diff --git a/mlair/configuration/defaults.py b/mlair/configuration/defaults.py
index 7b7584ad5ac5499f63f4f787f2215830a34ab6bb..fc4f7f0910c086bb5bb7f7802e5332404f7b5359 100644
--- a/mlair/configuration/defaults.py
+++ b/mlair/configuration/defaults.py
@@ -48,7 +48,7 @@ DEFAULT_CREATE_NEW_BOOTSTRAPS = False
DEFAULT_NUMBER_OF_BOOTSTRAPS = 20
DEFAULT_PLOT_LIST = ["PlotMonthlySummary", "PlotStationMap", "PlotClimatologicalSkillScore", "PlotTimeSeries",
"PlotCompetitiveSkillScore", "PlotBootstrapSkillScore", "PlotConditionalQuantiles",
- "PlotAvailability", "PlotAvailabilityHistogram", "PlotDataHistogram"]
+ "PlotAvailability", "PlotAvailabilityHistogram", "PlotDataHistogram", "PlotOversampling"]
DEFAULT_SAMPLING = "daily"
DEFAULT_DATA_ORIGIN = {"cloudcover": "REA", "humidity": "REA", "pblheight": "REA", "press": "REA", "relhum": "REA",
"temp": "REA", "totprecip": "REA", "u": "REA", "v": "REA", "no": "", "no2": "", "o3": "",
diff --git a/mlair/model_modules/model_class.py b/mlair/model_modules/model_class.py
index 9a0e97dbd1f3a3a52f5717c88d09702e5d0d7928..ec7f217902d7e29b1092ecd1ef51b3fc30602f62 100644
--- a/mlair/model_modules/model_class.py
+++ b/mlair/model_modules/model_class.py
@@ -377,7 +377,7 @@ class IntelliO3_ts_architecture(AbstractModelClass):
# apply to model
self.set_model()
self.set_compile_options()
- self.set_custom_objects(loss=self.compile_options["loss"],
+ self.set_custom_objects(loss=self.compile_options["loss"][0],
SymmetricPadding2D=SymmetricPadding2D,
LearningRateDecay=LearningRateDecay)
@@ -407,14 +407,14 @@ class IntelliO3_ts_architecture(AbstractModelClass):
pool_settings_dict1 = {'pool_kernel': (3, 1), 'tower_filter': 16, 'activation': activation}
conv_settings_dict2 = {
- 'tower_1': {'reduction_filter': 64, 'tower_filter': 32 * 2, 'tower_kernel': (3, 1),
+ 'tower_1': {'reduction_filter': 64, 'tower_filter': 32 * 2 * 2, 'tower_kernel': (3, 1),
'activation': activation},
- 'tower_2': {'reduction_filter': 64, 'tower_filter': 32 * 2, 'tower_kernel': (5, 1),
+ 'tower_2': {'reduction_filter': 64, 'tower_filter': 32 * 2 * 2, 'tower_kernel': (5, 1),
'activation': activation},
- 'tower_3': {'reduction_filter': 64, 'tower_filter': 32 * 2, 'tower_kernel': (1, 1),
+ 'tower_3': {'reduction_filter': 64, 'tower_filter': 32 * 2 * 2, 'tower_kernel': (1, 1),
'activation': activation}
}
- pool_settings_dict2 = {'pool_kernel': (3, 1), 'tower_filter': 32, 'activation': activation}
+ pool_settings_dict2 = {'pool_kernel': (3, 1), 'tower_filter': 32*2, 'activation': activation}
##########################################
inception_model = InceptionModelBase()
diff --git a/mlair/plotting/data_insight_plotting.py b/mlair/plotting/data_insight_plotting.py
index 8a5630743b4ddc59feb7e989064d13f879ae0199..3440321a8708ee905c5c991c4c8c5a1870719e63 100644
--- a/mlair/plotting/data_insight_plotting.py
+++ b/mlair/plotting/data_insight_plotting.py
@@ -19,6 +19,76 @@ from mlair.data_handler import DataCollection
from mlair.helpers import TimeTrackingWrapper, to_list
from mlair.plotting.abstract_plot_class import AbstractPlotClass
+@TimeTrackingWrapper
+class PlotOversamplingHistogram(AbstractPlotClass):
+
+ def __init__(self, Y, Y_extreme, bin_edges, plot_folder: str = ".",
+ plot_name="oversampling_histogram"):
+
+ super().__init__(plot_folder, plot_name)
+ self._plot(Y, Y_extreme, bin_edges)
+ self._save()
+
+ def _plot(self, Y, Y_extreme, bin_edges):
+ fig, ax = plt.subplots(1, 1)
+ Y.plot.hist(bins=bin_edges, histtype="step", label="Before", ax=ax)[0]
+ Y_extreme.plot.hist(bins=bin_edges, histtype="step", label="After", ax=ax)[0]
+ ax.set_title(f"Histogram before-after oversampling")
+ ax.legend()
+
+
+@TimeTrackingWrapper
+class PlotOversamplingDensityHistogram(AbstractPlotClass):
+
+ def __init__(self, Y, Y_extreme, bin_edges, plot_folder: str = ".",
+ plot_name="oversampling_density_histogram"):
+ super().__init__(plot_folder, plot_name)
+ self._plot(Y, Y_extreme, bin_edges)
+ self._save()
+
+ def _plot(self, Y, Y_extreme, bin_edges):
+ fig, ax = plt.subplots(1, 1)
+ Y.plot.hist(bins=bin_edges, density=True, histtype="step", label="Before", ax=ax)[0]
+ Y_extreme.plot.hist(bins=bin_edges, density=True, histtype="step", label="After", ax=ax)[0]
+ ax.set_title(f"Density Histogram before-after oversampling")
+ ax.legend()
+
+
+@TimeTrackingWrapper
+class PlotOversamplingRates(AbstractPlotClass):
+
+ def __init__(self, Y, Y_extreme, bin_edges, oversampling_rates, Y_hist, Y_extreme_hist, plot_folder: str = ".",
+ plot_name="oversampling_rates"):
+ super().__init__(plot_folder, plot_name)
+ self._plot(Y, Y_extreme, bin_edges, oversampling_rates, Y_hist, Y_extreme_hist)
+ self._save()
+
+ def _plot(self, Y, Y_extreme, bin_edges, oversampling_rates, Y_hist, Y_extreme_hist):
+ fig, ax = plt.subplots(1, 1)
+ real_oversampling = Y_extreme_hist[0] / Y_hist[0]
+ ax.plot(range(len(real_oversampling)), oversampling_rates, label="Desired oversampling_rates")
+ ax.plot(range(len(real_oversampling)), real_oversampling, label="Actual Oversampling Rates")
+ ax.set_title(f"Oversampling rates")
+ ax.legend()
+
+
+@TimeTrackingWrapper
+class PlotOversamplingRatesDeviation(AbstractPlotClass):
+
+ def __init__(self, Y, Y_extreme, bin_edges, oversampling_rates, Y_hist, Y_extreme_hist, plot_folder: str = ".",
+ plot_name="oversampling_rates_deviation"):
+ super().__init__(plot_folder, plot_name)
+ self._plot(Y, Y_extreme, bin_edges, oversampling_rates, Y_hist, Y_extreme_hist)
+ self._save()
+
+ def _plot(self, Y, Y_extreme, bin_edges, oversampling_rates, Y_hist, Y_extreme_hist):
+ fig, ax = plt.subplots(1, 1)
+ real_oversampling = Y_extreme_hist[0] / Y_hist[0]
+ ax.plot(range(len(real_oversampling)), real_oversampling / oversampling_rates,
+ label="Actual/Desired Rate")
+ ax.set_title(f"Deviation from desired oversampling rates")
+ ax.legend()
+
@TimeTrackingWrapper
class PlotStationMap(AbstractPlotClass): # pragma: no cover
diff --git a/mlair/run_modules/post_processing.py b/mlair/run_modules/post_processing.py
index 89a6f205d03892c57c55a66399a43c9ba2987b42..742acf2f772abded667bff3a54b17064f5901c4b 100644
--- a/mlair/run_modules/post_processing.py
+++ b/mlair/run_modules/post_processing.py
@@ -22,7 +22,8 @@ from mlair.model_modules import AbstractModelClass
from mlair.plotting.postprocessing_plotting import PlotMonthlySummary, PlotClimatologicalSkillScore, \
PlotCompetitiveSkillScore, PlotTimeSeries, PlotBootstrapSkillScore, PlotConditionalQuantiles, PlotSeparationOfScales
from mlair.plotting.data_insight_plotting import PlotStationMap, PlotAvailability, PlotAvailabilityHistogram, \
- PlotPeriodogram, PlotDataHistogram
+ PlotPeriodogram, PlotDataHistogram, PlotOversamplingHistogram, PlotOversamplingDensityHistogram, \
+ PlotOversamplingRates, PlotOversamplingRatesDeviation
from mlair.run_modules.run_environment import RunEnvironment
@@ -305,6 +306,24 @@ class PostProcessing(RunEnvironment):
target_dim = self.data_store.get("target_dim")
iter_dim = self.data_store.get("iter_dim")
+ try:
+ if (self.data_store.get('oversampling_method')=='bin_oversampling') and (
+ "PlotOversampling" in plot_list):
+ bin_edges = self.data_store.get('oversampling_bin_edges')
+ oversampling_rates = self.data_store.get('oversampling_rates_capped','train')
+ Y = self.data_store.get('Oversampling_Y')
+ Y_extreme = self.data_store.get('Oversampling_Y_extreme')
+ Y_hist = Y.plot.hist(bins=bin_edges, histtype="step")
+ Y_extreme_hist = Y_extreme.plot.hist(bins=bin_edges, histtype="step")
+ PlotOversamplingHistogram(Y, Y_extreme, bin_edges, plot_folder=self.plot_path)
+ PlotOversamplingDensityHistogram(Y, Y_extreme, bin_edges, plot_folder=self.plot_path)
+ PlotOversamplingRates(Y, Y_extreme, bin_edges, oversampling_rates, Y_hist, Y_extreme_hist,
+ plot_folder=self.plot_path)
+ PlotOversamplingRatesDeviation(Y, Y_extreme, bin_edges, oversampling_rates, Y_hist,
+ Y_extreme_hist, plot_folder=self.plot_path)
+ except Exception as e:
+ logging.error(f"Could not create plot OversamplingPlots due to the following error: {e}")
+
try:
if ("filter" in self.test_data[0].get_X(as_numpy=False)[0].coords) and (
"PlotSeparationOfScales" in plot_list):
diff --git a/mlair/run_modules/pre_processing.py b/mlair/run_modules/pre_processing.py
index 215c0bb80c05fd9ac267418961c2ca96e025b3e2..69f14bedc0a31afa4965778e33e7c884db77179f 100644
--- a/mlair/run_modules/pre_processing.py
+++ b/mlair/run_modules/pre_processing.py
@@ -113,7 +113,8 @@ class PreProcessing(RunEnvironment):
else:
Y = xr.concat([Y, station._Y], dim="Stations")
Y_extreme = xr.concat([Y_extreme, station._Y_extreme], dim="Stations")
-
+ self.data_store.set('Oversampling_Y', Y)
+ self.data_store.set('Oversampling_Y_extreme', Y_extreme)
'''
if not on HPC:
fig, ax = plt.subplots(nrows=2, ncols=2)
diff --git a/run.py b/run.py
index f2bb336e8a886a3c0c4d60736c77b5ebc27cad67..05b43ade453a4eb36952e18ad1c7ebab788dc37d 100644
--- a/run.py
+++ b/run.py
@@ -25,6 +25,7 @@ def main(parser_args):
# stations=["DEBW087","DEBW013", "DEBW107", "DEBW076"],
stations=["DEBW013", "DEBW087", "DEBW107", "DEBW076"],
train_model=False, create_new_model=True, network="UBA",
+ oversampling_method="bin_oversampling", oversampling_bins=10, oversampling_rates_cap=100, window_lead_time=2,
evaluate_bootstraps=False, # plot_list=["PlotCompetitiveSkillScore"],
competitors=["test_model", "test_model2"],
competitor_path=os.path.join(os.getcwd(), "data", "comp_test"),