Fix kriging analysis bugs (#302)

* Update `requirements-dev.txt`

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add `jupyter-book` tests to `tox`

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Kriging_bug_removal (#7)

* Updates to report generation test file

* General updates

* Report generation functionality

* Bugfixes to the kriging method

* Revert report changes for just kriging debug merging

* Fix to test

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

echopop/spatial/krige.py

@@ -22,7 +22,10 @@ def kriging(transect_data: pd.DataFrame, mesh_data: pd.DataFrame, settings_dict:
 
     # Extract biological variable values
     # ---- Define the variable name
-    variable_name = settings_dict["variable"]
+    if "density" not in settings_dict["variable"]:
+        variable_name = settings_dict["variable"] + "_density"
+    else:
+        variable_name = settings_dict["variable"]
     # ---- Extract array
     variable_data = transect_data[variable_name].to_numpy()
 
@@ -83,6 +86,8 @@ def kriging(transect_data: pd.DataFrame, mesh_data: pd.DataFrame, settings_dict:
     # ---- Calculate the integrated variable when distributed over area
     # --------- Compute area
     area = settings_dict["kriging_parameters"]["A0"] * mesh_data["fraction_cell_in_polygon"]
+    # -------- Drop erroneous negative values along edge
+    kriged_values[kriged_values[:, 0] < 0, 0] = 0.0
     # -------- Distribute biological variable over area
     survey_estimate = np.nansum(kriged_values[:, 0] * area)
     # ---- Compute the georeferenced CV at each mesh node
@@ -478,7 +483,7 @@ def adaptive_search_radius(
 def kriging_lambda(
     anisotropy: float,
     lagged_semivariogram: np.ndarray,
-    kriging_matrix: np.ndarray,
+    kriging_matrix_input: np.ndarray,
 ):
     """
     Apply singular value decomposition (SVD) to compute kriging (lambda) weights
@@ -489,14 +494,14 @@ def kriging_lambda(
         Anisotropy ratio.
     lagged_semivariogram: np.array
         Lagged semivariogram
-    kriging_matrix: np.array
+    kriging_matrix_input: np.array
         Kriging matrix.
     """
     # Singular value decomposition (SVD)
     # ---- U: left singular vectors (directions of maximum variance)
     # ---- Sigma: singular values (amount of variance captured by each singular vector, U)
     # ---- VH: conjugate transpose of the right singular vectors
-    U, Sigma, VH = np.linalg.svd(kriging_matrix, full_matrices=True)
+    U, Sigma, VH = np.linalg.svd(kriging_matrix_input, full_matrices=True)
 
     # Create Sigma mask informed by the ratio-threshold
     # ---- The ratio between all singular values and their respective

echopop/survey.py

@@ -908,7 +908,10 @@ def kriging_analysis(
                         and "model_config" in self.input["statistics"]["variogram"]
                     )
                     else (
-                        self.input["statistics"]["variogram"]["model_config"]
+                        {
+                            **self.input["statistics"]["variogram"]["model_config"],
+                            **{"model": ["exponential", "bessel"], "n_lags": 30},
+                        }
                         if (
                             not variogram_parameters
                             and "model_config" in self.input["statistics"]["variogram"]

echopop/tests/test_pydantic_validation.py

@@ -1124,12 +1124,12 @@ def test_KrigingParameterInputs_model_structure(description):
         (dict(), None, "Both 'correlation_range' and 'search_radius' arguments are missing"),
         (
             dict(correlation_range=1.0),
-            dict(anisotropy=0.0, kmin=3, kmax=10, correlation_range=1.0, search_radius=3.0),
+            dict(anisotropy=1e-3, kmin=3, kmax=10, correlation_range=1.0, search_radius=3.0),
             None,
         ),
         (
             dict(correlation_range=1.0, search_radius=5.0),
-            dict(anisotropy=0.0, kmin=3, kmax=10, correlation_range=1.0, search_radius=5.0),
+            dict(anisotropy=1e-3, kmin=3, kmax=10, correlation_range=1.0, search_radius=5.0),
             None,
         ),
         (

echopop/utils/validate_dict.py

@@ -914,7 +914,7 @@ def create(cls, **kwargs):
 class KrigingParameterInputs(
     BaseModel, arbitrary_types_allowed=True, title="kriging model parameters ('kriging_parameters')"
 ):
-    anisotropy: realposfloat = Field(default=0.0, allow_inf_nan=False)
+    anisotropy: realposfloat = Field(default=1e-3, allow_inf_nan=False)
     kmin: posint = Field(default=3, ge=3)
     kmax: posint = Field(default=10, ge=3)
     correlation_range: Optional[realposfloat] = Field(default=None, gt=0.0, allow_inf_nan=False)