Merge pull request #11 from JannisHoch/adding_more_vars

Adding more vars for ML

.vscode/settings.json

@@ -1,4 +1,4 @@
 {
-    "python.pythonPath": "C:\\Users\\hoch0001\\AppData\\Local\\Continuum\\anaconda3\\envs\\conflict_model\\python.exe",
+    "python.pythonPath": "C:\\Users\\hoch0001\\AppData\\Local\\Continuum\\anaconda3\\python.exe",
     "restructuredtext.confPath": "${workspaceFolder}\\docs"
 }

conflict_model/analysis.py

@@ -22,7 +22,7 @@ def conflict_in_year_bool(conflict_gdf, extent_gdf, config, sim_year, out_dir, s
         dataframe: dataframe containing column with boolean information about conflict for each year
     """    
 
-    print('determining whether a conflict took place or not...')
+    print('determining whether a conflict took place or not')
 
     out_df = extent_gdf.copy()
 

conflict_model/env_vars_nc.py

@@ -1,14 +1,15 @@
 import xarray as xr
 import rasterio as rio
+import pandas as pd
 import geopandas as gpd
 import rasterstats as rstats
 import numpy as np
 import matplotlib.pyplot as plt
 import os, sys
 
-def rasterstats_GDP_PPP(gdf_in, config, sim_year, out_dir, saving_plots=False, showing_plots=False):
+def rasterstats_GDP_PPP(gdf, config, sim_year, out_dir, saving_plots=False, showing_plots=False):
 
-    print('calculating zonal statistics per aggregation unit')
+    print('calculating GDP PPP mean per aggregation unit')
 
     nc_fo = os.path.join(config.get('general', 'input_dir'), 
                          config.get('env_vars', 'GDP_PPP'))
@@ -17,6 +18,46 @@ def rasterstats_GDP_PPP(gdf_in, config, sim_year, out_dir, saving_plots=False, s
 
     nc_var = nc_ds['GDP_per_capita_PPP']
 
+    # years = pd.to_datetime(nc_ds.time.values).to_period(freq='Y').strftime('%Y').to_numpy(dtype=int)
+    # if sim_year not in years:
+    #     raise ValueError('the simulation year {0} can not be found in file {1}'.format(sim_year, nc_fo))
+    # sim_year_idx = int(np.where(years == sim_year)[0])
+
+    affine = rio.open(nc_fo).transform
+
+    # gdf['zonal_stats_min_' + str(sim_year)] = np.nan
+    # gdf['zonal_stats_max_' + str(sim_year)] = np.nan
+    # gdf['GDP_PPP_mean_' + str(sim_year)] = np.nan
+
+    nc_arr = nc_var.sel(time=sim_year)
+    nc_arr_vals = nc_arr.values
+    if nc_arr_vals.size == 0:
+        raise ValueError('the data was found for this year in the nc-file {}, check if all is correct'.format(nc_fo))
+
+    list_GDP_PPP = []
+
+    for i in range(len(gdf)):
+        prov = gdf.iloc[i]
+        zonal_stats = rstats.zonal_stats(prov.geometry, nc_arr_vals, affine=affine, stats="mean")
+        # gdf.loc[i, 'zonal_stats_min_' + str(sim_year)] = zonal_stats[0]['min']
+        # gdf.loc[i, 'zonal_stats_max_' + str(sim_year)] = zonal_stats[0]['max']
+        list_GDP_PPP.append(zonal_stats[0]['mean'])
+
+    print('...DONE' + os.linesep)
+
+    return list_GDP_PPP
+
+def rasterstats_totalEvap(gdf_in, config, sim_year, out_dir):
+
+    print('calculating evaporation mean per aggregation unit')
+
+    nc_fo = os.path.join(config.get('general', 'input_dir'), 
+                         config.get('env_vars', 'evaporation'))
+
+    nc_ds = xr.open_dataset(nc_fo)
+
+    nc_var = nc_ds['total_evaporation']
+
     years = nc_ds['time'].values
     years = years[years>=config.getint('settings', 'y_start')]
     years = years[years<=config.getint('settings', 'y_end')]
@@ -25,9 +66,7 @@ def rasterstats_GDP_PPP(gdf_in, config, sim_year, out_dir, saving_plots=False, s
 
     gdf = gdf_in.copy()
 
-    gdf['zonal_stats_min_' + str(sim_year)] = np.nan
-    gdf['zonal_stats_max_' + str(sim_year)] = np.nan
-    gdf['zonal_stats_mean_' + str(sim_year)] = np.nan
+    gdf['evap_mean_' + str(sim_year)] = np.nan
 
     nc_arr = nc_var.sel(time=sim_year)
     nc_arr_vals = nc_arr.values
@@ -36,68 +75,9 @@ def rasterstats_GDP_PPP(gdf_in, config, sim_year, out_dir, saving_plots=False, s
 
     for i in range(len(gdf)):
         prov = gdf.iloc[i]
-        zonal_stats = rstats.zonal_stats(prov.geometry, nc_arr_vals, affine=affine, stats="mean min max")
-        gdf.loc[i, 'zonal_stats_min_' + str(sim_year)] = zonal_stats[0]['min']
-        gdf.loc[i, 'zonal_stats_max_' + str(sim_year)] = zonal_stats[0]['max']
-        gdf.loc[i, 'zonal_stats_mean_' + str(sim_year)] = zonal_stats[0]['mean']
+        zonal_stats = rstats.zonal_stats(prov.geometry, nc_arr_vals, affine=affine, stats="mean")
+        gdf.loc[i, 'evap_mean_' + str(sim_year)] = zonal_stats[0]['mean']
 
     print('...DONE' + os.linesep)
 
-    fig, axes = plt.subplots(1, 3 , figsize=(20, 10))
-
-    fig.suptitle(str(int(sim_year)), y=0.78)
-
-    gdf.plot(ax=axes[0],
-                column='zonal_stats_min_' + str(sim_year),
-                vmin=2000,
-                vmax=15000,
-                legend=True,
-                legend_kwds={'label': "min GDP_PPP",
-                                'orientation': "vertical",
-                                'shrink': 0.5,
-                                'extend': 'both'})
-    gdf.boundary.plot(ax=axes[0],
-                                color='0.5',
-                                linestyle=':',
-                                label='water province borders')
-
-    gdf.plot(ax=axes[1],
-                column='zonal_stats_max_' + str(sim_year),
-                vmin=2000,
-                vmax=15000,
-                legend=True,
-                legend_kwds={'label': "max GDP_PPP",
-                                'orientation': "vertical",
-                                'shrink': 0.5,
-                                'extend': 'both'})
-    gdf.boundary.plot(ax=axes[1],
-                                color='0.5',
-                                linestyle=':',
-                                label='water province borders')
-
-    gdf.plot(ax=axes[2],
-                column='zonal_stats_mean_' + str(sim_year),
-                vmin=2000,
-                vmax=15000,
-                legend=True,
-                legend_kwds={'label': "mean GDP_PPP",
-                                'orientation': "vertical",
-                                'shrink': 0.5,
-                                'extend': 'both'})
-    gdf.boundary.plot(ax=axes[2],
-                                color='0.5',
-                                linestyle=':',
-                                label='water province borders')
-
-    plt.tight_layout()
-
-    plt_name = 'GDP_PPP_zonal_stats_' + str(int(sim_year)) + '.png'
-    plt_name = os.path.join(out_dir, plt_name)
-
-    if saving_plots:
-        plt.savefig(plt_name, dpi=300)
-
-    if showing_plots == False:
-        plt.close()
-
     return gdf

data/run_setting.cfg

@@ -21,4 +21,5 @@ zones=BWh,BSh
 code2class=KoeppenGeiger/classification_codes.txt
 
 [env_vars]
-GDP_PPP=GDP_HDI/GDP_per_capita_PPP_1990_2015_Africa.nc
+GDP_PPP=GDP_HDI/GDP_per_capita_PPP_1990_2015_Africa.nc
+evaporation=PCRGLOBWB/totalEvap/totalEvaporation_monthTot_output_2000_2015_Africa_yearmean.nc