interpolate_points() - introduction of new parameters

Author: SimonMolinsky

src/pyinterpolate/core/pipelines/interpolate.py

@@ -1,3 +1,4 @@
+from numpy.typing import ArrayLike
 import os
 
 import dask
@@ -7,12 +8,15 @@
 
 from pyinterpolate.kriging.point.ordinary import ok_calc
 from pyinterpolate.semivariogram.theoretical.classes.theoretical_variogram import TheoreticalVariogram
+from transform.geo import geometry_and_values_array
 
 
 def interpolate_points(
         theoretical_model: TheoreticalVariogram,
-        known_locations: np.ndarray,
-        unknown_locations: np.ndarray,
+        unknown_locations: ArrayLike,
+        known_locations: ArrayLike = None,
+        known_values: ArrayLike = None,
+        known_geometries: ArrayLike = None,
         neighbors_range=None,
         no_neighbors=4,
         max_tick=5.,
@@ -29,13 +33,22 @@ def interpolate_points(
     theoretical_model : TheoreticalVariogram
         Fitted theoretical variogram model.
 
-    known_locations : numpy array
-        The known locations: x, y, value.
-
     unknown_locations : numpy array
         Points where you want to estimate value
         ``[(x, y), ...] <-> [(lon, lat), ...]``.
 
+    known_locations : numpy array, optional
+        The known locations: ``[x, y, value]``.
+
+    known_values : ArrayLike, optional
+        Observation in the i-th geometry (from ``known_geometries``). Optional
+        parameter, if not given then ``known_locations`` must be provided.
+
+    known_geometries : ArrayLike, optional
+        Array or similar structure with geometries. It must have the same
+        length as ``known_values``. Optional parameter, if not given then
+        ``known_locations`` must be provided. Point type geometry.
+
     neighbors_range : float, default=None
         The maximum distance where we search for the neighbors.
         If ``None`` is given then range is selected from
@@ -69,6 +82,12 @@ def interpolate_points(
         ``[predicted value, variance error, longitude (x), latitude (y)]``
     """
 
+    if known_locations is None:
+        known_locations = geometry_and_values_array(
+            geometry=known_geometries,
+            values=known_values
+        )
+
     interpolated_results = []
 
     _disable_progress_bar = not progress_bar
@@ -94,8 +113,10 @@ def interpolate_points(
 
 def interpolate_points_dask(
         theoretical_model: TheoreticalVariogram,
-        known_locations: np.ndarray,
-        unknown_locations: np.ndarray,
+        unknown_locations: ArrayLike,
+        known_locations: ArrayLike = None,
+        known_values: ArrayLike = None,
+        known_geometries: ArrayLike = None,
         neighbors_range=None,
         no_neighbors=4,
         max_tick=5.,
@@ -114,13 +135,22 @@ def interpolate_points_dask(
     theoretical_model : TheoreticalVariogram
         Fitted theoretical variogram model.
 
-    known_locations : numpy array
-        The known locations: x, y, value.
-
     unknown_locations : numpy array
         Points where you want to estimate value
         ``[(x, y), ...] <-> [(lon, lat), ...]``.
 
+    known_locations : numpy array, optional
+        The known locations: ``[x, y, value]``.
+
+    known_values : ArrayLike, optional
+        Observation in the i-th geometry (from ``known_geometries``). Optional
+        parameter, if not given then ``known_locations`` must be provided.
+
+    known_geometries : ArrayLike, optional
+        Array or similar structure with geometries. It must have the same
+        length as ``known_values``. Optional parameter, if not given then
+        ``known_locations`` must be provided. Point type geometry.
+
     neighbors_range : float, default=None
         The maximum distance where we search for the neighbors.
         If ``None`` is given then range is selected from
@@ -159,6 +189,12 @@ def interpolate_points_dask(
         ``[predicted value, variance error, longitude (x), latitude (y)]``
     """
 
+    if known_locations is None:
+        known_locations = geometry_and_values_array(
+            geometry=known_geometries,
+            values=known_values
+        )
+
     if number_of_workers == -1:
         core_num = os.cpu_count()
         if core_num > 1:

src/pyinterpolate/semivariogram/experimental/experimental_semivariogram.py

@@ -35,13 +35,13 @@ def calculate_semivariance(ds: Union[ArrayLike, VariogramPoints] = None,
         ``[x, y, value]``
 
     values : ArrayLike, optional
-        Aggregated values of each block. Optional parameter, if not
-        given then ``ds`` must be provided.
+        Observation in the i-th geometry (from ``geometries``). Optional
+        parameter, if not given then ``ds`` must be provided.
 
     geometries : ArrayLike, optional
         Array or similar structure with geometries. It must have the same
         length as ``values``. Optional parameter, if not given then ``ds``
-        must be provided. Those must be point geometries!
+        must be provided. Point type geometry.
 
     step_size : float
         The fixed distance between lags grouping point neighbors.

src/pyinterpolate/transform/geo.py

@@ -5,7 +5,45 @@
 import numpy as np
 import pandas as pd
 
-from shapely.geometry import Polygon, MultiPolygon
+from shapely.geometry import Polygon, MultiPolygon, Point
+
+
+def geometry_and_values_array(geometry,
+                              values) -> ArrayLike:
+    """
+    Function creates single object from geometries and aggregated values.
+
+    Parameters
+    ----------
+    geometry : ArrayLike
+
+    values : ArrayLike
+
+    Returns
+    -------
+    : numpy array
+    """
+
+    if len(geometry) != len(values):
+        raise ValueError(
+            'Number of geometries must be equal to number of values'
+        )
+
+    arr = []
+
+    is_point = isinstance(geometry[0], Point)
+
+    if is_point:
+        for idx, rec in enumerate(geometry):
+            arr.append(
+                [rec.x, rec.y, values[idx]]
+            )
+    else:
+        for idx, rec in enumerate(geometry):
+            arr.append(
+                [rec[0], rec[1], values[idx]]
+            )
+    return np.array(arr)
 
 
 def largest_geometry(geometry: MultiPolygon) -> Polygon: