non-ascii char rm from filename

create_doren.py

@@ -22,7 +22,7 @@ sp_req_src = r'c:\Users\roelo008\Wageningen University & Research\DOREN - Genera
 sp_req_sheet, column = 'PGO-1', 'newsoort'
 # sp_req_src = r'c:\Users\roelo008\Wageningen University & Research\DOREN - General\2020-09-17 uniek soorten per habitat (2).xlsx'
 
-testing = False
+testing = True
 
 doren = dc.Doren(header_src=param_header_src, sp_src=param_sp_src)
 doren.initiate(sample=testing)
@@ -38,6 +38,14 @@ doren.add_posch(posch_src_dir=param_posch)
 doren.get_requested_species(xls=sp_req_src, sheet=sp_req_sheet, col=column, simplify_names=False)
 doren.test()
 
+sp = 'Holcus lanatus'
+doren.select_plts_w_species(species_name=sp)
+for structuurtype in doren.structuurtypes:
+    doren.nearest_positive_queryd(col='structuurtype', val=structuurtype)
+doren.get_bedekking_selected_sp()
+doren.write_stuff('plot_covars_file')
+
+doren.write_stuff('species_single_file')
 doren.write_stuff('species_list')
 doren.write_stuff('typische_soorten')
 doren.write_stuff('report')

utils/doren_classes.py

@@ -11,7 +11,6 @@ import datetime
 import matplotlib.pyplot as plt
 import matplotlib.patches as mpatches
 import shapely
-import random
 
 from utils import doren as do
 
@@ -45,6 +44,7 @@ class Doren:
         self.sel_sp_coverage = None   # Series of coverage of selected species in the positive plots
         self.buffer_gdf = None        # holder for geodataframe w. buffers
         self.sel_species = None       # holder for a species
+        self.sel_species_ascii = None # holder for a species name with ascci encondig
         self.buffer_size = None       # holder for buffer size
         self.structuurtypes = None    # holder for list of structuurtypes. Must be list, not set, for ordering!
         self.sample = False           # Dataset is a random sample of all plots, for testing purposes.
@@ -101,8 +101,9 @@ class Doren:
             self.weird_species = sp_series.loc[~sp_check]
 
         # Read EVA Header data
+        # header_src = r"W:\PROJECTS\Doren19\a_brondata\EVA\delivery_20201118\EVA_Doren_header.csv"
         eva = pd.read_csv(self.header_src, comment='#', sep=',', low_memory=False,
-                          memory_map=True,
+                          memory_map=True, quotechar='"',
                           usecols=['PlotObservationID', 'TV2 relevé number', 'Country','Longitude', 'Latitude',
                                    'Date of recording', 'Dataset', 'EUNIS_Old', 'EUNIS_New'])
         try:
@@ -121,6 +122,10 @@ class Doren:
         eva['plot_point_wgs84'] = [shapely.geometry.Point(x, y) for (x, y) in eva.plot_coordinates_wgs84]
         eva['plot_coordinates_3035'] = eva.plot_coordinates_wgs84.apply(do.lon_lat_2_east_north)
 
+        # Replace "," in composite EUNIS codes
+        eva.eunis_old = eva.eunis_old.str.replace(',', '-')
+        eva.eunis_new = eva.eunis_new.str.replace(',', '-')
+
         # Assign final EUNIS code using EUNIS_new where possible else EUNIS_old
         use_old_indx = eva.loc[(eva.eunis_new.isna()) | (eva.eunis_new == '?') | (eva.eunis_new == 'I')].index
         use_new_indx = eva.index.difference(use_old_indx)
@@ -128,7 +133,7 @@ class Doren:
         eva.loc[use_old_indx, 'eunis_code'] = eva.loc[use_old_indx, 'eunis_old']
         eva.loc[use_new_indx, 'eunis_src'] = 'eunis_new'
         eva.loc[use_old_indx, 'eunis_src'] = 'eunis_old'
-        eva.eunis_code.fillna('?')  # Fill NAs where EUNIS_Old was also NA
+        eva.eunis_code.fillna('?', inplace=True)  # Fill NAs where EUNIS_Old was also NA
 
         # Attach as attribute
         self.eva = gp.GeoDataFrame(eva, geometry='plot_coordinates_3035', crs={"init": "epsg:3035"})
@@ -543,6 +548,7 @@ class Doren:
 
         """header data of plots containing the species"""
         self.sel_species = species_name
+        self.sel_species_ascii = self.sel_species.replace('ë', 'e').encode('ascii', 'replace')
         self.positive_plots = set(self.spec.plot_obs_id[self.spec.species_name_hdr == species_name])
         self.negative_plots = self.eva.index.difference(self.positive_plots)
 
@@ -789,7 +795,8 @@ class Doren:
                 return None
 
             # Dedicated directory for the PG output and output filename
-            pg_out_name = '{0}_NDep_Nearest'.format(self.sel_species.replace(' ', '_'))
+            # TODO: replace non-ascii characters
+            pg_out_name = '{0}_NDep_Nearest'.format(self.sel_species_ascii)
             pg_dir = os.path.join(out_dir, 'pg_input')
             if not os.path.isdir(pg_dir):
                 os.mkdir(pg_dir)