diff --git a/extreme_fit/estimator/margin_estimator/abstract_margin_estimator.py b/extreme_fit/estimator/margin_estimator/abstract_margin_estimator.py
index 00285f89396d7c315c86ca28a5fed5b83a238c9f..8286e8d56d86ab76741ea3fa12ca0ba5e07db0dd 100644
--- a/extreme_fit/estimator/margin_estimator/abstract_margin_estimator.py
+++ b/extreme_fit/estimator/margin_estimator/abstract_margin_estimator.py
@@ -35,7 +35,8 @@ class LinearMarginEstimator(AbstractMarginEstimator):
@property
def coordinate_temp(self):
return self.dataset.coordinates.df_temporal_coordinates_for_fit(split=self.train_split,
- starting_point=self.margin_model.starting_point)
+ starting_point=self.margin_model.starting_point,
+ drop_duplicates=self.margin_model.drop_duplicates)
@property
def maxima_gev_train(self):
diff --git a/extreme_fit/function/margin_function/linear_margin_function.py b/extreme_fit/function/margin_function/linear_margin_function.py
index 3cdc1f8423b6dfdd932ee46ac481a477af1c9c13..7deb1ab33d94260529b00c40a6c69dfc987b0c33 100644
--- a/extreme_fit/function/margin_function/linear_margin_function.py
+++ b/extreme_fit/function/margin_function/linear_margin_function.py
@@ -64,7 +64,7 @@ class LinearMarginFunction(ParametricMarginFunction):
@property
def form_dict(self) -> Dict[str, str]:
form_dict = {}
- for gev_param_name in GevParams.PARAM_NAMES:
+ for gev_param_name in self.params_class.PARAM_NAMES:
linear_dims = self.gev_param_name_to_dims.get(gev_param_name, [])
# Load spatial form_dict (only if we have some spatial coordinates)
if self.coordinates.has_spatial_coordinates:
diff --git a/extreme_fit/model/margin_model/linear_margin_model/abstract_temporal_linear_margin_model.py b/extreme_fit/model/margin_model/linear_margin_model/abstract_temporal_linear_margin_model.py
index b441211cfde37b2d45d5b14332126db93ee76221..eb8ba9cf1786a152e928a19c3a37c6bc88bc2ca1 100644
--- a/extreme_fit/model/margin_model/linear_margin_model/abstract_temporal_linear_margin_model.py
+++ b/extreme_fit/model/margin_model/linear_margin_model/abstract_temporal_linear_margin_model.py
@@ -44,7 +44,8 @@ class AbstractTemporalLinearMarginModel(LinearMarginModel):
def fitmargin_from_maxima_gev(self, data: np.ndarray, df_coordinates_spat: pd.DataFrame,
df_coordinates_temp: pd.DataFrame) -> AbstractResultFromModelFit:
data = data[0]
- assert len(data) == len(df_coordinates_temp.values)
+ assert len(data) == len(df_coordinates_temp.values), 'len(data)={} != len(temp)={}'.format(len(data),
+ len(df_coordinates_temp.values))
x = ro.FloatVector(data)
if self.params_class is GevParams:
if self.fit_method == TemporalMarginFitMethod.is_mev_gev_fit:
diff --git a/extreme_fit/model/margin_model/linear_margin_model/temporal_linear_margin_exp_models.py b/extreme_fit/model/margin_model/linear_margin_model/temporal_linear_margin_exp_models.py
index b10c027734346aade96ffed3b3853e0112a8ec31..677f1865a6df36475c5889c36bec3b62376c9db6 100644
--- a/extreme_fit/model/margin_model/linear_margin_model/temporal_linear_margin_exp_models.py
+++ b/extreme_fit/model/margin_model/linear_margin_model/temporal_linear_margin_exp_models.py
@@ -9,6 +9,7 @@ class NonStationaryRateTemporalModel(AbstractTemporalLinearMarginModel, Abstract
def __init__(self, *arg, **kwargs):
kwargs['params_class'] = ExpParams
super().__init__(*arg, **kwargs)
+ self.drop_duplicates = False
def load_margin_functions(self, gev_param_name_to_dims=None):
super().load_margin_functions({ExpParams.RATE: [self.coordinates.idx_temporal_coordinates]})
diff --git a/extreme_fit/model/margin_model/parametric_margin_model.py b/extreme_fit/model/margin_model/parametric_margin_model.py
index 724366c45e5cad1fbdf21abda1256b76be33d234..49f1995c99ad612194b1093543ab796c567f20a0 100644
--- a/extreme_fit/model/margin_model/parametric_margin_model.py
+++ b/extreme_fit/model/margin_model/parametric_margin_model.py
@@ -23,6 +23,7 @@ class ParametricMarginModel(AbstractMarginModel, ABC):
self.starting_point = starting_point
self.margin_function_sample = None # type: ParametricMarginFunction
self.margin_function_start_fit = None # type: ParametricMarginFunction
+ self.drop_duplicates = True
super().__init__(coordinates, use_start_value, params_start_fit, params_sample, params_class)
def fitmargin_from_maxima_gev(self, data: np.ndarray, df_coordinates_spat: pd.DataFrame,
diff --git a/projects/quantile_regression_vs_evt/main_non_stationary_quantile_regression.py b/projects/quantile_regression_vs_evt/main_non_stationary_quantile_regression.py
index ca70617ace8d473df81b8a769a259cf3bce361f7..c9a812969ce9f7cec8d1db5d36210f16e84cd8d1 100644
--- a/projects/quantile_regression_vs_evt/main_non_stationary_quantile_regression.py
+++ b/projects/quantile_regression_vs_evt/main_non_stationary_quantile_regression.py
@@ -1,3 +1,4 @@
+from extreme_fit.model.daily_data_model import TemporalCoordinatesQuantileRegressionModelOnDailyData
from extreme_fit.model.margin_model.linear_margin_model.temporal_linear_margin_models import \
NonStationaryLocationTemporalModel, NonStationaryLocationGumbelModel
from extreme_fit.model.quantile_model.quantile_regression_model import TemporalCoordinatesQuantileRegressionModel
@@ -8,16 +9,19 @@ from projects.quantile_regression_vs_evt.annual_maxima_simulation.gev_simulation
from spatio_temporal_dataset.coordinates.transformed_coordinates.transformation.abstract_transformation import \
CenteredScaledNormalization, IdentityTransformation
-nb_time_series = 20
+nb_time_series = 10
quantile = 0.98
time_series_lengths = [50, 100, 200]
transformation_class = [IdentityTransformation, CenteredScaledNormalization][1]
-model_classes = [NonStationaryLocationTemporalModel,
- TemporalCoordinatesQuantileRegressionModel,
- NonStationaryLocationGumbelModel]
+model_classes = [
+ NonStationaryLocationTemporalModel,
+ TemporalCoordinatesQuantileRegressionModel,
+ NonStationaryLocationGumbelModel,
+ TemporalCoordinatesQuantileRegressionModelOnDailyData
+]
simulation_class = [NonStationaryLocationGumbelSimulation,
NonStationaryLocationGevSimulation,
- NonStationaryExpSimulation][-2]
+ NonStationaryExpSimulation][-1]
simulation = simulation_class(nb_time_series=nb_time_series,
quantile=quantile,
diff --git a/spatio_temporal_dataset/coordinates/abstract_coordinates.py b/spatio_temporal_dataset/coordinates/abstract_coordinates.py
index f98974e9345b912e109c8cb1b1a0f2c101177960..76a211f1d2055e7964d72cde18c8894eb18b03e4 100644
--- a/spatio_temporal_dataset/coordinates/abstract_coordinates.py
+++ b/spatio_temporal_dataset/coordinates/abstract_coordinates.py
@@ -235,18 +235,23 @@ class AbstractCoordinates(object):
def has_temporal_coordinates(self) -> bool:
return self.nb_temporal_coordinates > 0
- def df_temporal_coordinates(self, split: Split = Split.all, transformed=True) -> pd.DataFrame:
+ def df_temporal_coordinates(self, split: Split = Split.all, transformed=True,
+ drop_duplicates=True) -> pd.DataFrame:
if self.nb_temporal_coordinates == 0:
return pd.DataFrame()
else:
- return self.df_coordinates(split, transformed=transformed).loc[:, self.temporal_coordinates_names] \
- .drop_duplicates()
+ df = self.df_coordinates(split, transformed=transformed).loc[:, self.temporal_coordinates_names]
+ if drop_duplicates:
+ return df.drop_duplicates()
+ else:
+ return df
def df_temporal_coordinates_for_fit(self, split=Split.all, starting_point=None,
- temporal_covariate_for_fit: Union[None, type] = None) -> pd.DataFrame:
+ temporal_covariate_for_fit: Union[None, type] = None,
+ drop_duplicates=True) -> pd.DataFrame:
# Load time covariate
if starting_point is None:
- df = self.df_temporal_coordinates(split=split, transformed=True)
+ df = self.df_temporal_coordinates(split=split, transformed=True, drop_duplicates=drop_duplicates)
else:
# Load the un transformed coordinates
df_temporal_coordinates = self.df_temporal_coordinates(split=split, transformed=False)
diff --git a/spatio_temporal_dataset/spatio_temporal_observations/daily_observations.py b/spatio_temporal_dataset/spatio_temporal_observations/daily_observations.py
index 00ca0ba93d0f15b2713f6ec19cbef1785b100c5e..e89b3bad95654cabfc6a0a5fc06f486b5c7c3bb4 100644
--- a/spatio_temporal_dataset/spatio_temporal_observations/daily_observations.py
+++ b/spatio_temporal_dataset/spatio_temporal_observations/daily_observations.py
@@ -2,15 +2,22 @@ import pandas as pd
from extreme_fit.model.margin_model.abstract_margin_model import AbstractMarginModel
from spatio_temporal_dataset.coordinates.abstract_coordinates import AbstractCoordinates
+from spatio_temporal_dataset.coordinates.temporal_coordinates.abstract_temporal_coordinates import \
+ AbstractTemporalCoordinates
from spatio_temporal_dataset.spatio_temporal_observations.abstract_spatio_temporal_observations import \
AbstractSpatioTemporalObservations
class DailyObservations(AbstractSpatioTemporalObservations):
- def transform_to_standard_shape(self, coordinates: AbstractCoordinates):
- coordinates.df_all_coordinates = pd.concat([coordinates.df_all_coordinates for _ in range(self.nb_obs)])
- df = pd.DataFrame(pd.concat([self.df_maxima_gev[c] for c in self.columns]), index=coordinates.index)
+ def transform_to_standard_shape(self, coordinates: AbstractTemporalCoordinates):
+ assert isinstance(coordinates, AbstractTemporalCoordinates)
+ df_coordinates = pd.concat([coordinates.df_all_coordinates for _ in range(self.nb_obs)])
+ df_coordinates.index = pd.Index(range(self.nb_obs * coordinates.nb_steps))
+ coordinates = AbstractTemporalCoordinates.from_df(df_coordinates, train_split_ratio=None,
+ transformation_class=coordinates.transformation_class)
+ df = pd.DataFrame(pd.concat([self.df_maxima_gev[c] for c in self.columns]))
+ df.index = coordinates.index
observation = AbstractSpatioTemporalObservations(df_maxima_gev=df)
return observation, coordinates
diff --git a/test/test_projects/test_quantile_regression/test_annual_maxima_simulations.py b/test/test_projects/test_quantile_regression/test_annual_maxima_simulations.py
index 377164f8c9a0717bd206df003add5f4f583970f2..1998818dd36d432158486e7eb3f50818e24f5140 100644
--- a/test/test_projects/test_quantile_regression/test_annual_maxima_simulations.py
+++ b/test/test_projects/test_quantile_regression/test_annual_maxima_simulations.py
@@ -1,6 +1,7 @@
import unittest
-from extreme_fit.model.daily_data_model import ConstantQuantileRegressionModelOnDailyData
+from extreme_fit.model.daily_data_model import ConstantQuantileRegressionModelOnDailyData, \
+ TemporalCoordinatesQuantileRegressionModelOnDailyData
from extreme_fit.model.margin_model.linear_margin_model.temporal_linear_margin_exp_models import \
NonStationaryRateTemporalModel
from extreme_fit.model.margin_model.linear_margin_model.temporal_linear_margin_models import StationaryTemporalModel, \
@@ -42,10 +43,29 @@ class TestExpSimulations(unittest.TestCase):
TemporalCoordinatesQuantileRegressionModel])
simulation.plot_error_for_last_year_quantile(self.DISPLAY)
- # Fit is way too long.... Probability the regression quantile estimator does not scale well at all...
- # def test_stationary_run_daily_data_model(self):
+
+class TestExpSimulationsDailyDataModels(unittest.TestCase):
+ DISPLAY = False
+
+ def test_stationary_run_daily_data_quantile_regression_model(self):
+ simulation = StationaryExpSimulation(nb_time_series=1, quantile=0.5, time_series_lengths=[50, 60],
+ model_classes=[ConstantQuantileRegressionModelOnDailyData])
+ simulation.plot_error_for_last_year_quantile(self.DISPLAY)
+
+ def test_non_stationary_run_daily_data_quantile_regression_model(self):
+ simulation = NonStationaryExpSimulation(nb_time_series=1, quantile=0.5, time_series_lengths=[50, 60],
+ model_classes=[TemporalCoordinatesQuantileRegressionModelOnDailyData])
+ first_estimator = simulation.model_class_to_time_series_length_to_estimators[
+ TemporalCoordinatesQuantileRegressionModelOnDailyData][50][0]
+ self.assertEqual(len(first_estimator.dataset.df_dataset), 50 * 365)
+ simulation.plot_error_for_last_year_quantile(self.DISPLAY)
+
+ # WARNING: It does not work yet, read fevd manual to understand how does he expect the parameters
+ # probably the formula to provide should be w.r.t to the scale parameter
+ # & there seems to be a need to be a need to provide a threshold parameter...
+ # def test_stationary_run_daily_data_exponential_model(self):
# simulation = StationaryExpSimulation(nb_time_series=1, quantile=0.5, time_series_lengths=[1, 2],
- # model_classes=[ConstantQuantileRegressionModelOnDailyData])
+ # model_classes=[NonStationaryRateTemporalModel])
# simulation.plot_error_for_last_year_quantile(self.DISPLAY)