From 613524c6a262869d21971eb6b4ca38376c71181b Mon Sep 17 00:00:00 2001
From: Le Roux Erwan <erwan.le-roux@irstea.fr>
Date: Sun, 19 Apr 2020 20:05:44 +0200
Subject: [PATCH] [contrasting] add numpy random state to pd.Series for sample.
improve test_two_fold_fit.py
---
extreme_fit/model/utils.py | 1 +
.../altitudes_fit/two_fold_detail_fit.py | 16 ++++----
.../coordinates/abstract_coordinates.py | 3 ++
spatio_temporal_dataset/slicer/split.py | 4 +-
.../test_contrasting/test_two_fold_fit.py | 41 +++++++++++--------
5 files changed, 40 insertions(+), 25 deletions(-)
diff --git a/extreme_fit/model/utils.py b/extreme_fit/model/utils.py
index 03e653be..c04eb802 100644
--- a/extreme_fit/model/utils.py
+++ b/extreme_fit/model/utils.py
@@ -45,6 +45,7 @@ warnings.filters = default_filters
def set_seed_for_test(seed=42):
set_seed_r(seed=seed)
+ np.random.seed(seed=seed)
random.seed(seed)
diff --git a/projects/contrasting_trends_in_snow_loads/altitudes_fit/two_fold_detail_fit.py b/projects/contrasting_trends_in_snow_loads/altitudes_fit/two_fold_detail_fit.py
index d58f1d47..57332d46 100644
--- a/projects/contrasting_trends_in_snow_loads/altitudes_fit/two_fold_detail_fit.py
+++ b/projects/contrasting_trends_in_snow_loads/altitudes_fit/two_fold_detail_fit.py
@@ -1,4 +1,4 @@
-from typing import List
+from typing import List, Tuple
import numpy as np
@@ -59,19 +59,19 @@ class TwoFoldSampleFit(object):
key = lambda model_class: self.model_class_to_model_fit[model_class].score(score)
return sorted(self.model_classes, key=key)
+ def scores(self, score):
+ return [self.model_class_to_model_fit[model_class].score(score) for model_class in self.model_classes]
+
class TwoFoldModelFit(object):
def __init__(self, model_class, two_fold_datasets, fit_method):
self.model_class = model_class
self.fit_method = fit_method
- self.estimator_fold_1, self.estimator_fold_2 = [
- fitted_linear_margin_estimator_short(model_class=self.model_class, dataset=dataset,
- fit_method=self.fit_method) for dataset in two_fold_datasets]
-
- @property
- def estimators(self) -> List[LinearMarginEstimator]:
- return [self.estimator_fold_1, self.estimator_fold_2]
+ self.estimators = [fitted_linear_margin_estimator_short(model_class=self.model_class, dataset=dataset,
+ fit_method=self.fit_method) for dataset in two_fold_datasets] # type: List[LinearMarginEstimator]
+ self.estimator_fold_1 = self.estimators[0]
+ self.estimator_fold_2 = self.estimators[1]
def score(self, score):
if score == Score.NLLH_TEST:
diff --git a/spatio_temporal_dataset/coordinates/abstract_coordinates.py b/spatio_temporal_dataset/coordinates/abstract_coordinates.py
index 9cb1f567..10b5e563 100644
--- a/spatio_temporal_dataset/coordinates/abstract_coordinates.py
+++ b/spatio_temporal_dataset/coordinates/abstract_coordinates.py
@@ -158,6 +158,9 @@ class AbstractCoordinates(object):
def coordinates_values(self, split: Split = Split.all, transformed=True) -> np.ndarray:
return self.df_coordinates(split, transformed=transformed).values
+ def coordinates_index(self, split: Split = Split.all) -> pd.Index:
+ return self.df_coordinates(split).index
+
@property
def ind_train_spatial(self) -> pd.Series:
return ind_train_from_s_split(s_split=self.s_split_spatial)
diff --git a/spatio_temporal_dataset/slicer/split.py b/spatio_temporal_dataset/slicer/split.py
index ac18f76a..a5168fad 100644
--- a/spatio_temporal_dataset/slicer/split.py
+++ b/spatio_temporal_dataset/slicer/split.py
@@ -1,4 +1,5 @@
from enum import Enum
+import numpy as np
from typing import Union
import pandas as pd
@@ -46,7 +47,8 @@ def small_s_split_from_ratio(index: pd.Index, train_split_ratio):
s = pd.Series(TEST_SPLIT_STR, index=index)
nb_points_train = int(length * train_split_ratio)
assert 0 < nb_points_train < length
- train_ind = pd.Series.sample(s, n=nb_points_train).index
+ random_state = np.random.mtrand._rand
+ train_ind = pd.Series.sample(s, n=nb_points_train, random_state=random_state).index
assert 0 < len(train_ind) < length, "number of training points:{} length:{}".format(len(train_ind), length)
s.loc[train_ind] = TRAIN_SPLIT_STR
return s
diff --git a/test/test_projects/test_contrasting/test_two_fold_fit.py b/test/test_projects/test_contrasting/test_two_fold_fit.py
index 4f0311dd..7e07a95e 100644
--- a/test/test_projects/test_contrasting/test_two_fold_fit.py
+++ b/test/test_projects/test_contrasting/test_two_fold_fit.py
@@ -10,7 +10,9 @@ from extreme_fit.model.margin_model.utils import MarginFitMethod
from extreme_fit.model.utils import set_seed_for_test
from projects.contrasting_trends_in_snow_loads.altitudes_fit.altitudes_studies import AltitudesStudies
from projects.contrasting_trends_in_snow_loads.altitudes_fit.two_fold_datasets_generator import TwoFoldDatasetsGenerator
+from projects.contrasting_trends_in_snow_loads.altitudes_fit.two_fold_detail_fit import TwoFoldModelFit
from projects.contrasting_trends_in_snow_loads.altitudes_fit.two_fold_fit import TwoFoldFit
+from projects.contrasting_trends_in_snow_loads.altitudes_fit.utils import Score
from spatio_temporal_dataset.slicer.split import Split
@@ -19,26 +21,33 @@ class TestTwoFoldFit(unittest.TestCase):
def setUp(self) -> None:
super().setUp()
set_seed_for_test()
- altitudes = [900, 1200]
- study_class = SafranSnowfall1Day
- studies = AltitudesStudies(study_class, altitudes, year_min=1959, year_max=1989)
- self.two_fold_datasets_generator = TwoFoldDatasetsGenerator(studies, nb_samples=2, massif_names=['Vercors'])
- self.model_family_name_to_model_class = {'Stationary': [ConstantMarginModel],
- 'Linear': [ConstantMarginModel, LinearLocationAllDimsMarginModel]}
-
- def load_two_fold_fit(self, fit_method):
+
+ def load_two_fold_fit(self, fit_method, year_max):
+ self.altitudes = [900, 1200]
+ self.study_class = SafranSnowfall1Day
+ studies = AltitudesStudies(self.study_class, self.altitudes, year_max=year_max)
+ self.two_fold_datasets_generator = TwoFoldDatasetsGenerator(studies, nb_samples=1, massif_names=['Vercors'])
+ self.model_family_name_to_model_class = {'Stationary': [ConstantMarginModel]}
return TwoFoldFit(two_fold_datasets_generator=self.two_fold_datasets_generator,
model_family_name_to_model_classes=self.model_family_name_to_model_class,
fit_method=fit_method)
- # def test_best_fit_spatial_extreme(self):
- # two_fold_fit = self.load_two_fold_fit(fit_method=MarginFitMethod.spatial_extremes_mle)
- # try:
- # best_model_class = two_fold_fit.massif_name_to_best_model()['Vercors']
- # except AssertionError as e:
- # self.assertTrue(False, msg=e.__str__())
- # best_model_class = None
- # self.assertEqual(best_model_class, LinearLocationAllDimsMarginModel)
+ def test_determinism_dataset_generation(self):
+ two_fold_fit = self.load_two_fold_fit(fit_method=MarginFitMethod.spatial_extremes_mle, year_max=1963)
+ massif_fit = two_fold_fit.massif_name_to_massif_fit['Vercors']
+ model_fit = massif_fit.sample_id_to_sample_fit[0].model_class_to_model_fit[
+ ConstantMarginModel] # type: TwoFoldModelFit
+ dataset_fold1 = model_fit.estimator_fold_1.dataset
+ index_train = list(dataset_fold1.coordinates.coordinates_index(split=Split.train_temporal))
+ self.assertEqual([2, 3, 8, 9], index_train)
+ self.assertEqual(110.52073192596436, np.sum(dataset_fold1.maxima_gev(split=Split.train_temporal)))
+
+ def test_determinism_fit_spatial_extreme(self):
+ two_fold_fit = self.load_two_fold_fit(fit_method=MarginFitMethod.spatial_extremes_mle, year_max=2019)
+ massif_fit = two_fold_fit.massif_name_to_massif_fit['Vercors']
+ model_fit = massif_fit.sample_id_to_sample_fit[0].model_class_to_model_fit[
+ ConstantMarginModel] # type: TwoFoldModelFit
+ self.assertEqual(461.6710428902022, model_fit.score(score=Score.NLLH_TEST))
if __name__ == '__main__':
--
GitLab