diff --git a/experiment/meteo_france_SCM_study/visualization/study_visualization/non_stationary_trends.py b/experiment/meteo_france_SCM_study/visualization/study_visualization/non_stationary_trends.py
index 822268e9f8145ae01a006595e7fcdd29c33d5408..33b0031b6f2f86f5237d00c8d8c5d35a083b4063 100644
--- a/experiment/meteo_france_SCM_study/visualization/study_visualization/non_stationary_trends.py
+++ b/experiment/meteo_france_SCM_study/visualization/study_visualization/non_stationary_trends.py
@@ -33,6 +33,9 @@ class AbstractNonStationaryTrendTest(object):
if (margin_model_class, starting_point) not in self._margin_model_class_and_starting_point_to_estimator:
margin_model = margin_model_class(coordinates=self.dataset.coordinates, starting_point=starting_point)
estimator = self._load_estimator(margin_model)
+ estimator_name = get_display_name_from_object_type(estimator)
+ margin_model_name = get_display_name_from_object_type(margin_model)
+ print('Fitting {} with margin: {} for starting_point={}'.format(estimator_name, margin_model_name, starting_point))
estimator.fit()
self._margin_model_class_and_starting_point_to_estimator[(margin_model_class, starting_point)] = estimator
return self._margin_model_class_and_starting_point_to_estimator[(margin_model_class, starting_point)]
@@ -76,11 +79,12 @@ class AbstractNonStationaryTrendTest(object):
mu1_trends = [self.get_mu1(starting_point=year) for year in years]
ax2 = ax.twinx()
color_mu1 = 'c'
+ print(mu1_trends)
ax2.plot(years, mu1_trends, color_mu1 + 'o-')
ax2.set_ylabel('mu1 parameter', color=color_mu1)
ax.set_xlabel('starting year for the linear trend of mu1')
- align_yaxis_on_zero(ax, ax2)
+ # align_yaxis_on_zero(ax, ax2)
title = self.display_name
ax.set_title(title)
ax.legend()
diff --git a/spatio_temporal_dataset/coordinates/abstract_coordinates.py b/spatio_temporal_dataset/coordinates/abstract_coordinates.py
index a51fe21862f8a473ee6a0bd5c21c5ce66ea51057..523d51310dcf1d28569eeca21c363e7ffa3550ad 100644
--- a/spatio_temporal_dataset/coordinates/abstract_coordinates.py
+++ b/spatio_temporal_dataset/coordinates/abstract_coordinates.py
@@ -47,10 +47,8 @@ class AbstractCoordinates(object):
# Sort coordinates according to a specified order
sorted_coordinates_columns = [c for c in self.COORDINATES_NAMES if c in coordinate_columns]
self.df_all_coordinates = df.loc[:, sorted_coordinates_columns].copy() # type: pd.DataFrame
- # Check the data type of the coordinate columns
- accepted_dtypes = ['int']
- assert len(self.df_all_coordinates.select_dtypes(include=self.ALL_COORDINATES_ACCEPTED_TYPES).columns) \
- == len(coordinate_columns), 'coordinates columns dtypes should belong to {}'.format(accepted_dtypes)
+ # Cast coordinates
+ self.df_all_coordinates = self.df_all_coordinates.astype(self.COORDINATE_TYPE) # type: pd.DataFrame
# Slicing attributes
self.s_split_spatial = s_split_spatial # type: pd.Series
@@ -60,6 +58,10 @@ class AbstractCoordinates(object):
# Transformation attribute
if transformation_class is None:
transformation_class = IdentityTransformation
+ # Transformation only works for float coordinates
+ accepted_dtypes = [self.COORDINATE_TYPE]
+ assert len(self.df_all_coordinates.select_dtypes(include=accepted_dtypes).columns) \
+ == len(coordinate_columns), 'coordinates columns dtypes should belong to {}'.format(accepted_dtypes)
# Transformation class is instantiated with all coordinates
self.transformation = transformation_class(self.df_all_coordinates)
assert isinstance(self.transformation, AbstractTransformation)
@@ -137,8 +139,7 @@ class AbstractCoordinates(object):
# Split
def df_coordinates(self, split: Split = Split.all) -> pd.DataFrame:
- df_all_coordinate_as_float = self.df_all_coordinates.astype(self.COORDINATE_TYPE) # type: pd.DataFrame
- df_transformed_coordinates = self.transformation.transform_df(df_all_coordinate_as_float)
+ df_transformed_coordinates = self.transformation.transform_df(self.df_all_coordinates)
return df_sliced(df=df_transformed_coordinates, split=split, slicer=self.slicer)
def coordinates_values(self, split: Split = Split.all) -> np.ndarray:
diff --git a/spatio_temporal_dataset/coordinates/spatio_temporal_coordinates/abstract_spatio_temporal_coordinates.py b/spatio_temporal_dataset/coordinates/spatio_temporal_coordinates/abstract_spatio_temporal_coordinates.py
index dc86c8c9f760af0757fc22f339558920db20ead5..26bb7e0b1421a995539045eb129981ee8e4adfdb 100644
--- a/spatio_temporal_dataset/coordinates/spatio_temporal_coordinates/abstract_spatio_temporal_coordinates.py
+++ b/spatio_temporal_dataset/coordinates/spatio_temporal_coordinates/abstract_spatio_temporal_coordinates.py
@@ -17,15 +17,17 @@ class AbstractSpatioTemporalCoordinates(AbstractCoordinates):
transformation_class: type = None,
spatial_coordinates: AbstractSpatialCoordinates = None,
temporal_coordinates: AbstractTemporalCoordinates = None):
- super().__init__(df, slicer_class, s_split_spatial, s_split_temporal, transformation_class)
+ super().__init__(df, slicer_class, s_split_spatial, s_split_temporal, None)
# Spatial coordinates'
if spatial_coordinates is None:
- self.spatial_coordinates = AbstractSpatialCoordinates.from_df(df=self.df_spatial_coordinates())
+ self.spatial_coordinates = AbstractSpatialCoordinates.from_df(df=self.df_spatial_coordinates(),
+ transformation_class=transformation_class)
else:
self.spatial_coordinates = spatial_coordinates
# Temporal coordinates
if temporal_coordinates is None:
- self.temporal_coordinates = AbstractTemporalCoordinates.from_df(df=self.df_temporal_coordinates())
+ self.temporal_coordinates = AbstractTemporalCoordinates.from_df(df=self.df_temporal_coordinates(),
+ transformation_class=transformation_class)
else:
self.temporal_coordinates = temporal_coordinates
@@ -58,28 +60,33 @@ class AbstractSpatioTemporalCoordinates(AbstractCoordinates):
spatial_coordinates=spatial_coordinates, temporal_coordinates=temporal_coordinates)
@classmethod
- def from_df(cls, df: pd.DataFrame, train_split_ratio: float = None):
+ def from_df(cls, df: pd.DataFrame, train_split_ratio: float = None, transformation_class: type = None):
assert cls.COORDINATE_T in df.columns
assert cls.COORDINATE_X in df.columns
# Assert that the time steps are in the good order with respect to the coordinates
nb_points = len(set(df[cls.COORDINATE_X]))
first_time_step_for_all_points = df.iloc[:nb_points][cls.COORDINATE_T]
assert len(set(first_time_step_for_all_points)) == 1
- return super().from_df_and_slicer(df, SpatioTemporalSlicer, train_split_ratio)
+ return super().from_df_and_slicer(df, SpatioTemporalSlicer, train_split_ratio, transformation_class)
@classmethod
- def from_df_spatial_and_coordinate_t_values(cls, df_spatial, coordinate_t_values, train_split_ratio: float = None):
+ def from_df_spatial_and_coordinate_t_values(cls, df_spatial, coordinate_t_values, train_split_ratio: float = None,
+ transformation_class: type = None):
df_time_steps = cls.get_df_from_df_spatial_and_coordinate_t_values(coordinate_t_values, df_spatial)
- return cls.from_df(df=df_time_steps, train_split_ratio=train_split_ratio)
-
+ return cls.from_df(df=df_time_steps, train_split_ratio=train_split_ratio,
+ transformation_class=transformation_class)
@classmethod
- def from_df_spatial_and_nb_steps(cls, df_spatial, nb_steps, train_split_ratio: float = None, start=0):
+ def from_df_spatial_and_nb_steps(cls, df_spatial, nb_steps, train_split_ratio: float = None, start=0,
+ transformation_class: type = None):
coordinate_t_values = [start + t for t in range(nb_steps)]
- return cls.from_df_spatial_and_coordinate_t_values(df_spatial, coordinate_t_values, train_split_ratio)
+ return cls.from_df_spatial_and_coordinate_t_values(df_spatial, coordinate_t_values, train_split_ratio,
+ transformation_class)
@classmethod
- def from_df_spatial_and_df_temporal(cls, df_spatial, df_temporal, train_split_ratio: float = None):
+ def from_df_spatial_and_df_temporal(cls, df_spatial, df_temporal, train_split_ratio: float = None,
+ transformation_class: type = None):
nb_steps = len(df_temporal)
coordinate_t_values = [df_temporal.iloc[t].values[0] for t in range(nb_steps)]
- return cls.from_df_spatial_and_coordinate_t_values(df_spatial, coordinate_t_values, train_split_ratio)
+ return cls.from_df_spatial_and_coordinate_t_values(df_spatial, coordinate_t_values, train_split_ratio,
+ transformation_class)
diff --git a/spatio_temporal_dataset/coordinates/spatio_temporal_coordinates/generated_spatio_temporal_coordinates.py b/spatio_temporal_dataset/coordinates/spatio_temporal_coordinates/generated_spatio_temporal_coordinates.py
index b29738fc6377a453a9f381c50811511822530a54..3c461629cb694c6b247652a022ac98ccb1117120 100644
--- a/spatio_temporal_dataset/coordinates/spatio_temporal_coordinates/generated_spatio_temporal_coordinates.py
+++ b/spatio_temporal_dataset/coordinates/spatio_temporal_coordinates/generated_spatio_temporal_coordinates.py
@@ -10,17 +10,28 @@ class GeneratedSpatioTemporalCoordinates(AbstractSpatioTemporalCoordinates):
SPATIAL_COORDINATES_CLASS = None
@classmethod
- def from_nb_points_and_nb_steps(cls, nb_points, nb_steps, train_split_ratio: float = None):
+ def from_nb_points_and_nb_steps(cls, nb_points, nb_steps, train_split_ratio: float = None,
+ transformation_class: type = None):
assert isinstance(nb_steps, int) and nb_steps >= 1
- assert cls.SPATIAL_COORDINATES_CLASS is not None
- assert hasattr(cls.SPATIAL_COORDINATES_CLASS, 'df_spatial')
- df_spatial = cls.SPATIAL_COORDINATES_CLASS.df_spatial(nb_points=nb_points)
- return cls.from_df_spatial_and_nb_steps(df_spatial, nb_steps, train_split_ratio)
+ assert hasattr(cls.spatial_coordinate_class(), 'df_spatial')
+ df_spatial = cls.spatial_coordinate_class().df_spatial(nb_points=nb_points)
+ return cls.from_df_spatial_and_nb_steps(df_spatial, nb_steps, train_split_ratio,
+ transformation_class=transformation_class)
+
+ @classmethod
+ def spatial_coordinate_class(cls):
+ raise NotImplementedError
class UniformSpatioTemporalCoordinates(GeneratedSpatioTemporalCoordinates):
- SPATIAL_COORDINATES_CLASS = UniformSpatialCoordinates
+
+ @classmethod
+ def spatial_coordinate_class(cls):
+ return UniformSpatialCoordinates
class LinSpaceSpatial2DSpatioTemporalCoordinates(GeneratedSpatioTemporalCoordinates):
- SPATIAL_COORDINATES_CLASS = LinSpaceSpatial2DCoordinates
+
+ @classmethod
+ def spatial_coordinate_class(cls):
+ return LinSpaceSpatial2DCoordinates
diff --git a/spatio_temporal_dataset/coordinates/transformed_coordinates/transformation/abstract_transformation.py b/spatio_temporal_dataset/coordinates/transformed_coordinates/transformation/abstract_transformation.py
index 4f6bdc9ca930006495dc7a44d4ddcddae2573853..e4092e0fc3c17d11cccdd34586bc2dbc4af4958c 100644
--- a/spatio_temporal_dataset/coordinates/transformed_coordinates/transformation/abstract_transformation.py
+++ b/spatio_temporal_dataset/coordinates/transformed_coordinates/transformation/abstract_transformation.py
@@ -5,7 +5,7 @@ import numpy as np
class AbstractTransformation(object):
def __init__(self, df_coordinates):
- self.df_coordinates = df_coordinates
+ self.df_coordinates = df_coordinates.copy()
@property
def nb_dimensions(self):
@@ -19,6 +19,7 @@ class AbstractTransformation(object):
return pd.Series(self.transform_array(s_coord.values), index=s_coord.index)
def transform_df(self, df_coord: pd.DataFrame) -> pd.DataFrame:
+ df_coord = df_coord.copy()
data = [self.transform_serie(r) for _, r in df_coord.iterrows()]
return pd.DataFrame(data, index=df_coord.index, columns=df_coord.columns)
diff --git a/test/test_spatio_temporal_dataset/test_transformation.py b/test/test_spatio_temporal_dataset/test_transformation.py
index 5c8cdedaa4023763795eb42af9a8caf3065a8016..c6f2342ce1985786bdda5adaafb6d9033b9f6a88 100644
--- a/test/test_spatio_temporal_dataset/test_transformation.py
+++ b/test/test_spatio_temporal_dataset/test_transformation.py
@@ -2,6 +2,8 @@ import unittest
import numpy as np
+from spatio_temporal_dataset.coordinates.spatio_temporal_coordinates.generated_spatio_temporal_coordinates import \
+ GeneratedSpatioTemporalCoordinates, UniformSpatioTemporalCoordinates
from spatio_temporal_dataset.coordinates.temporal_coordinates.generated_temporal_coordinates import \
ConsecutiveTemporalCoordinates
from spatio_temporal_dataset.coordinates.transformed_coordinates.transformation.uniform_normalization import \
@@ -25,6 +27,22 @@ class TestTransformation(unittest.TestCase):
self.assertTrue(equals.all(),
msg="expected: {}, res:{}".format(expected_coordinates, normalized_coordinates))
+ def test_spatio_temporal_normalization(self):
+
+ transformation_class_to_expected = {BetweenZeroAndOneNormalization: [0.0, 1.0],
+ BetweenMinusOneAndOneNormalization: [-1.0, 1.0]}
+
+ for transformation_class, expected in transformation_class_to_expected.items():
+ coordinates = UniformSpatioTemporalCoordinates.from_nb_points_and_nb_steps(nb_points=2, nb_steps=50,
+ transformation_class=transformation_class)
+ temporal_coordinates = coordinates.temporal_coordinates
+ normalized_coordinates = temporal_coordinates.df_coordinates().iloc[:, 0].values
+ normalized_coordinates = np.array([normalized_coordinates[0], normalized_coordinates[-1]])
+ expected_coordinates = np.array(expected)
+ equals = normalized_coordinates == expected_coordinates
+ self.assertTrue(equals.all(),
+ msg="expected: {}, res:{}".format(expected_coordinates, normalized_coordinates))
+
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_utils.py b/test/test_utils.py
index 170988f3da51be4b46620aac92c09580a2e89b2c..072bd796382121dc76042e95bdb38bbb19e62a9f 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -89,9 +89,10 @@ def load_test_temporal_coordinates(nb_steps, train_split_ratio=None):
TEST_TEMPORAL_COORDINATES]
-def load_test_spatiotemporal_coordinates(nb_points, nb_steps, train_split_ratio=None):
+def load_test_spatiotemporal_coordinates(nb_points, nb_steps, train_split_ratio=None, transformation_class: type = None):
return [coordinate_class.from_nb_points_and_nb_steps(nb_points=nb_points, nb_steps=nb_steps,
- train_split_ratio=train_split_ratio)
+ train_split_ratio=train_split_ratio,
+ transformation_class=transformation_class)
for coordinate_class in TEST_SPATIO_TEMPORAL_COORDINATES]