From 10bc2a5ba52394c3d1774ca7e8032ed1b9c69857 Mon Sep 17 00:00:00 2001
From: Le Roux Erwan <erwan.le-roux@irstea.fr>
Date: Thu, 21 Mar 2019 17:10:12 +0100
Subject: [PATCH] [COORDINATES] add spatial_index attributes. add test
accordingly.
---
.../coordinates/abstract_coordinates.py | 3 +++
.../abstract_spatio_temporal_coordinates.py | 13 ++++++-----
.../generated_spatio_temporal_coordinates.py | 3 +--
.../test_coordinates.py | 22 +++++++++++++++++--
4 files changed, 32 insertions(+), 9 deletions(-)
diff --git a/spatio_temporal_dataset/coordinates/abstract_coordinates.py b/spatio_temporal_dataset/coordinates/abstract_coordinates.py
index 9c430450..4705d7d0 100644
--- a/spatio_temporal_dataset/coordinates/abstract_coordinates.py
+++ b/spatio_temporal_dataset/coordinates/abstract_coordinates.py
@@ -168,6 +168,9 @@ class AbstractCoordinates(object):
else:
return self.df_coordinates(split).loc[:, self.coordinates_spatial_names].drop_duplicates()
+ def spatial_index(self, split: Split = Split.all) -> pd.Index:
+ return self.df_spatial_coordinates(split).index
+
# Temporal attributes
@property
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 47883682..c0ff737e 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
@@ -17,12 +17,15 @@ class AbstractSpatioTemporalCoordinates(AbstractCoordinates):
return super().from_df_and_slicer(df, SpatioTemporalSlicer, train_split_ratio)
@classmethod
- def generate_df_spatio_temporal(cls, df_spatial, nb_steps):
- # df_temporal = ConsecutiveTemporalCoordinates.df_temporal(nb_temporal_steps=nb_temporal_steps)
+ def from_df_spatial_and_nb_steps(cls, df_spatial, nb_steps, train_split_ratio: float = None, start=0):
df_time_steps = []
+ index_type = type(df_spatial.index[0])
for t in range(nb_steps):
df_time_step = df_spatial.copy()
- df_time_step[cls.COORDINATE_T] = t
+ df_time_step[cls.COORDINATE_T] = start + t
+ index_suffix = index_type(t + len(df_spatial))
+ time_step_index = [i + index_suffix for i in df_spatial.index] if t > 0 else df_spatial.index
+ df_time_step.index = time_step_index
df_time_steps.append(df_time_step)
- df_time_steps = pd.concat(df_time_steps, ignore_index=True)
- return df_time_steps
\ No newline at end of file
+ df_time_steps = pd.concat(df_time_steps)
+ return cls.from_df(df=df_time_steps, train_split_ratio=train_split_ratio)
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 9d6ba771..b29738fc 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
@@ -15,8 +15,7 @@ class GeneratedSpatioTemporalCoordinates(AbstractSpatioTemporalCoordinates):
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)
- df_time_steps = cls.generate_df_spatio_temporal(df_spatial, nb_steps)
- return cls.from_df(df=df_time_steps, train_split_ratio=train_split_ratio)
+ return cls.from_df_spatial_and_nb_steps(df_spatial, nb_steps, train_split_ratio)
class UniformSpatioTemporalCoordinates(GeneratedSpatioTemporalCoordinates):
diff --git a/test/test_spatio_temporal_dataset/test_coordinates.py b/test/test_spatio_temporal_dataset/test_coordinates.py
index baf51fc9..0fbe5007 100644
--- a/test/test_spatio_temporal_dataset/test_coordinates.py
+++ b/test/test_spatio_temporal_dataset/test_coordinates.py
@@ -4,8 +4,9 @@ from collections import Counter, OrderedDict
from spatio_temporal_dataset.coordinates.abstract_coordinates import AbstractCoordinates
from spatio_temporal_dataset.coordinates.spatio_temporal_coordinates.generated_spatio_temporal_coordinates import \
- UniformSpatioTemporalCoordinates
-from spatio_temporal_dataset.coordinates.spatial_coordinates.coordinates_1D import UniformSpatialCoordinates
+ UniformSpatioTemporalCoordinates, GeneratedSpatioTemporalCoordinates
+from spatio_temporal_dataset.coordinates.spatial_coordinates.coordinates_1D import UniformSpatialCoordinates, \
+ LinSpaceSpatialCoordinates
from spatio_temporal_dataset.coordinates.spatial_coordinates.alps_station_2D_coordinates import \
AlpsStation2DCoordinatesBetweenZeroAndOne
from spatio_temporal_dataset.coordinates.spatial_coordinates.alps_station_3D_coordinates import \
@@ -52,6 +53,23 @@ class SpatioTemporalCoordinates(unittest.TestCase):
good_count = c == Counter([2, 2, 2, 2]) or c == Counter([0, 0, 4, 4])
self.assertTrue(good_count)
+ def test_unique_spatio_temporal_index_and_matching_spatial_index(self):
+ spatial_coordinates = LinSpaceSpatialCoordinates.from_nb_points(self.nb_points)
+ spatial_indexes = [[10, 11, 12, 13], ['a', 'b', 'c', 'd']]
+ for spatial_index in spatial_indexes:
+ spatial_coordinates.df_all_coordinates.index = spatial_index
+ df_spatial = spatial_coordinates.df_spatial_coordinates()
+ coordinates = GeneratedSpatioTemporalCoordinates.from_df_spatial_and_nb_steps(df_spatial=df_spatial,
+ nb_steps=self.nb_steps)
+
+ # the uniqueness of each spatio temporal index is not garanteed by the current algo
+ # it will work in classical cases, and raise an assert when uniqueness is needed (when using a slicer)
+ index1 = pd.Series(spatial_coordinates.spatial_index())
+ index2 = pd.Series(coordinates.spatial_index())
+ ind = index1 != index2 # type: pd.Series
+ self.assertEqual(sum(ind), 0, msg="spatial_coordinates:\n{} \n!= spatio_temporal_coordinates \n{}".
+ format(index1.loc[ind], index2.loc[ind]))
+
def test_ordered_coordinates(self):
# Order coordinates, to ensure that the first dimension/the second dimension and so on..
# Always are in the same order to a given type (e.g. spatio_temporal= of coordinates
--
GitLab