diff --git a/src/plotting/postprocessing_plotting.py b/src/plotting/postprocessing_plotting.py
index 3a70e14f69de4929c55e688f3cc326525c546e36..a4e7173bebc7d25bc276251b66cd8beae2d6d2bd 100644
--- a/src/plotting/postprocessing_plotting.py
+++ b/src/plotting/postprocessing_plotting.py
@@ -861,45 +861,70 @@ class PlotAvailability(AbstractPlotClass):
@TimeTrackingWrapper
class PlotAvailabilityHistogram(AbstractPlotClass):
"""
+ Create data availability plots as histogram.
+ Each entry of each generator is checked for `notnull()` values along all the datetime axis (boolean).
+ Calling this class creates two different types of histograms where each generator
+
+ 1) data_availability_histogram: datetime (xaxis) vs. number of stations with availabile data (yaxis)
+ 2) data_availability_histogram_cumulative: number of samples (xaxis) vs. number of stations having at least number
+ of samples (yaxis)
"""
- def __init__(self, generators: Dict[str, DataGenerator], plot_folder: str = ".", sampling="daily"):
+ def __init__(self, generators: Dict[str, DataGenerator], plot_folder: str = ".", sampling="daily",
+ subset_dim: str = 'DataSet', temporal_dim: str = 'datetime', history_dim: str = 'window',
+ station_dim: str = 'Stations'):
super().__init__(plot_folder, "data_availability_histogram")
self.freq = self._get_sampling(sampling)
+ self.subset_dim = subset_dim
+ self.temporal_dim = temporal_dim
+ self.history_dim = history_dim
+ self.station_dim = station_dim
self._prepare_data(generators)
- self._plot(plt_type='hist')
- self._save()
- self.plot_name += '_cumulative'
- self._plot(plt_type='hist_cum')
- self._save()
+
+ for plt_type in self.allowed_plot_types:
+ plot_name_tmp = self.plot_name
+ self.plot_name += '_' + plt_type
+ self._plot(plt_type=plt_type)
+ self._save()
+ self.plot_name = plot_name_tmp
+
+ @property
+ def allowed_plot_types(self):
+ plot_types = ['hist', 'hist_cum']
+ return plot_types
def _prepare_data(self, generators: Dict[str, DataGenerator]):
+ """
+ Prepares data to be used by plot methods.
+
+ Creates xarrays which are sums of valid data (boolean sums) across i) station_dim and ii) temporal_dim
+ """
avail_data_time_sum = {}
avail_data_station_sum = {}
- dataset_time_interval={}
+ dataset_time_interval = {}
for subset, generator in generators.items():
avail_list = []
for station in generator.stations:
- station_data_X, _ = generator[station]
- station_data_X = station_data_X.loc[{'window': 0, # select recent window frame
+ station_data_x, _ = generator[station]
+ station_data_x = station_data_x.loc[{self.history_dim: 0, # select recent window frame
generator.target_dim: generator.variables[0]}]
- avail_list.append(station_data_X.notnull())
- avail_data = xr.concat(avail_list, dim='Stations').notnull()
- avail_data_time_sum[subset] = avail_data.sum(dim='Stations')
- avail_data_station_sum[subset] = avail_data.sum(dim='datetime')
+ avail_list.append(station_data_x.notnull())
+ avail_data = xr.concat(avail_list, dim=self.station_dim).notnull()
+ avail_data_time_sum[subset] = avail_data.sum(dim=self.station_dim)
+ avail_data_station_sum[subset] = avail_data.sum(dim=self.temporal_dim)
dataset_time_interval[subset] = self._get_first_and_last_indexelement_from_xarray(
- avail_data_time_sum[subset], dim_name='datetime', return_type='as_dict'
+ avail_data_time_sum[subset], dim_name=self.temporal_dim, return_type='as_dict'
)
avail_data_amount = xr.concat(avail_data_time_sum.values(), pd.Index(avail_data_time_sum.keys(),
- name='DataSet')
+ name=self.subset_dim)
)
- full_time_index = self._make_full_time_index(avail_data_amount.coords['datetime'].values, freq=self.freq)
+ full_time_index = self._make_full_time_index(avail_data_amount.coords[self.temporal_dim].values, freq=self.freq)
self.avail_data_cum_sum = xr.concat(avail_data_station_sum.values(), pd.Index(avail_data_station_sum.keys(),
- name='DataSet'))
- self.avail_data_amount = avail_data_amount.reindex({'datetime': full_time_index})
+ name=self.subset_dim))
+ self.avail_data_amount = avail_data_amount.reindex({self.temporal_dim: full_time_index})
self.dataset_time_interval = dataset_time_interval
@staticmethod
@@ -930,19 +955,19 @@ class PlotAvailabilityHistogram(AbstractPlotClass):
raise ValueError(f"plt_type mus be 'hist' or 'hist_cum', but is {type}")
def _plot_hist(self, *args):
- # for dataset in
colors = self.get_dataset_colors()
fig, axes = plt.subplots(figsize=(10, 3))
for i, subset in enumerate(self.dataset_time_interval.keys()):
- plot_dataset = self.avail_data_amount.sel({'DataSet': subset,
- 'datetime': slice(self.dataset_time_interval[subset]['first'],
- self.dataset_time_interval[subset]['last']
- )
+ plot_dataset = self.avail_data_amount.sel({self.subset_dim: subset,
+ self.temporal_dim: slice(
+ self.dataset_time_interval[subset]['first'],
+ self.dataset_time_interval[subset]['last']
+ )
}
)
plot_dataset.plot.step(color=colors[subset], ax=axes, label=subset)
- plt.fill_between(plot_dataset.coords['datetime'].values, plot_dataset.values, color=colors[subset])
+ plt.fill_between(plot_dataset.coords[self.temporal_dim].values, plot_dataset.values, color=colors[subset])
lgd = fig.legend(loc="upper right", ncol=len(self.dataset_time_interval))
for lgd_line in lgd.get_lines():
@@ -957,25 +982,28 @@ class PlotAvailabilityHistogram(AbstractPlotClass):
fig, axes = plt.subplots(figsize=(10, 3))
n_bins = int(self.avail_data_cum_sum.max().values)
bins = np.arange(0, n_bins+1)
- descending_subsets = self.avail_data_cum_sum.max(dim='Stations').sortby(
- self.avail_data_cum_sum.max(dim='Stations'), ascending=False
- ).coords['DataSet'].values
+ descending_subsets = self.avail_data_cum_sum.max(dim=self.station_dim).sortby(
+ self.avail_data_cum_sum.max(dim=self.station_dim), ascending=False
+ ).coords[self.subset_dim].values
for subset in descending_subsets:
- self.avail_data_cum_sum.sel({'DataSet': subset}).plot.hist(ax=axes,
- bins=bins,
- label=subset,
- cumulative=-1,
- color=colors[subset],
- alpha=.6)
-
- lgd = fig.legend(loc="upper right", ncol=len(self.dataset_time_interval))
+ self.avail_data_cum_sum.sel({self.subset_dim: subset}).plot.hist(ax=axes,
+ bins=bins,
+ label=subset,
+ cumulative=-1,
+ color=colors[subset],
+ # alpha=.5
+ )
+
+ lgd = fig.legend(loc="upper right", ncol=len(self.dataset_time_interval),
+ facecolor='white', framealpha=1, edgecolor='black')
plt.title('')
plt.ylabel('Number of stations')
plt.xlabel('Number of samples')
plt.xlim((bins[0], bins[-1]))
plt.tight_layout()
+
if __name__ == "__main__":
stations = ['DEBW107', 'DEBY081', 'DEBW013', 'DEBW076', 'DEBW087']
path = "../../testrun_network/forecasts"