diff --git a/src/plotting/postprocessing_plotting.py b/src/plotting/postprocessing_plotting.py
index 48606d4f8531812672391304b41885555608473b..14e3074a7d8f09bd597fb2fbf53a298d83ab6556 100644
--- a/src/plotting/postprocessing_plotting.py
+++ b/src/plotting/postprocessing_plotting.py
@@ -16,6 +16,7 @@ import pandas as pd
import seaborn as sns
import xarray as xr
from matplotlib.backends.backend_pdf import PdfPages
+import matplotlib.patches as mpatches
from src import helpers
from src.helpers import TimeTracking, TimeTrackingWrapper
@@ -33,14 +34,14 @@ class AbstractPlotClass:
def _plot(self, *args):
raise NotImplementedError
-
- def _save(self):
+
+ def _save(self, **kwargs):
"""
Standard save method to store plot locally. Name of and path to plot need to be set on initialisation
"""
plot_name = os.path.join(os.path.abspath(self.plot_folder), f"{self.plot_name}.pdf")
logging.debug(f"... save plot to {plot_name}")
- plt.savefig(plot_name, dpi=self.resolution)
+ plt.savefig(plot_name, dpi=self.resolution, **kwargs)
plt.close('all')
@@ -626,12 +627,24 @@ class PlotTimeSeries:
@TimeTrackingWrapper
class PlotAvailability(AbstractPlotClass):
- def __init__(self, generators: Dict[str, DataGenerator], plot_folder: str = ".", sampling="daily"):
+ def __init__(self, generators: Dict[str, DataGenerator], plot_folder: str = ".", sampling="daily",
+ summary_name="data availability"):
+ # create standard Gantt plot for all stations (currently in single pdf file with single page)
super().__init__(plot_folder, "data_availability")
self.sampling = self._get_sampling(sampling)
plot_dict = self._prepare_data(generators)
- self._plot(plot_dict)
- self._save()
+ lgd = self._plot(plot_dict)
+ self._save(bbox_extra_artists=(lgd, ), bbox_inches="tight")
+ # create summary Gantt plot (is data in at least one station available)
+ self.plot_name += "_summary"
+ plot_dict_summary = self._summarise_data(generators, summary_name)
+ lgd = self._plot(plot_dict_summary)
+ self._save(bbox_extra_artists=(lgd, ), bbox_inches="tight")
+ # combination of station and summary plot, last element is summary broken bar
+ self.plot_name = "data_availability_combined"
+ plot_dict_summary.update(plot_dict)
+ lgd = self._plot(plot_dict_summary)
+ self._save(bbox_extra_artists=(lgd, ), bbox_inches="tight")
@staticmethod
def _get_sampling(sampling):
@@ -659,12 +672,37 @@ class PlotAvailability(AbstractPlotClass):
plt_dict[station].update({subset: t2})
return plt_dict
+ def _summarise_data(self, generators: Dict[str, DataGenerator], summary_name: str):
+ plt_dict = {}
+ for subset, generator in generators.items():
+ all_data = None
+ stations = generator.stations
+ for station in stations:
+ station_data = generator.get_data_generator(station)
+ labels = station_data.get_transposed_label().resample(datetime=self.sampling, skipna=True).mean()
+ labels_bool = labels.sel(window=1).notnull()
+ if all_data is None:
+ all_data = labels_bool
+ else:
+ tmp = all_data.combine_first(labels_bool) # expand dims to merged datetime coords
+ all_data = np.logical_or(tmp, labels_bool).combine_first(all_data) # apply logical on merge and fill missing with all_data
+
+ group = (all_data != all_data.shift(datetime=1)).cumsum()
+ plot_data = pd.DataFrame({"avail": all_data.values, "group": group.values}, index=all_data.datetime.values)
+ t = plot_data.groupby("group").apply(lambda x: (x["avail"].head(1)[0], x.index[0], x.shape[0]))
+ t2 = [i[1:] for i in t if i[0]]
+ if plt_dict.get(summary_name) is None:
+ plt_dict[summary_name] = {subset: t2}
+ else:
+ plt_dict[summary_name].update({subset: t2})
+ return plt_dict
+
+
def _plot(self, plt_dict):
- # colors = {"train": "orange", "val": "skyblue", "test": "blueishgreen"}
- colors = {"train": "#e69f00", "val": "#56b4e9", "test": "#009e73"}
- # colors = {"train": (230, 159, 0), "val": (86, 180, 233), "test": (0, 158, 115)}
+ # colors = {"train": "orange", "val": "blueishgreen", "test": "skyblue"} # color names
+ colors = {"train": "#e69f00", "val": "#009e73", "test": "#56b4e9"} # hex code
+ # colors = {"train": (230, 159, 0), "val": (0, 158, 115), "test": (86, 180, 233)} # in rgb but as abs values
pos = 0
- count = 0
height = 0.8 # should be <= 1
yticklabels = []
number_of_stations = len(plt_dict.keys())
@@ -681,4 +719,6 @@ class PlotAvailability(AbstractPlotClass):
ax.set_ylim([height, number_of_stations + 1])
ax.set_yticks(np.arange(len(plt_dict.keys()))+1+height/2)
ax.set_yticklabels(yticklabels)
- plt.tight_layout()
+ handles = [mpatches.Patch(color=c, label=k) for k, c in colors.items()]
+ lgd = plt.legend(handles=handles, bbox_to_anchor=(0, 1, 1, 0.2), loc="lower center", ncol=len(handles))
+ return lgd
diff --git a/src/run_modules/experiment_setup.py b/src/run_modules/experiment_setup.py
index 95bd5056febbe06babfd59191332c1f4cb8078d4..150399cb2e4997a6b9adfb30dfa3ff89de73d4ac 100644
--- a/src/run_modules/experiment_setup.py
+++ b/src/run_modules/experiment_setup.py
@@ -21,7 +21,8 @@ DEFAULT_VAR_ALL_DICT = {'o3': 'dma8eu', 'relhum': 'average_values', 'temp': 'max
'pblheight': 'maximum'}
DEFAULT_TRANSFORMATION = {"scope": "data", "method": "standardise", "mean": "estimate"}
DEFAULT_PLOT_LIST = ["PlotMonthlySummary", "PlotStationMap", "PlotClimatologicalSkillScore", "PlotTimeSeries",
- "PlotCompetitiveSkillScore", "PlotBootstrapSkillScore", "plot_conditional_quantiles"]
+ "PlotCompetitiveSkillScore", "PlotBootstrapSkillScore", "plot_conditional_quantiles",
+ "PlotAvailability"]
class ExperimentSetup(RunEnvironment):
diff --git a/src/run_modules/post_processing.py b/src/run_modules/post_processing.py
index 1361dab63e93ea813c3b92394822fb683c7621c1..8a962888ec0b789a14a24b20c97148e7a8315b30 100644
--- a/src/run_modules/post_processing.py
+++ b/src/run_modules/post_processing.py
@@ -214,8 +214,9 @@ class PostProcessing(RunEnvironment):
if "PlotTimeSeries" in plot_list:
PlotTimeSeries(self.test_data.stations, path, r"forecasts_%s_test.nc", plot_folder=self.plot_path,
sampling=self._sampling)
- avail_data = {"train": self.train_data, "val": self.val_data, "test": self.test_data}
- PlotAvailability(avail_data, plot_folder=self.plot_path)
+ if "PlotAvailability" in plot_list:
+ avail_data = {"train": self.train_data, "val": self.val_data, "test": self.test_data}
+ PlotAvailability(avail_data, plot_folder=self.plot_path)
def calculate_test_score(self):
test_score = self.model.evaluate_generator(generator=self.test_data_distributed.distribute_on_batches(),