nearest neighbor search method

create_doren.py

@@ -18,8 +18,8 @@ cv_temp_dir = r'c:\Users\roelo008\OneDrive - WageningenUR\a_projects\DOREN\a_bro
 cv_temp_src = "EObs_v200e_tg_5yrmean"
 sp_req_src = r'c:\Users\roelo008\OneDrive - WageningenUR\a_projects\DOREN\z_scratch\soortenlijst.csv'
 
-doren = dc.Doren(header_src= param_header_src, sp_src=param_sp_src)
-doren.initiate()
+doren = dc.Doren(header_src=param_header_src, sp_src=param_sp_src)
+doren.initiate(sample=True)
 doren.rename(old_name='Oxycoccus palustris', new_name='Vaccinium oxycoccos')
 doren.apply_requirements('req1', 'req2', 'req3', 'req4', 'req8', 'req9', 'req10', aoi_src=param_aoi_src,
                          dem_src=param_dem_src)

utils/doren.py

@@ -6,14 +6,19 @@ Helper functions for the DOREN project
 import os
 import json
 import rasterstats as rast
+import rasterio as rio
 import geopandas as gp
 import numpy as np
 import re
-import pyproj
 import shapely
 import pandas as pd
 from shapely.geometry import Polygon
 
+# set pyproj project library if needed
+if not os.environ['PROJ_LIB']:
+    os.environ['PROJ_LIB'] = 'C:\\Users\\roelo008\\AppData\\Local\\ESRI\\conda\\envs\\hdr001\\Library\\share'
+import pyproj
+
 
 def eva_colnames_orig():
     """
@@ -305,6 +310,7 @@ def get_raster_vals(coords, rast_src, nominal=False):
 
     if not os.path.isfile(rast_src):
         raise Exception('{0} does not exists as valid rastersource'.format(rast_src))
+    raster = rio.open(rast_src)
 
     interpolation = 'nearest' if nominal else 'bilinear'
 
@@ -316,10 +322,23 @@ def get_raster_vals(coords, rast_src, nominal=False):
         coords = coords.apply(shapely.geometry.Point)
 
     # the numeric raster values
-    rast_vals = rast.point_query(coords, rast_src, interpolate=interpolation)
+    rast_vals = rast.point_query(coords, raster.read(1), interpolate=interpolation, affine=raster.affine)
 
     return pd.DataFrame(data={'vals': rast_vals}, index=coords.index)
 
+
+def nearest(row, geom_union, df1, df2, geom1_col='geometry', geom2_col='geometry', src_column=None):
+    """
+    Find the nearest point and return the corresponding value from specified column.
+    Src: https://automating-gis-processes.github.io/CSC18/lessons/L4/nearest-neighbour.html
+    """
+
+    # Find the geometry that is closest
+    nearest = df2[geom2_col] == shapely.ops.nearest_points(row[geom1_col], geom_union)[1]
+    # Get the corresponding value from df2 (matching is based on the geometry)
+    value = df2[nearest][src_column].get_values()[0]
+    return value
+
 '''
 pattern = re.compile(r' s\.l\.$| subsp\.? | var\.? | aggr\.? | ""| ssp\.? | s\.? | mod\.? | \(')
 sp1 = 'Rosa spinosissima' # begint met s
@@ -338,6 +357,6 @@ sp12 = 'Rosa spinosissima mod. HANS'
 sp12 = 'Rosa spinosissima mod HANS'
 sps = [sp1,sp2,sp3,sp4,sp5,sp6,sp7,sp8,sp9,sp10,sp11,sp12]
 [re.split(pattern, x) for x in sps]
+pattern = re.compile(r'[A-Z]{1}[a-z]{1,} [a-z]{1,}')
 '''
 
-pattern = re.compile(r'[A-Z]{1}[a-z]{1,} [a-z]{1,}')
\ No newline at end of file

utils/doren_classes.py

@@ -454,6 +454,24 @@ class Doren:
         self.nearby_plots = nearby_plots
         self.buffer_size = buffer_size
 
+    def nearest_positive(self):
+        """
+        Determine distance of each negative plots to nearest positive plot.
+        :return:
+        """
+
+        origin = self.eva.loc[self.eva.index.difference(self.positive_plots)]
+        target = self.eva.loc[self.positive_plots]
+        unary_union = target.geometry.unary_union
+
+        nearest_n = origin.apply(do.nearest, geom_union=unary_union, df1=origin, df2=target,
+                                 geom1_col='plot_coordinates_3035', geom2_col='plot_coordinates_3035',
+                                 src_column='plot_id', axis=1)
+
+        # TODO: join nearest_n series to self.eva and put distance 0 for self.eva.loc[self.positive_plots]
+
+
+
     def write_stuff(self, what, covars=False):
         """
         Write contents to file. This should prob be organised as: self.generate_report(X) and then self.write_report(x)