streamlined and optimised tide functions + added CI

.github/workflows/run_tests.yml

@@ -0,0 +1,58 @@
+name: test
+
+on:
+  push:
+    branches:
+      - "main"
+      - "master"
+      - "dev"
+    paths:
+      - "**.py"
+      - ".github/workflows/*test*.yml"
+      - "pyproject.toml"
+      - "poetry.lock"
+      - "requirements/requirements*.txt"
+  pull_request:
+    paths:
+      - "**.py"
+      - ".github/workflows/*test*.yml"
+      - "pyproject.toml"
+      - "poetry.lock"
+      - "requirements/requirements*.txt"
+
+jobs:
+  test:
+    name: "test Python ${{ matrix.python }} on ${{ matrix.os }}"
+    runs-on: "${{ matrix.os }}"
+    strategy:
+      fail-fast: false
+      matrix:
+        os: ["ubuntu-latest"]
+        python: ["3.9", "3.10", "3.11"]
+        # include:
+        #   - os: "macos-latest"
+        #     python-version: "3.10"
+    defaults:
+      run:
+        shell: "bash -eo pipefail {0}"
+
+    steps:
+      - uses: "actions/checkout@main"
+      - uses: "actions/setup-python@main"
+        with:
+          python-version: "${{ matrix.python }}"
+      - uses: "actions/cache@main"
+        id: "cache"
+        with:
+          path: "${{ env.pythonLocation }}"
+          key: "test-${{ runner.os }}-${{ env.pythonLocation }}-${{ hashFiles('pyproject.toml', 'requirements/*') }}"
+      - run: "python --version"
+      - run: "python -mpip install -U pip"
+      - run: "python -mpip --version"
+      - run: "python -mpip install -r requirements/requirements-dev.txt"
+      - run: "python -mpip install ./"
+      - run: "python -mpip cache info"
+      - run: "python -mpip freeze"
+      - run: "pytest tests/"
+        env:
+          PYTHONPATH: ${{ github.workspace }}/tests

.pre-commit-config.yaml

@@ -91,7 +91,6 @@ repos:
             "-o",
             "requirements/requirements-dev.txt",
           ]
-
   - repo: "local"
     hooks:
       - id: "mypy"

analysea/custom_types.py

@@ -3,15 +3,26 @@
 import datetime
 from typing import Any
 from typing import Dict
+from typing import TypedDict
 from typing import TypeVar
 from typing import Union
 
 import numpy.typing as npt
 import pandas as pd
+from typing_extensions import NotRequired
 from typing_extensions import TypeAlias  # "from typing" in Python 3.9+
 
 
 StrDict: TypeAlias = Dict[str, Any]
 DateTimeLike: TypeAlias = Union[str, datetime.date, datetime.datetime, pd.Timestamp]
 
 ScalarOrArray = TypeVar("ScalarOrArray", int, float, npt.NDArray[Any])
+
+
+class UTideArgs(TypedDict):
+    constit: NotRequired[str]
+    method: NotRequired[str]
+    order_constit: NotRequired[str]
+    Rayleigh_min: NotRequired[float]
+    lat: str
+    verbose: NotRequired[str]

analysea/filters.py

@@ -19,7 +19,7 @@ def interp(df: pd.Series[Any], new_index: pd.Index[Any]) -> pd.DataFrame:
     return df_out
 
 
-def filter_fft(df: pd.DataFrame) -> pd.DataFrame:
+def filter_fft(df: pd.DataFrame, fcut: float = 20) -> pd.DataFrame:
     # df is a single channel dataframe with :
     # index as pandas.DatetimeIndex
     data = df.dropna().values
@@ -31,7 +31,7 @@ def filter_fft(df: pd.DataFrame) -> pd.DataFrame:
     fA = fs * 3600 * 24  # seconds in a day
     fftfreq = sp.fftpack.fftfreq(len(temp_psd), 1 / fA)
     temp_fft_bis = temp_fft.copy()
-    temp_fft_bis[np.abs(fftfreq) > 20] = 0
+    temp_fft_bis[np.abs(fftfreq) > fcut] = 0
     # suppressing everything passed the 10th harmonic
     # (first one being the semi-diurnal consituent of the tide)
     temp_slow = np.real(sp.fftpack.ifft(temp_fft_bis))

analysea/gesla.py

@@ -2,7 +2,6 @@
 from __future__ import annotations
 
 import warnings
-from typing import Optional
 from typing import Union
 
 import geopandas as gp
@@ -132,11 +131,11 @@ def load_N_closest(self, lat, lon, N=1, force_xarray=False):
 
     def load_lat_lon_range(
         self,
-        region: Optional[Union[Polygon, MultiPolygon]] = None,
-        south_lat: Optional[float] = None,
-        north_lat: Optional[float] = None,
-        west_lon: Optional[float] = None,
-        east_lon: Optional[float] = None,
+        region: Union[Polygon, MultiPolygon] | None,
+        south_lat: float | None,
+        north_lat: float | None,
+        west_lon: float | None,
+        east_lon: float | None,
         force_xarray=False,
     ):
         """Load GESLA records within a rectangular lat/lon range into a xarray.
@@ -171,7 +170,9 @@ def load_lat_lon_range(
         )
 
         locations = gp.GeoDataFrame(
-            self.meta, geometry=gp.points_from_xy(self.meta.longitude, self.meta.latitude), crs="EPSG:4326"
+            self.meta,
+            geometry=gp.points_from_xy(self.meta.longitude, self.meta.latitude),
+            crs="EPSG:4326",
         )
 
         meta = self.meta.loc[locations.within(region)]

analysea/steps.py

@@ -8,8 +8,6 @@
 import numpy.typing as npt
 import pandas as pd
 import ruptures as rpt
-from scipy import interpolate
-from skimage.restoration import denoise_tv_chambolle
 
 from analysea.utils import detect_time_step
 
@@ -69,18 +67,3 @@ def remove_steps_simple(df: pd.DataFrame, threshold: float) -> Tuple[pd.DataFram
         step = df.interpolate().iloc[stepx : steps_ix[i + 1]].mean()
         step_function.iloc[stepx : steps_ix[i + 1]] = step
     return step_function, steps_ix
-
-
-def step_function_TV(df: pd.DataFrame, weight: float = 1) -> Tuple[pd.DataFrame, npt.NDArray[Any]]:
-    idx = range(0, len(df), 200)
-    signal = np.array(df.interpolate())[idx]
-    # adjust the parameters
-    signal_denoise = denoise_tv_chambolle(signal, weight=weight)  # type: ignore[no-untyped-call]
-    # x_step = -2*np.cumsum(signal_denoise)
-    # step_indicator = x_step == x_step.max()
-    f = interpolate.interp1d(
-        idx, signal_denoise, fill_value="extrapolate"
-    )  # for extrapolation in last scipy version
-    res = pd.Series(data=f(range(len(df))), index=df.index)
-    #
-    return remove_steps_simple(res, res.std())