def test_closest_point_lenght_no_filter(self):
params = {'filter': False, 'distance': 0}
link_strategy = ClosestPoint(params)
ds_a = App.get_ds(self.gf1.get_id())
ds_b = App.get_ds(self.gf2.get_id())
dataset = link_strategy.link(ds_a, ds_b)
self.assertEqual(len(dataset.index), 3)
def test_empty_closest_point(self):
params = {'filter': True, 'distance': 3}
link_strategy = ClosestPoint(params)
ds_a = App.get_ds(self.gf1.get_id())
ds_b = App.get_ds(self.gf2.get_id())
dataset = link_strategy.link(ds_a, ds_b)
self.assertEqual(dataset.size, 0)
def test_polygon_lenght(self):
params = {'distance': 3000}
link_strategy = Polygon(params)
ds_a = App.get_ds(self.gf1.get_id())
ds_b = App.get_ds(self.gf2.get_id())
dataset = link_strategy.link(ds_a, ds_b)
self.assertEqual(len(dataset.index), 9)
def test_empty_polygon(self):
params = {'distance': 3}
link_strategy = Polygon(params)
ds_a = App.get_ds(self.gf1.get_id())
ds_b = App.get_ds(self.gf2.get_id())
dataset = link_strategy.link(ds_a, ds_b)
self.assertEqual(dataset.size, 0)
def test_closest_point(self):
params = {'distance': 0, 'filter': False}
link_strategy = ClosestPoint(params)
ds_a = App.get_ds(self.gf1.get_id())
ds_b = App.get_ds(self.gf2.get_id())
dataset = link_strategy.link(ds_a, ds_b)
linked_file = App.link_closest_points(self.gf1.get_id(), self.gf2.get_id(), "name", "description", params)
dataset_linked = linked_file.get_data()
pd.testing.assert_frame_equal(dataset, dataset_linked)
def test_polygon(self):
params = {'distance': 3000}
link_strategy = Polygon(params)
ds_a = App.get_ds(self.gf1.get_id())
ds_b = App.get_ds(self.gf2.get_id())
dataset = link_strategy.link(ds_a, ds_b)
linked_file = App.link_polygon(self.gf1.get_id(), self.gf2.get_id(), "name", "description", params)
dataset_linked = linked_file.get_data()
pd.testing.assert_frame_equal(dataset, dataset_linked)
def test_link_similarity_same_y_column(self):
r_1 = Rule('verificado', 'JURISDICCI', [{"Verificado": "PROV"}])
r_2 = Rule('valorVinchuca', 'JURISDICCI', [{"patagonica": "PROV"}])
rules = [r_1, r_2]
params = {'rules': rules}
link_strategy = Similarity(params)
ds_a = App.get_ds(self.gf1.get_id())
ds_b = App.get_ds(self.gf2.get_id())
dataset = link_strategy.link(ds_a, ds_b)
self.assertTrue(len(dataset.index) == 1)
def test_categorize_uncategorize_values(self):
dataset = App.get_ds(self.gf2.get_id()).get_data()
cat_col = Categorizer.categorize_column(dataset, 'p1')
dataset['p1_cat'] = cat_col
cat_value = dataset.iloc[0]['p1_cat']
real_value = dataset.iloc[0]['p1']
uncat_value = Categorizer.uncategorize_value(dataset, 'p1', cat_value)
self.assertEqual(real_value, uncat_value)
def test_get_details(self):
ds_a = App.get_ds(self.gf.get_id())
details = ds_a.get_details()
self.assertEqual(details['name'], 'geofile test')
self.assertEqual(details['description'], 'description')
self.assertEqual(details['doc'], 'test_files/GeoVin_sample.csv')
def test_categorize_column_long(self):
dataset = App.get_ds(self.gf2.get_id()).get_data()
cat_col = Categorizer.categorize_column(dataset, 'p1')
uncat_col = dataset[['p1']]
self.assertEqual(len(cat_col), len(uncat_col))