Merge pull request #197 from DataverseLabs/main-neighbors-selection

V0.2.4

__init__.py

@@ -1 +1 @@
-__version__ = '0.2.3.post1'
+__version__ = '0.2.4'

changelog.rst

@@ -6,15 +6,18 @@ PyInterpolate is designed as the Python library for geostatistics. It's role is
 Changes by date
 ===============
 
-2021-XX-XX
+2021-12-11
 ----------
 
-**version 0.2.XX**
+**version 0.2.4**
 
 * `self.points_values` chenged to `self.points_array` in `TheoreticalSemivariogram` class,
 * `NaN` values are tested and checked in `calc_semivariance_from_pt_cloud()` function,
 * new semivariogram models included in the package: **cubic**, **circular**, **power**,
-
+* corrected calculation of the closest neighbors for kriging interpolation,
+* changed `prepare_kriging_data()` function,
+* the new optional parameter `check_coordinates` (**bool**) of `calc_point_to_point_distance()` function to control the coordinates uniqueness tests. This test is very resource-consuming and should be avoided in a normal work and it should be performed before data injection into the modeling pipeline.
+* the new `dev/profiling/` directory to test and profile parts of a code.
 
 2021-08-23
 ----------

docs/build/doctrees/nbsphinx/code_documentation/distance.ipynb

@@ -21,15 +21,18 @@
     "```python\n",
     "pyinterpolate.distance.calc_point_to_point_distance(\n",
     "    points_a,\n",
-    "    points_b=None)\n",
+    "    points_b=None,\n",
+    "    check_coordinates=False\n",
+    ")\n",
     "```\n",
     "\n",
     "Function calculates distances between all points in the given array.\n",
     "\n",
     "INPUT:\n",
     "\n",
     "- **points_a**: (_numpy array_) points coordinates,\n",
-    "- **points_b**: (_numpy array_) points coordinates, default is `None`. If `None` is given then distances between all points within `points_a` is calculated.\n",
+    "- **points_b**: (_numpy array_) points coordinates, default is `None`. If `None` is given then distances between all points within `points_a` is calculated,\n",
+    "- **check_coordinates**: (_bool_) checks if coordinates are unique within a given array. It is a resource-consuming process and it should be invoked with caution, especially for large datasets.\n",
     "\n",
     "OUTPUT:\n",
     "\n",
@@ -54,7 +57,7 @@
     "pyinterpolate.distance.calc_block_to_block_distance(areas)\n",
     "```\n",
     "\n",
-    "Function calculates distances between blocks based on the population points within the block.\n",
+    "Function calculates distances between all given blocks.\n",
     "\n",
     "INPUT:\n",
     "\n",
@@ -94,7 +97,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -108,7 +111,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.8"
+   "version": "3.7.12"
   }
  },
  "nbformat": 4,

docs/build/doctrees/nbsphinx/code_documentation/kriging.ipynb

@@ -269,7 +269,9 @@
     "```python\n",
     "Krige.ordinary_kriging(self,\n",
     "                       unknown_location,\n",
-    "                       number_of_neighbours,\n",
+    "                       neighbors_range=None,\n",
+    "                       min_no_neighbors=1,\n",
+    "                       max_no_neighbors=256,\n",
     "                       test_anomalies=True)\n",
     "```\n",
     "\n",
@@ -278,7 +280,9 @@
     "INPUT:\n",
     "\n",
     "- **unknown_location**: (_tuple_) position of unknown location,\n",
-    "- **number_of_neighbours**: (_int_) number of the closest locations to the unknown position which should be included in the modeling,\n",
+    "- **neighbors_range**: (_float_) distance for each neighbors are affecting the interpolated point, if not given then it is set to the semivariogram range,\n",
+    "- **min_no_neighbors**: (int) minimum number of neighbors used for interpolation if there is not any neighbor within the range specified by neighbors_range,\n",
+    "- **max_no_neighbors**: (_int_) maximum number of n-closest neighbors used for interpolation if there are too many neighbors in range. It speeds up calculations for large datasets and affects final prediction error.\n",
     "- **test_anomalies**: (_bool_) check if weights are negative.\n",
     "\n",
     "OUTPUT:\n",
@@ -301,8 +305,10 @@
     "```python\n",
     "Krige.simple_kriging(self,\n",
     "                     unknown_location,\n",
-    "                     number_of_neighbours,\n",
     "                     global_mean,\n",
+    "                     neighbors_range=None,\n",
+    "                     min_no_neighbors=1,\n",
+    "                     max_no_neighbors=256,\n",
     "                     test_anomalies=True)\n",
     "```\n",
     "\n",
@@ -311,8 +317,10 @@
     "INPUT:\n",
     "\n",
     "- **unknown_location**: (_tuple_) position of unknown location,\n",
-    "- **number_of_neighbours**: (_int_) number of the closest locations to the unknown position which should be included in the modeling,\n",
     "- **global_mean**: (_float_) global mean which should be known before processing,\n",
+    "- **neighbors_range**: (_float_) distance for each neighbors are affecting the interpolated point, if not given then it is set to the semivariogram range,\n",
+    "- **min_no_neighbors**: (int) minimum number of neighbors used for interpolation if there is not any neighbor within the range specified by neighbors_range,\n",
+    "- **max_no_neighbors**: (_int_) maximum number of n-closest neighbors used for interpolation if there are too many neighbors in range. It speeds up calculations for large datasets and affects final prediction error.\n",
     "- **test_anomalies**: (_bool_) check if weights are negative.\n",
     "\n",
     "OUTPUT:\n",
@@ -328,11 +336,18 @@
     "]\n",
     "```"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "---"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -346,7 +361,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.7.12"
   }
  },
  "nbformat": 4,

docs/build/doctrees/nbsphinx/code_documentation/semivariance.ipynb

@@ -707,6 +707,9 @@
     "    - gaussian_model(distance, nugget, sill, semivar_range)\n",
     "    - exponential_model(distance, nugget, sill, semivar_range)\n",
     "    - linear_model(distance, nugget, sill, semivar_range)\n",
+    "    - cubic_model(distance, nugget, sill, semivar_range)\n",
+    "    - circular_model(distance, nugget, sill, semivar_range)\n",
+    "    - power_model(distance, nugget, sill, semivar_range)\n",
     "\n",
     "\n",
     "INITIALIZATION PARAMS:\n",
@@ -846,7 +849,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.10"
+   "version": "3.7.12"
   }
  },
  "nbformat": 4,

docs/build/doctrees/nbsphinx/code_documentation/transform.ipynb

@@ -28,7 +28,6 @@
   {
    "cell_type": "markdown",
    "metadata": {
-    "collapsed": false,
     "pycharm": {
      "name": "#%% md\n"
     }
@@ -93,7 +92,6 @@
   {
    "cell_type": "markdown",
    "metadata": {
-    "collapsed": false,
     "pycharm": {
      "name": "#%% md\n"
     }
@@ -105,7 +103,6 @@
   {
    "cell_type": "markdown",
    "metadata": {
-    "collapsed": false,
     "pycharm": {
      "name": "#%% md\n"
     }
@@ -147,7 +144,10 @@
     "pyinterpolate.transform.prepare_kriging_data(\n",
     "    unknown_position,\n",
     "    data_array,\n",
-    "    number_of_neighbours=10)\n",
+    "    neighbors_range,\n",
+    "    min_number_of_neighbors=1,\n",
+    "    max_number_of_neighbors=256\n",
+    ")\n",
     "```\n",
     "\n",
     "Function prepares data for kriging - array of point position, value and distance to an unknown point.\n",
@@ -157,7 +157,9 @@
     "\n",
     "- **unknown_position**: (_numpy array_) position of unknown value,\n",
     "- **data_array**: (_numpy array_) known positions and their values,\n",
-    "- **number_of_neighbours**: (_int_) number of the closest locations to the unknown position.\n",
+    "- **neighbors_range**: (_float_) range within neighbors are included in the prediction,\n",
+    "- **min_number_of_neighbors**: (_int_) number of the n-closest neighbors used for interpolation if not any neighbor is selected within neighbors_range,\n",
+    "- **max_number_of_neighbors**: (_int_) maximum number of n-closest neighbors used for interpolation if there are too many neighbors in range. It speeds up calculations for large datasets.\n",
     "\n",
     "\n",
     "OUTPUT:\n",
@@ -462,7 +464,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -476,7 +478,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.7.12"
   }
  },
  "nbformat": 4,