {
@@ -118,7 +119,7 @@
    },
    "outputs": [],
    "source": [
-    "east_stations.hvplot.points(geo=True, tiles=True)"
+    "east_coast_stations.hvplot.points(geo=True, tiles=True)"
    ]
   },
   {
@@ -128,7 +129,7 @@
    "source": [
     "## Retrieve IOC station data\n",
     "\n",
-    "The function for retrieving data is called `fetch_ioc_station()`. \n",
+    "The function for retrieving data is called `fetch_ioc_station()` and it returns \n",
     "\n",
     "In its simplest form it only requires the station_id (i.e. IOC_CODE) and it will retrieve the last week of data:"
    ]
@@ -163,7 +164,6 @@
     "    station_id=\"alva\",\n",
     "    start_date=pd.Timestamp(\"2024-05-01\"),\n",
     "    end_date=pd.Timestamp(\"2024-05-10\"),\n",
-    "    progress_bar=False,\n",
     ")\n",
     "df"
    ]
@@ -175,7 +175,7 @@
    "source": [
     "If we request more than 30 days, then multiple HTTP requests are send to the IOC servers via multithreading and the responses are merged to a single dataframe. \n",
     "\n",
-    "In this case, setting `progress_bar=True` can be useful in monitoring the progress of HTTP requests. \n",
+    "In this case, setting `progress_bar=True` can be helpful in monitoring the progress of the HTTP requests. \n",
     "For example to retrieve data for the first 6 months of 2020:"
    ]
   },
@@ -200,7 +200,7 @@
    "id": "15",
    "metadata": {},
    "source": [
-    "Keep in mind that each IOC station may return dataframes with different sensors/columns. For example the station in Bahamas returns a bunch of them:"
+    "Keep in mind that each IOC station may return dataframes with different sensors/columns. For example the `setp1` station in Bahamas returns a bunch of them:"
    ]
   },
   {
@@ -224,7 +224,7 @@
    "id": "17",
    "metadata": {},
    "source": [
-    "Furthermore, not all of these timeseries are ready to be used. \n",
+    "Nevertheless, the returned timeseries are **not** ready to be used. \n",
     "\n",
     "E.g. we see that in the last days of May the `rad` sensor was offline for some time:"
    ]
@@ -236,7 +236,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "bahamas.rad.hvplot()"
+    "bahamas.rad.hvplot(grid=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "19",
+   "metadata": {},
+   "source": [
+    "So the IOC data **do** need some data-cleaning."
    ]
   }
  ],

pyproject.toml

@@ -71,6 +71,7 @@ sphinx = "*"
 sphinx-autodoc-typehints = "*"
 sphinxext-opengraph = "*"
 toml = "*"
+sphinx-autodoc-typehints = "*"
 
 [tool.poetry.group.jupyter.dependencies]
 hvplot = {version = "*", extras = ["geo"]}

requirements/requirements-dev.txt

@@ -25,7 +25,7 @@ covdefaults==2.3.0 ; python_version >= "3.9" and python_version < "4.0"
 coverage==7.5.3 ; python_version >= "3.9" and python_version < "4.0"
 coverage[toml]==7.5.3 ; python_version >= "3.9" and python_version < "4.0"
 cycler==0.12.1 ; python_version >= "3.9" and python_version < "4.0"
-dask==2024.6.0 ; python_version >= "3.9" and python_version < "4.0"
+dask==2024.6.2 ; python_version >= "3.9" and python_version < "4.0"
 dataretrieval==1.0.9 ; python_version >= "3.9" and python_version < "4.0"
 debugpy==1.8.1 ; python_version >= "3.9" and python_version < "4.0"
 decorator==5.1.1 ; python_version >= "3.9" and python_version < "4.0"