post processing can plot station_map(), but countries are not filled with e.g....

post processing can plot station_map(), but countries are not filled with e.g. elevation data (just blank fill)

README.md

@@ -6,4 +6,10 @@ This is a collection of all relevant functions used for ML stuff in the ESDE gro
 
 See a description [here](https://towardsdatascience.com/a-simple-guide-to-the-versions-of-the-inception-network-7fc52b863202)
 or take a look on the papers [Going Deeper with Convolutions (Szegedy et al., 2014)](https://arxiv.org/abs/1409.4842)
-and [Network In Network (Lin et al., 2014)](https://arxiv.org/abs/1312.4400).
\ No newline at end of file
+and [Network In Network (Lin et al., 2014)](https://arxiv.org/abs/1312.4400).
+
+
+# Installation
+
+* Install __proj__ on your machine using the console. E.g. for opensuse / leap `zypper install proj`
+* c++ compiler required for cartopy installation
\ No newline at end of file

requirements.txt

@@ -14,4 +14,12 @@ statsmodels
 seaborn
 dask==0.20.2
 toolz  # for dask
-cloudpickle  # for dask
\ No newline at end of file
+cloudpickle  # for dask
+cython
+pyshp
+six
+pyproj
+shapely
+cartopy==0.16.0
+matplotlib
+pillow
\ No newline at end of file

src/plotting/postprocessing_plotting.py

@@ -8,10 +8,9 @@ import xarray as xr
 import matplotlib
 import seaborn as sns
 import matplotlib.pyplot as plt
+import cartopy.crs as ccrs
+import cartopy.feature as cfeature
 
-import dask.array as da
-import dask
-import dask.dataframe as ddf
 logging.getLogger('matplotlib').setLevel(logging.WARNING)
 
 
@@ -53,3 +52,30 @@ def plot_monthly_summary(stations, data_path, name: str, window_lead_time, targe
     plt.close('all')
 
 
+def plot_climsum_boxplot():
+    return
+
+
+def station_map(generators, plot_folder="."):
+
+    logging.debug("run station_map()")
+    fig = plt.figure(figsize=(10, 5))
+    ax = fig.add_subplot(1, 1, 1, projection=ccrs.PlateCarree())
+    ax.set_extent([0, 20, 42, 58], crs=ccrs.PlateCarree())
+    ax.add_feature(cfeature.COASTLINE.with_scale("10m"), edgecolor='black')
+    ax.add_feature(cfeature.LAKES.with_scale("50m"))
+    ax.add_feature(cfeature.OCEAN.with_scale("50m"))
+    ax.add_feature(cfeature.RIVERS.with_scale("10m"))
+    ax.add_feature(cfeature.BORDERS.with_scale("10m"), facecolor='none', edgecolor='black')
+
+    if generators is not None:
+        for color, gen in generators.items():
+            for k, v in enumerate(gen):
+                station_coords = gen.get_data_generator(k).meta.loc[['station_lon', 'station_lat']]
+                station_names = gen.get_data_generator(k).meta.loc[['station_id']]
+                IDx, IDy = float(station_coords.loc['station_lon'].values), float(station_coords.loc['station_lat'].values)
+                ax.plot(IDx, IDy, mfc=color, mec='k', marker='s', markersize=6, transform=ccrs.PlateCarree())
+
+    plot_path = os.path.join(os.path.abspath(plot_folder), 'test_map_plot.pdf')
+    plt.savefig(plot_path)
+    plt.close('all')

src/run_modules/post_processing.py

@@ -17,7 +17,7 @@ from src.model_modules.linear_model import OrdinaryLeastSquaredModel
 from src import statistics
 from src import helpers
 from src.helpers import TimeTracking
-from src.plotting.postprocessing_plotting import plot_monthly_summary
+from src.plotting.postprocessing_plotting import plot_monthly_summary, plot_climsum_boxplot, station_map
 
 
 class PostProcessing(RunEnvironment):
@@ -39,11 +39,14 @@ class PostProcessing(RunEnvironment):
         self.plot()
 
     def plot(self):
+        logging.debug("Run plotting routines...")
         path = self.data_store.get("forecast_path", "general")
         window_lead_time = self.data_store.get("window_lead_time", "general")
         target_var = self.data_store.get("target_var", "general")
+        station_map(generators={'b': self.test_data}, plot_folder=self.plot_path)
         plot_monthly_summary(self.test_data.stations, path, r"forecasts_%s_test.nc", window_lead_time, target_var,
                              plot_folder=self.plot_path)
+        # plot_climsum_boxplot()
 
     def calculate_test_score(self):
         test_score = self.model.evaluate(generator=self.test_data_distributed.distribute_on_batches(),