From 1043377b7fcd3a23682503dcbe6637b7f0f69fae Mon Sep 17 00:00:00 2001
From: Felix Kleinert <f.kleinert@fz-juelich.de>
Date: Thu, 15 Oct 2020 23:36:05 +0200
Subject: [PATCH] Include num_samples vs. num_stations plot #192 by using
extraction method from #191
---
src/plotting/postprocessing_plotting.py | 61 ++++++++++++++++++++-----
1 file changed, 49 insertions(+), 12 deletions(-)
diff --git a/src/plotting/postprocessing_plotting.py b/src/plotting/postprocessing_plotting.py
index a62b44bb..3a70e14f 100644
--- a/src/plotting/postprocessing_plotting.py
+++ b/src/plotting/postprocessing_plotting.py
@@ -865,17 +865,20 @@ class PlotAvailabilityHistogram(AbstractPlotClass):
"""
- def __init__(self, generators: Dict[str, DataGenerator], plot_folder: str = ".", sampling="daily",
- summary_name="data availability"):
+ def __init__(self, generators: Dict[str, DataGenerator], plot_folder: str = ".", sampling="daily"):
super().__init__(plot_folder, "data_availability_histogram")
self.freq = self._get_sampling(sampling)
self._prepare_data(generators)
- self._plot()
+ self._plot(plt_type='hist')
+ self._save()
+ self.plot_name += '_cumulative'
+ self._plot(plt_type='hist_cum')
self._save()
def _prepare_data(self, generators: Dict[str, DataGenerator]):
- avail_dict = {}
+ avail_data_time_sum = {}
+ avail_data_station_sum = {}
dataset_time_interval={}
for subset, generator in generators.items():
avail_list = []
@@ -884,13 +887,19 @@ class PlotAvailabilityHistogram(AbstractPlotClass):
station_data_X = station_data_X.loc[{'window': 0, # select recent window frame
generator.target_dim: generator.variables[0]}]
avail_list.append(station_data_X.notnull())
- avail_dict[subset] = xr.concat(avail_list, dim='Stations').notnull().sum(dim='Stations')
+ 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')
dataset_time_interval[subset] = self._get_first_and_last_indexelement_from_xarray(
- avail_dict[subset], dim_name='datetime', return_type='as_dict'
+ avail_data_time_sum[subset], dim_name='datetime', return_type='as_dict'
)
- avail_data_amount = xr.concat(avail_dict.values(), pd.Index(avail_dict.keys(), name='DataSet'))
+ avail_data_amount = xr.concat(avail_data_time_sum.values(), pd.Index(avail_data_time_sum.keys(),
+ name='DataSet')
+ )
full_time_index = self._make_full_time_index(avail_data_amount.coords['datetime'].values, freq=self.freq)
- self.avail_data_amount = avail_data_amount.reindex({'datetime': full_time_index}, fill_value=0.)
+ 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})
self.dataset_time_interval = dataset_time_interval
@staticmethod
@@ -912,10 +921,18 @@ class PlotAvailabilityHistogram(AbstractPlotClass):
full_time_index = pd.date_range(start=irregular_time_index[0], end=irregular_time_index[-1], freq=freq)
return full_time_index
- def _plot(self, *args):
+ def _plot(self, plt_type='hist', *args):
+ if plt_type == 'hist':
+ self._plot_hist()
+ elif plt_type == 'hist_cum':
+ self._plot_hist_cum()
+ else:
+ 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))
+ 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'],
@@ -935,9 +952,29 @@ class PlotAvailabilityHistogram(AbstractPlotClass):
plt.ylabel('Number of samples')
plt.tight_layout()
+ def _plot_hist_cum(self, *args):
+ colors = self.get_dataset_colors()
+ 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
+
+ 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))
+ 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']
--
GitLab