Convert river and tidal modules to xarray

mhkit/power/characteristics.py

@@ -2,6 +2,7 @@
 import xarray as xr
 import numpy as np
 from scipy.signal import hilbert
+from mhkit.utils import convert_to_dataset
 
 
 def instantaneous_frequency(um, time_dimension="", to_pandas=True):
@@ -39,7 +40,7 @@ def instantaneous_frequency(um, time_dimension="", to_pandas=True):
         )
 
     # Convert input to xr.Dataset
-    um = _convert_to_dataset(um, "data")
+    um = convert_to_dataset(um, "data")
 
     if time_dimension != "" and time_dimension not in um.coords:
         raise ValueError(
@@ -114,8 +115,8 @@ def dc_power(voltage, current, to_pandas=True):
         raise TypeError(f"to_pandas must be of type bool. Got: {type(to_pandas)}")
 
     # Convert inputs to xr.Dataset
-    voltage = _convert_to_dataset(voltage, "voltage")
-    current = _convert_to_dataset(current, "current")
+    voltage = convert_to_dataset(voltage, "voltage")
+    current = convert_to_dataset(current, "current")
 
     # Check that sizes are the same
     if not (
@@ -190,8 +191,8 @@ def ac_power_three_phase(
         raise TypeError(f"to_pandas must be of type bool. Got: {type(to_pandas)}")
 
     # Convert inputs to xr.Dataset
-    voltage = _convert_to_dataset(voltage, "voltage")
-    current = _convert_to_dataset(current, "current")
+    voltage = convert_to_dataset(voltage, "voltage")
+    current = convert_to_dataset(current, "current")
 
     # Check that sizes are the same
     if not len(voltage.data_vars) == 3:
@@ -215,66 +216,3 @@ def ac_power_three_phase(
         P = P.to_pandas()
 
     return P
-
-
-def _convert_to_dataset(data, name="data"):
-    """
-    Converts the given data to an xarray.Dataset.
-
-    This function is designed to handle inputs that can be either a pandas DataFrame, a pandas Series,
-    an xarray DataArray, or an xarray Dataset. It ensures that the output is consistently an xarray.Dataset.
-
-    Parameters
-    ----------
-    data: pandas DataFrame, pandas Series, xarray DataArray, or xarray Dataset
-        The data to be converted.
-
-    name: str (Optional)
-        The name to assign to the data variable in case the input is an xarray DataArray without a name.
-        Default value is 'data'.
-
-    Returns
-    -------
-    xarray.Dataset
-        The input data converted to an xarray.Dataset. If the input is already an xarray.Dataset,
-        it is returned as is.
-
-    Examples
-    --------
-    >>> df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})
-    >>> ds = _convert_to_dataset(df)
-    >>> type(ds)
-    <class 'xarray.core.dataset.Dataset'>
-
-    >>> series = pd.Series([1, 2, 3], name='C')
-    >>> ds = _convert_to_dataset(series)
-    >>> type(ds)
-    <class 'xarray.core.dataset.Dataset'>
-
-    >>> data_array = xr.DataArray([1, 2, 3])
-    >>> ds = _convert_to_dataset(data_array, name='D')
-    >>> type(ds)
-    <class 'xarray.core.dataset.Dataset'>
-    """
-    if not isinstance(data, (pd.DataFrame, pd.Series, xr.DataArray, xr.Dataset)):
-        raise TypeError(
-            "Input data must be of type pandas.DataFrame, pandas.Series, "
-            "xarray.DataArray, or xarray.Dataset"
-        )
-
-    if not isinstance(name, str):
-        raise TypeError("The 'name' parameter must be a string")
-
-    # Takes data that could be pd.DataFrame, pd.Series, xr.DataArray, or
-    # xr.Dataset and converts it to xr.Dataset
-    if isinstance(data, (pd.DataFrame, pd.Series)):
-        data = data.to_xarray()
-
-    if isinstance(data, xr.DataArray):
-        if data.name is None:
-            data.name = (
-                name  # xr.DataArray.to_dataset() breaks if the data variable is unnamed
-            )
-        data = data.to_dataset()
-
-    return data

mhkit/power/quality.py

@@ -2,7 +2,7 @@
 import numpy as np
 from scipy import fftpack
 import xarray as xr
-from .characteristics import _convert_to_dataset
+from mhkit.utils import convert_to_dataset
 
 
 # This group of functions are to be used for power quality assessments
@@ -46,7 +46,7 @@ def harmonics(x, freq, grid_freq, to_pandas=True):
         raise TypeError(f"to_pandas must be of type bool. Got {type(to_pandas)}")
 
     # Convert input to xr.Dataset
-    x = _convert_to_dataset(x, "data")
+    x = convert_to_dataset(x, "data")
 
     sample_spacing = 1.0 / freq
 
@@ -120,7 +120,7 @@ def harmonic_subgroups(harmonics, grid_freq, frequency_dimension="", to_pandas=T
         )
 
     # Convert input to xr.Dataset
-    harmonics = _convert_to_dataset(harmonics, "harmonics")
+    harmonics = convert_to_dataset(harmonics, "harmonics")
 
     if frequency_dimension != "" and frequency_dimension not in harmonics.coords:
         raise ValueError(
@@ -200,7 +200,7 @@ def total_harmonic_current_distortion(
         )
 
     # Convert input to xr.Dataset
-    harmonics_subgroup = _convert_to_dataset(harmonics_subgroup, "harmonics")
+    harmonics_subgroup = convert_to_dataset(harmonics_subgroup, "harmonics")
 
     if frequency_dimension != "" and frequency_dimension not in harmonics.coords:
         raise ValueError(
@@ -263,7 +263,7 @@ def interharmonics(harmonics, grid_freq, frequency_dimension="", to_pandas=True)
         raise TypeError(f"to_pandas must be of type bool. Got: {type(to_pandas)}")
 
     # Convert input to xr.Dataset
-    harmonics = _convert_to_dataset(harmonics, "harmonics")
+    harmonics = convert_to_dataset(harmonics, "harmonics")
 
     if frequency_dimension != "" and frequency_dimension not in harmonics.coords:
         raise ValueError(

mhkit/river/graphics.py

@@ -1,6 +1,7 @@
 import numpy as np
-import pandas as pd
+import xarray as xr
 import matplotlib.pyplot as plt
+from mhkit.utils import convert_to_dataarray
 
 
 def _xy_plot(x, y, fmt=".", label=None, xlabel=None, ylabel=None, title=None, ax=None):
@@ -74,8 +75,8 @@ def plot_flow_duration_curve(D, F, label=None, ax=None):
 
     """
     # Sort by F
-    temp = pd.DataFrame({"D": D, "F": F})
-    temp.sort_values("F", ascending=False, kind="mergesort", inplace=True)
+    temp = xr.Dataset(data_vars={"D": D, "F": F})
+    temp.sortby("F", ascending=False)
 
     ax = _xy_plot(
         temp["D"],
@@ -116,8 +117,8 @@ def plot_velocity_duration_curve(V, F, label=None, ax=None):
 
     """
     # Sort by F
-    temp = pd.DataFrame({"V": V, "F": F})
-    temp.sort_values("F", ascending=False, kind="mergesort", inplace=True)
+    temp = xr.Dataset(data_vars={"V": V, "F": F})
+    temp.sortby("F", ascending=False)
 
     ax = _xy_plot(
         temp["V"],
@@ -157,8 +158,8 @@ def plot_power_duration_curve(P, F, label=None, ax=None):
 
     """
     # Sort by F
-    temp = pd.DataFrame({"P": P, "F": F})
-    temp.sort_values("F", ascending=False, kind="mergesort", inplace=True)
+    temp = xr.Dataset(data_vars={"P": P, "F": F})
+    temp.sortby("F", ascending=False)
 
     ax = _xy_plot(
         temp["P"],
@@ -173,7 +174,7 @@ def plot_power_duration_curve(P, F, label=None, ax=None):
     return ax
 
 
-def plot_discharge_timeseries(Q, label=None, ax=None):
+def plot_discharge_timeseries(Q, time_dimension="", label=None, ax=None):
     """
     Plots discharge time-series
 
@@ -182,6 +183,10 @@ def plot_discharge_timeseries(Q, label=None, ax=None):
     Q: array-like
         Discharge [m3/s] indexed by time
 
+    time_dimension: string (optional)
+        Name of the xarray dimension corresponding to time. If not supplied,
+        defaults to the first dimension.
+
     label: string
        Label to use in the legend
 
@@ -194,8 +199,13 @@ def plot_discharge_timeseries(Q, label=None, ax=None):
     ax : matplotlib pyplot axes
 
     """
+    Q = convert_to_dataarray(Q)
+
+    if time_dimension == "":
+        time_dimension = list(Q.coords)[0]
+
     ax = _xy_plot(
-        Q.index,
+        Q.coords[time_dimension].values,
         Q,
         fmt="-",
         label=label,
@@ -213,10 +223,10 @@ def plot_discharge_vs_velocity(D, V, polynomial_coeff=None, label=None, ax=None)
 
     Parameters
     ------------
-    D : pandas Series
+    D : array-like
         Discharge [m/s] indexed by time
 
-    V : pandas Series
+    V : array-like
         Velocity [m/s] indexed by time
 
     polynomial_coeff: numpy polynomial
@@ -263,10 +273,10 @@ def plot_velocity_vs_power(V, P, polynomial_coeff=None, label=None, ax=None):
 
     Parameters
     ------------
-    V : pandas Series
+    V : array-like
         Velocity [m/s] indexed by time
 
-    P: pandas Series
+    P: array-like
         Power [W] indexed by time
 
     polynomial_coeff: numpy polynomial