Merge branch 'dev' into R_benchmark

.github/workflows/python-publish.yml

@@ -13,9 +13,9 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: '3.x'
     - name: Install dependencies

.github/workflows/tests.yml

@@ -12,11 +12,6 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - name: Test suite with py38-ubuntu
-            python: "3.8"
-            os: ubuntu-latest
-            toxenv: py38
-            experimental: false
           - name: Test suite with py39-ubuntu
             python: "3.9"
             os: ubuntu-latest
@@ -33,10 +28,10 @@ jobs:
             toxenv: py311
             experimental: false
           - name: Test suite with py312-ubuntu
-            python: "3.12-dev"
+            python: "3.12"
             os: ubuntu-latest
             toxenv: py312
-            experimental: true
+            experimental: false
           - name: Type check with mypy
             python: "3.9"
             os: ubuntu-latest
@@ -72,10 +67,10 @@ jobs:
       # Pytest
       PYTEST_ADDOPTS: "--color=yes"
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Set up Python ${{ matrix.python }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
           check-latest: true

README.md

@@ -43,11 +43,11 @@ To get the development version download or clone the GitHub repository to your l
 
 ## Literature
 
- 1. B. Lloyd-Hughes and M.A. Saunders (2002) - A Drought Climatology for Europe. DOI: 10.1002/joc.846
- 2. S.M. Vicente-Serrano, S. Beguería and J.I. López-Moreno (2010) - A Multi-scalar drought index sensitive to global warming: The Standardized Precipitation Evapotranspiration Index. DOI: 10.1175/2009JCLI2909.1
- 3. J.P.Bloomfield and B.P. Marchant, B. P. (2013) - Analysis of groundwater drought building on the standardised precipitation index approach. DOI: 10.5194/hess-17-4769-2013
- 4. A. Babre, A. Kalvāns, Z. Avotniece, I. Retiķe, J. Bikše, K.P.M. Jemeljanova, A. Zelenkevičs and A. Dēliņa (2022) - The use of predefined drought indices for the assessment of groundwater drought episodes in the Baltic States over the period 1989–2018. DOI: 10.1016/j.ejrh.2022.101049
- 5. E. Tijdeman, K. Stahl and L.M. Tallaksen (2020) - Drought characteristics derived based on the Standardized Streamflow Index: A large sample comparison for parametric and nonparametric methods. DOI: 10.1029/2019WR026315
+1.   B. Lloyd-Hughes and M.A. Saunders (2002) - A Drought Climatology for Europe. DOI: 10.1002/joc.846
+2.   S.M. Vicente-Serrano, S. Beguería and J.I. López-Moreno (2010) - A Multi-scalar drought index sensitive to global warming: The Standardized Precipitation Evapotranspiration Index. DOI: 10.1175/2009JCLI2909.1
+3.   J.P. Bloomfield and B.P. Marchant, B. P. (2013) - Analysis of groundwater drought building on the standardised precipitation index approach. DOI: 10.5194/hess-17-4769-2013
+4.   A. Babre, A. Kalvāns, Z. Avotniece, I. Retiķe, J. Bikše, K.P.M. Jemeljanova, A. Zelenkevičs and A. Dēliņa (2022) - The use of predefined drought indices for the assessment of groundwater drought episodes in the Baltic States over the period 1989–2018. DOI: 10.1016/j.ejrh.2022.101049
+5.   E. Tijdeman, K. Stahl and L.M. Tallaksen (2020) - Drought characteristics derived based on the Standardized Streamflow Index: A large sample comparison for parametric and nonparametric methods. DOI: 10.1029/2019WR026315
 
 Note that the method for calculating the drought indices does not come from these articles and SciPy is used for deriving the distribution. However the literature is helpful as a reference to understand the context and application of drought indices.
 

doc/examples/example04_package_comparison.ipynb

@@ -84,7 +84,9 @@
    "source": [
     "# get rolling sum\n",
     "prec_rsum = prec.rolling(\"30D\", min_periods=30).sum().dropna()\n",
-    "prec_rsum.plot(grid=True, linewidth=0.5, title=\"Precipitation, 30day rolling sum\", figsize=(6.5, 4));"
+    "prec_rsum.plot(\n",
+    "    grid=True, linewidth=0.5, title=\"Precipitation, 30day rolling sum\", figsize=(6.5, 4)\n",
+    ");"
    ]
   },
   {

pyproject.toml

@@ -9,11 +9,10 @@ authors = [{ name = "Martin Vonk", email = "[email protected]" }]
 description = "A simple Python package to calculate drought indices for time series such as the SPI, SPEI and SGI."
 readme = "README.md"
 license = { file = "LICENSE" }
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 dependencies = ["numpy", "scipy", "matplotlib", "pandas"]
 classifiers = [
         'Programming Language :: Python :: 3 :: Only',
-        'Programming Language :: Python :: 3.8',
         'Programming Language :: Python :: 3.9',
         'Programming Language :: Python :: 3.10',
         'Programming Language :: Python :: 3.11',
@@ -63,7 +62,7 @@ line-length = 88
 legacy_tox_ini = """
     [tox]
     requires = tox>=4
-    env_list = format, type, lint, py38, py39, py310, py311, py312
+    env_list = format, type, lint, py39, py310, py311, py312
 
     [testenv]
     description = run unit tests

src/spei/climdex.py

@@ -33,7 +33,7 @@ def sdii(series: Series, threshold: float = 1.0, period: str = "30D") -> Series:
     return series.loc[w].resample(period).sum() / w.sum()
 
 
-def rnmm(series: Series, threshold: float, period: str = "1Y") -> Series:
+def rnmm(series: Series, threshold: float, period: str = "1YE") -> Series:
     """Annual count of days when precipitation ≥ n mm. n is a user-defined threshold"""
     series = validate_series(series)
     _ = validate_index(series.index)
@@ -43,12 +43,12 @@ def rnmm(series: Series, threshold: float, period: str = "1Y") -> Series:
     return w.resample(period).sum()
 
 
-def r10mm(series: Series, threshold: float = 10.0, period: str = "1Y") -> Series:
+def r10mm(series: Series, threshold: float = 10.0, period: str = "1YE") -> Series:
     """Annual count of days when precipitation ≥ 10 mm"""
     return rnmm(series=series, threshold=threshold, period=period)
 
 
-def r20mm(series: Series, threshold: float = 20.0, period: str = "1Y") -> Series:
+def r20mm(series: Series, threshold: float = 20.0, period: str = "1YE") -> Series:
     """Annual count of days when precipitation ≥ 20 mm"""
     return rnmm(series=series, threshold=threshold, period=period)
 
@@ -75,7 +75,7 @@ def cwd(series: Series, threshold: float = 1.0, period: str = "365D") -> Series:
     return w.diff().rolling(period).sum().dropna().astype(int)
 
 
-def prcptot(series: Series, period: str = "1Y") -> Series:
+def prcptot(series: Series, period: str = "1YE") -> Series:
     """Total precipitation on wet days over a certain period"""
     series = validate_series(series)
     _ = validate_index(series.index)
@@ -84,7 +84,7 @@ def prcptot(series: Series, period: str = "1Y") -> Series:
 
 
 def rnnp(
-    series: Series, quantile: float, threshold: float = 1.0, period: str = "1Y"
+    series: Series, quantile: float, threshold: float = 1.0, period: str = "1YE"
 ) -> Series:
     """Total amount of precipitation on wet days above certain quantile"""
     series = validate_series(series)
@@ -97,21 +97,21 @@ def rnnp(
 
 
 def r95p(
-    series: Series, quantile: float = 0.95, threshold: float = 1.0, period: str = "1Y"
+    series: Series, quantile: float = 0.95, threshold: float = 1.0, period: str = "1YE"
 ) -> Series:
     """Total amount of precipitation on very wet days"""
     return rnnp(series=series, quantile=quantile, threshold=threshold, period=period)
 
 
 def r99p(
-    series: Series, quantile: float = 0.99, threshold: float = 1.0, period: str = "1Y"
+    series: Series, quantile: float = 0.99, threshold: float = 1.0, period: str = "1YE"
 ) -> Series:
     """Total amount of precipitation on extremely wet days"""
     return rnnp(series=series, quantile=quantile, threshold=threshold, period=period)
 
 
 def r95ptot(
-    series: Series, quantile: float = 0.95, threshold: float = 1.0, period: str = "1Y"
+    series: Series, quantile: float = 0.95, threshold: float = 1.0, period: str = "1YE"
 ) -> Series:
     """Contribution to total precipitation from very wet days"""
     r95 = r95p(series=series, quantile=quantile, threshold=threshold, period=period)
@@ -120,7 +120,7 @@ def r95ptot(
 
 
 def r99ptot(
-    series: Series, quantile: float = 0.99, threshold: float = 1.0, period: str = "1Y"
+    series: Series, quantile: float = 0.99, threshold: float = 1.0, period: str = "1YE"
 ) -> Series:
     """Contribution to total precipitation from extremely wet days"""
     r99 = r99p(series=series, quantile=quantile, threshold=threshold, period=period)

src/spei/utils.py

@@ -59,6 +59,15 @@ def validate_index(index: Index) -> DatetimeIndex:
         )
         index = DatetimeIndex(to_datetime(index))
 
+    if index.has_duplicates:
+        msg = (
+            "Duplicated indices found. Please remove them. For instance by"
+            " using `series = "
+            "series.loc[~series.index.duplicated(keep='first/last')]`"
+        )
+        logging.error(msg)
+        raise ValueError(msg)
+
     return index
 
 

tests/test_validate.py

@@ -1,23 +1,37 @@
 import logging
 
 import pytest
-from pandas import DataFrame, Series, to_datetime
+from pandas import DataFrame, DatetimeIndex, Series, Timestamp, to_datetime
 
 from spei.utils import validate_index, validate_series
 
 
 def test_validate_index(caplog) -> None:
     caplog.set_level(logging.INFO)
-    series = Series([1, 2, 3], index=["2018", "2019", "2020"])
+    series = Series([1.0, 2.0, 3.0], index=["2018", "2019", "2020"])
     validate_index(series.index)
     msg = (
         f"Expected the index to be a DatetimeIndex. Automatically converted "
         f"{type(series.index)} using pd.to_datetime(Index)\n"
     )
-    print(f"{caplog.text=}")
     assert msg in caplog.text
 
 
+def test_validate_index_duplicated(caplog) -> None:
+    caplog.set_level(logging.ERROR)
+    series = Series(
+        [1.0, 1.0],
+        index=DatetimeIndex([Timestamp("2000-01-01"), Timestamp("2000-01-01")]),
+    )
+    with pytest.raises(ValueError):
+        validate_index(series.index)
+        msg = (
+            "Duplicated indices found. Please remove them. For instance by using"
+            "`series = series.loc[~series.index.duplicated(keep='first/last')]`"
+        )
+        assert msg in caplog.text
+
+
 def test_validate_series() -> None:
     with pytest.raises(TypeError):
         validate_series([1, 2, 3])