Bug fix, some CI updates and codespace badge

.devcontainer/devcontainer.json

@@ -0,0 +1,15 @@
+{   "name": "Hydropandas",
+    // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+    "image": "mcr.microsoft.com/devcontainers/python:0-3.11",
+    "updateContentCommand": "chmod u+x .devcontainer/setup.sh && .devcontainer/setup.sh && chmod 666 .devcontainer/setup.sh",
+    "postAttachCommand": "code examples/01_groundwater_observations.ipynb", //alternative for customizations openFile -> https://github.com/orgs/community/discussions/58399#discussioncomment-6222762
+    "customizations": {
+      "vscode": {
+        "extensions": [
+          "github.codespaces",
+          "ms-python.python",
+          "ms-toolsai.jupyter"
+        ]
+      }
+    }
+  }

.devcontainer/setup.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+# Create model environments
+pip install -e .

.github/workflows/ci.yml

@@ -11,34 +11,25 @@ on:
 
 jobs:
   test:
-    runs-on: ${{ matrix.os }}
+    runs-on: ubuntu-latest
     strategy:
       fail-fast: true
       matrix:
         include:
           - name: Test suite with py312-ubuntu
             python: "3.12"
-            os: ubuntu-latest
             toxenv: py312
           - name: Test suite with py311-ubuntu
             python: "3.11"
-            os: ubuntu-latest
             toxenv: py311
           - name: Test suite with py310-ubuntu
             python: "3.10"
-            os: ubuntu-latest
             toxenv: py310
-          - name: Formatting with black + isort
-            python: "3.9"
-            os: ubuntu-latest
-            toxenv: format
-          - name: Linting with flake8 + ruff
-            python: "3.9"
-            os: ubuntu-latest
-            toxenv: lint
+          - name: Formatting and linting with ruff
+            python: "3.11"
+            toxenv: ruff
           - name: Test suite for notebooks and coverage
             python: "3.9"
-            os: ubuntu-latest
             toxenv: notebooks
 
     name: ${{ matrix.name }}
@@ -68,11 +59,4 @@ jobs:
         run: tox -e ${{ matrix.toxenv }} --notest
 
       - name: Test
-        run: tox -e ${{ matrix.toxenv }} --skip-pkg-install
-
-      - name: Run codacy-coverage-reporter
-        if: ${{ matrix.toxenv == 'notebooks' && github.repository == 'ArtesiaWater/hydropandas' && success() }}
-        uses: codacy/codacy-coverage-reporter-action@master
-        with:
-          project-token: ${{ secrets.CODACY_PROJECT_TOKEN }}
-          coverage-reports: coverage.xml
+        run: tox -e ${{ matrix.toxenv }} --skip-pkg-install

hydropandas/__init__.py

@@ -33,6 +33,7 @@
     WaterlvlObs,
     WaterQualityObs,
 )
+from .rcparams import rcParams
 from .version import __version__, show_versions
 
 logging.getLogger("hydropandas").addHandler(logging.NullHandler())

hydropandas/extensions/plots.py

@@ -735,9 +735,9 @@ def series_per_group(
             if savefig:
                 if isinstance(by, list):
                     by_name = "-".join(by)
+                    groupname = "-".join(groupname)
                 else:
                     by_name = by
-                    groupname = "-".join(groupname)
                 if naming_method is None:
                     filename = f"series_by_{by_name}_group_{groupname}.png"
                 elif naming_method == "infer_name_monitoring_well":

hydropandas/io/bro.py

@@ -5,13 +5,15 @@
 import json
 import logging
 import xml.etree.ElementTree
+from functools import lru_cache
 
 import numpy as np
 import pandas as pd
 import requests
 from pyproj import Proj, Transformer
 from tqdm import tqdm
 
+from ..rcparams import rcParams
 from ..util import EPSG_28992
 
 logger = logging.getLogger(__name__)
@@ -422,8 +424,9 @@ def get_full_metadata_from_gmw(bro_id, tube_nr):
     return meta
 
 
-def get_tube_nrs_from_gmw(bro_id):
-    """returns all tube numbers from a groundwater monitoring well (gmw)
+@lru_cache()
+def _get_gmw_from_bro_id(bro_id, retries=0):
+    """get a gmw object from a bro_id
 
     Parameters
     ----------
@@ -432,31 +435,71 @@ def get_tube_nrs_from_gmw(bro_id):
 
     Returns
     -------
-    list of int
-        tube numbers
+    Element
+        xml reference to gmw object
+
+    Raises
+    ------
+    ValueError
+        if bro_id is invalid.
     """
 
+    if not bro_id.startswith("GMW"):
+        raise ValueError("can only get metadata if bro id starts with GMW")
+
     ns = {
         "dsgmw": "http://www.broservices.nl/xsd/dsgmw/1.1",
         "gmwcommon": "http://www.broservices.nl/xsd/gmwcommon/1.1",
         "gml": "http://www.opengis.net/gml/3.2",
     }
 
-    if not bro_id.startswith("GMW"):
-        raise ValueError("can only get metadata if bro id starts with GMW")
-
     url = f"https://publiek.broservices.nl/gm/gmw/v1/objects/{bro_id}"
     req = requests.get(url)
 
     # read results
     tree = xml.etree.ElementTree.fromstring(req.text)
 
-    # get gmw
     gmws = tree.findall(".//dsgmw:GMW_PO", ns)
     if len(gmws) != 1:
+        max_retries = rcParams["bro"]["max_retries"]
+        val_ind = req.text.find("valid")
+        valid = req.text[(val_ind + 9) : (val_ind + 14)]
+        if valid == "false" and retries < max_retries:
+            logger.debug(
+                f"got invalid response for {bro_id}, trying again {retries+1}/{max_retries}"
+            )
+            return _get_gmw_from_bro_id(bro_id, retries=retries + 1)
+        elif valid == "false":
+            raise Exception(
+                f"got invalid response for {bro_id} after trying {retries} times"
+            )
         raise (Exception("Only one gmw supported"))
     gmw = gmws[0]
 
+    return gmw
+
+
+def get_tube_nrs_from_gmw(bro_id):
+    """returns all tube numbers from a groundwater monitoring well (gmw)
+
+    Parameters
+    ----------
+    bro_id : str
+        bro id of groundwater monitoring well e.g. 'GMW000000036287'.
+
+    Returns
+    -------
+    list of int
+        tube numbers
+    """
+    ns = {
+        "dsgmw": "http://www.broservices.nl/xsd/dsgmw/1.1",
+        "gmwcommon": "http://www.broservices.nl/xsd/gmwcommon/1.1",
+        "gml": "http://www.opengis.net/gml/3.2",
+    }
+
+    gmw = _get_gmw_from_bro_id(bro_id)
+
     # get tube nrs
     tube_numbers = [
         int(tube.text)
@@ -490,28 +533,16 @@ def get_metadata_from_gmw(bro_id, tube_nr):
         dictionary with metadata.
 
     """
+    if not isinstance(tube_nr, int):
+        raise TypeError(f"expected integer got {type(tube_nr)}")
+
     ns = {
         "dsgmw": "http://www.broservices.nl/xsd/dsgmw/1.1",
         "gmwcommon": "http://www.broservices.nl/xsd/gmwcommon/1.1",
         "gml": "http://www.opengis.net/gml/3.2",
     }
 
-    if not bro_id.startswith("GMW"):
-        raise ValueError("can only get metadata if bro id starts with GMW")
-
-    if not isinstance(tube_nr, int):
-        raise TypeError(f"expected integer got {type(tube_nr)}")
-
-    url = f"https://publiek.broservices.nl/gm/gmw/v1/objects/{bro_id}"
-    req = requests.get(url)
-
-    # read results
-    tree = xml.etree.ElementTree.fromstring(req.text)
-
-    gmws = tree.findall(".//dsgmw:GMW_PO", ns)
-    if len(gmws) != 1:
-        raise (Exception("Only one gmw supported"))
-    gmw = gmws[0]
+    gmw = _get_gmw_from_bro_id(bro_id)
 
     meta = {"monitoring_well": bro_id, "tube_nr": tube_nr, "source": "BRO"}
 

hydropandas/io/knmi.py

@@ -1023,7 +1023,7 @@ def get_knmi_daily_meteo_url(stn: int) -> Tuple[pd.DataFrame, Dict[str, Any]]:
 
 
 def read_knmi_file(
-    path: Union[str, Path, StringIO]
+    path: Union[str, Path, StringIO],
 ) -> Tuple[pd.DataFrame, Dict[str, Any]]:
     """read knmi daily meteo data from a file
 

hydropandas/io/pastas.py

@@ -3,6 +3,7 @@
 
 @author: Artesia
 """
+
 import logging
 import numbers
 

hydropandas/obs_collection.py

@@ -812,6 +812,19 @@ def read_pastastore(
     )
 
 
+def _obscollection_constructor_with_fallback(*args, **kwargs):
+    """
+    A flexible constructor for ObsCollection._constructor, which falls back
+    to returning a DataFrame (if a certain operation does not preserve the
+    obs column). Copied from geopandas.
+    """
+    oc = ObsCollection(*args, **kwargs)
+    if "obs" not in oc.columns:
+        oc = pd.DataFrame(oc)
+
+    return oc
+
+
 class ObsCollection(pd.DataFrame):
     """Class for a collection of point observations.
 
@@ -871,7 +884,7 @@ def __init__(self, *args, **kwargs):
 
     @property
     def _constructor(self):
-        return ObsCollection
+        return _obscollection_constructor_with_fallback
 
     def _infer_otype(self):
         """Infer observation type from the obs column.

hydropandas/observation.py

@@ -17,11 +17,11 @@
 import logging
 import os
 import warnings
+from _io import StringIO
 from typing import List, Optional
 
 import numpy as np
 import pandas as pd
-from _io import StringIO
 from pandas._config import get_option
 from pandas.api.types import is_numeric_dtype
 from pandas.io.formats import console

hydropandas/rcparams.py

@@ -0,0 +1 @@
+rcParams = {"bro": {"max_retries": 5}}

hydropandas/version.py

@@ -1,7 +1,7 @@
 from importlib import metadata
 from sys import version as os_version
 
-__version__ = "0.12.1"
+__version__ = "0.12.2"
 
 
 def show_versions():

pyproject.toml

@@ -65,11 +65,10 @@ rtd = [
     "nbsphinx",
     "nbsphinx_link",
 ]
-linting = ["flake8", "ruff"]
-formatting = ["black[jupyter]", "isort"]
+ruffing = ["ruff"]
 pytesting = ["hydropandas[full,rtd]", "pytest>=7", "pytest-cov", "pytest-sugar"]
 coveraging = ["coverage"]
-dev = ["hydropandas[linting,formatting,pytesting]", "tox"]
+dev = ["hydropandas[ruffing,pytesting]", "tox"]
 
 [tool.setuptools]
 include-package-data = true
@@ -99,7 +98,7 @@ markers = ["slow: mark test as slow."]
 legacy_tox_ini = """
     [tox]
     requires = tox>=4
-    env_list = format, lint, notebooks, py{39, 310, 311, 312}
+    env_list = ruff, notebooks, py{39, 310, 311, 312}
 
     [testenv]
     description = run unit tests
@@ -114,19 +113,18 @@ legacy_tox_ini = """
             coverage run -m pytest tests
             coverage xml
 
-    [testenv:format]
-    description = run formatters
-    basepython = python3.9
-    extras = formatting
+    [testenv:ruff]
+    description = run ruff checks
+    basepython = python3.11
+    extras = ruffing
     commands =
-            black . --check --diff
-            isort . --check-only --diff
+            ruff check --extend-select I --preview
+            ruff format --check
 
-    [testenv:lint]
-    description = run linters
-    basepython = python3.9
-    extras = linting
+    [testenv:ruff_fix]
+    description = run ruff locally and fix issues
+    extras = ruffing
     commands =
-            flake8 . --max-line-length=88 --ignore=E741,W503
-            ruff check .
+            ruff check --extend-select I --fix
+            ruff format
 """

readme.md

@@ -2,7 +2,8 @@
 
 [![PyPi](https://img.shields.io/pypi/v/hydropandas.svg)](https://pypi.python.org/pypi/hydropandas)
 [![PyPi Supported Python Versions](https://img.shields.io/pypi/pyversions/hydropandas)](https://pypi.python.org/pypi/hydropandas)
-[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/ArtesiaWater/hydropandas/master)
+[<img src="https://github.com/codespaces/badge.svg" height="20">](https://codespaces.new/ArtesiaWater/hydropandas?quickstart=1)
+
 
 [![hydropandas](https://github.com/ArtesiaWater/hydropandas/workflows/hydropandas/badge.svg)](https://github.com/ArtesiaWater/hydropandas/actions?query=workflow%3Ahydropandas)
 [![Codacy Badge](https://app.codacy.com/project/badge/Grade/c1b99f474bdc49b0a47e00e4e9f66c2f)](https://www.codacy.com/gh/ArtesiaWater/hydropandas/dashboard?utm_source=github.com&utm_medium=referral&utm_content=ArtesiaWater/hydropandas&utm_campaign=Badge_Grade)

tests/test_001_to_from.py

@@ -18,7 +18,7 @@ def test_bro_gld():
 
 def test_bro_gmn():
     # single observation
-    bro_id = "GMN000000000163"
+    bro_id = "GMN000000001084"  # 34 objects as per 2024-7-11
     hpd.read_bro(bro_id=bro_id, only_metadata=True)
 
 
@@ -31,7 +31,7 @@ def test_bro_extent():
 
 
 def test_bro_extent_too_big():
-    extent = (102395, 213550, 334331, 473920)  # to many observations in extent
+    extent = (102395, 213550, 334331, 473920)  # too many observations in extent
 
     with pytest.raises(HTTPError):
         hpd.read_bro(extent=extent, only_metadata=True)