def test_simple_graph(self):
for input_type in [pd.DataFrame, SFrame, list]:
g = SGraph()
if input_type is list:
vertices = [Vertex(x[1]['vid'], {'color': x[1]['color'], 'vec': x[1]['vec']}) for x in self.vertices.iterrows()]
edges = [Edge(x[1]['src_id'], x[1]['dst_id'], {'weight': x[1]['weight']}) for x in self.edges.iterrows()]
g = g.add_vertices(vertices)
g = g.add_edges(edges)
else:
g = g.add_vertices(input_type(self.vertices), vid_field='vid')
g = g.add_edges(input_type(self.edges), src_field='src_id', dst_field='dst_id')
self.assertEqual(g.summary(), {'num_vertices': 4, 'num_edges': 3})
self.assertItemsEqual(g.get_fields(), ['__id', '__src_id', '__dst_id', 'color', 'vec', 'weight'])
self.assertItemsEqual(g.get_vertices(format='dataframe').columns.values, ['color', 'vec'])
self.assertItemsEqual(g.get_edges(format='dataframe').columns.values, ['__src_id', '__dst_id', 'weight'])
self.assertTrue(g.get_edges(format='dataframe').shape, (3, 3))
self.assertTrue(g.get_vertices(format='dataframe').shape, (4, 3))
self.assertTrue(g.get_vertices(format='dataframe', fields={'color': 'g'}).shape, (1, 2))
self.assertTrue(g.get_edges(format='dataframe', fields={'weight': 0.}).shape, (1, 3))
self.assertItemsEqual(g.get_vertices(format='sframe').column_names(), ['__id', 'color', 'vec'])
self.assertItemsEqual(g.get_edges(format='sframe').column_names(), ['__src_id', '__dst_id', 'weight'])
self.assertTrue(g.get_edges(format='sframe').shape, (3, 3))
self.assertTrue(g.get_vertices(format='sframe').shape, (4, 3))
self.assertTrue(g.get_vertices(format='sframe', fields={'color': 'g'}).shape, (1, 2))
self.assertTrue(g.get_edges(format='sframe', fields={'weight': 0.}).shape, (1, 3))
vertices = g.get_vertices(format='list')
edges = g.get_edges(format='list')
self.assertEqual(len(vertices), 4)
self.assertEqual(len(edges), 3)
# get edges is lazy
edges = g.get_edges()
self.assertFalse(edges.__is_materialized__())
def test_save_load(self):
g = SGraph().add_vertices(self.vertices,
'vid').add_edges(self.edges, 'src_id',
'dst_id')
with util.TempDirectory() as f:
g.save(f)
g2 = load_graph(f, 'binary')
self.assertEqual(g2.summary(), {'num_vertices': 4, 'num_edges': 3})
self.assertItemsEqual(
g2.get_fields(),
{'__id', '__src_id', '__dst_id', 'color', 'vec', 'weight'})
with util.TempDirectory() as f:
g.save(f, format='csv')
vertices = SFrame.read_csv(f + "/vertices.csv")
edges = SFrame.read_csv(f + "/edges.csv")
g2 = SGraph().add_edges(edges, '__src_id',
'__dst_id').add_vertices(vertices, '__id')
self.assertEqual(g2.summary(), {'num_vertices': 4, 'num_edges': 3})
self.assertItemsEqual(
g2.get_fields(),
{'__id', '__src_id', '__dst_id', 'color', 'vec', 'weight'})
with tempfile.NamedTemporaryFile(suffix='.json') as f:
g.save(f.name)
with open(f.name, 'r') as f2:
data = f2.read()
g2 = json.loads(data)
self.assertTrue("vertices" in g2)
self.assertTrue("edges" in g2)
def test_empty_graph(self):
g = SGraph()
self.assertEqual(g.summary(), {'num_vertices': 0, 'num_edges': 0})
self.assertEqual(len(g.get_fields()), 3)
self.assertTrue(g.get_vertices(format='sframe').shape, (0, 1))
self.assertTrue(g.get_edges(format='sframe').shape, (0, 2))
self.assertTrue(g.vertices.shape, (0, 1))
self.assertTrue(g.edges.shape, (0, 2))
self.assertTrue(len(g.get_vertices(format='list')) == 0)
self.assertTrue(len(g.get_edges(format='list')) == 0)
def test_empty_graph(self):
g = SGraph()
self.assertEqual(g.summary(), {'num_vertices': 0, 'num_edges': 0})
self.assertEqual(len(g.get_fields()), 3)
self.assertTrue(g.get_vertices(format='sframe').shape, (0, 1))
self.assertTrue(g.get_edges(format='sframe').shape, (0, 2))
self.assertTrue(g.vertices.shape, (0, 1))
self.assertTrue(g.edges.shape, (0, 2))
self.assertTrue(len(g.get_vertices(format='list')) == 0)
self.assertTrue(len(g.get_edges(format='list')) == 0)
def test_select_query_with_same_vertex_edge_field(self):
vertices = SFrame({'__id': range(10)})
edges = SFrame({'__src_id': range(10), '__dst_id': range(1, 11)})
g = SGraph(vertices, edges)
g.vertices['weight'] = 0
g.vertices['v'] = 0
g.edges['weight'] = 0
g.edges['e'] = 0
self.assertItemsEqual(g.get_fields(), ['v', 'e', 'weight', 'weight', '__id', '__src_id', '__dst_id'])
g2 = g.select_fields('weight')
self.assertItemsEqual(g2.get_fields(), ['weight', 'weight', '__id', '__src_id', '__dst_id'])
def test_select_query(self):
g = SGraph()
g = g.add_vertices(self.vertices, 'vid').add_edges(self.edges, 'src_id', 'dst_id')
g2 = g.select_fields(["color", "weight"])
self.assertSequenceEqual((g2.get_fields()), ['__id', 'color', '__src_id', '__dst_id', 'weight'])
g2 = g.select_fields(["color"])
self.assertSequenceEqual((g2.get_fields()), ['__id', 'color', '__src_id', '__dst_id'])
del g.edges['weight']
del g.vertices['vec']
g.vertices['color2'] = g.vertices['color']
self.assertSequenceEqual((g.get_fields()), ['__id', 'color', 'color2', '__src_id', '__dst_id'])
g2 = g.select_fields([])
self.assertSequenceEqual((g2.get_fields()), ['__id', '__src_id', '__dst_id'])
def test_select_query_with_same_vertex_edge_field(self):
vertices = SFrame({'__id': range(10)})
edges = SFrame({'__src_id': range(10), '__dst_id': range(1, 11)})
g = SGraph(vertices, edges)
g.vertices['weight'] = 0
g.vertices['v'] = 0
g.edges['weight'] = 0
g.edges['e'] = 0
self.assertItemsEqual(
g.get_fields(),
['v', 'e', 'weight', 'weight', '__id', '__src_id', '__dst_id'])
g2 = g.select_fields('weight')
self.assertItemsEqual(
g2.get_fields(),
['weight', 'weight', '__id', '__src_id', '__dst_id'])
def test_robust_parse(self):
df = pd.DataFrame({'int': [1, 2, 3],
'float': [1., 2., 3.],
'str': ['one', 'two', 'three'],
'nan': [np.nan, np.nan, np.nan],
'sparse_int': [1, 2, np.nan],
'sparse_float': [np.nan, 2., 3.],
'sparse_str': [None, 'two', None]
})
g = SGraph().add_vertices(df)
self.assertItemsEqual(g.get_fields(), df.columns.tolist() + ['__id', '__src_id', '__dst_id'])
df2 = g.get_vertices(format='dataframe')
sf = g.get_vertices(format='sframe')
for col in df.columns:
# potential bug: df2 is missing the 'nan' column.
if (col != 'nan'):
self.assertItemsEqual(sorted(list(df2[col].dropna())), sorted(list(df[col].dropna())))
self.assertItemsEqual(sorted(list(sf[col].dropna())), sorted(list(df[col].dropna())))
def test_select_query(self):
g = SGraph()
g = g.add_vertices(self.vertices,
'vid').add_edges(self.edges, 'src_id', 'dst_id')
g2 = g.select_fields(["color", "weight"])
self.assertSequenceEqual(
(g2.get_fields()),
['__id', 'color', '__src_id', '__dst_id', 'weight'])
g2 = g.select_fields(["color"])
self.assertSequenceEqual((g2.get_fields()),
['__id', 'color', '__src_id', '__dst_id'])
del g.edges['weight']
del g.vertices['vec']
g.vertices['color2'] = g.vertices['color']
self.assertSequenceEqual(
(g.get_fields()),
['__id', 'color', 'color2', '__src_id', '__dst_id'])
g2 = g.select_fields([])
self.assertSequenceEqual((g2.get_fields()),
['__id', '__src_id', '__dst_id'])
def test_save_load(self):
g = SGraph().add_vertices(self.vertices, 'vid').add_edges(self.edges, 'src_id', 'dst_id')
with util.TempDirectory() as f:
g.save(f)
g2 = load_graph(f, 'binary')
self.assertEqual(g2.summary(), {'num_vertices': 4, 'num_edges': 3})
self.assertItemsEqual(g2.get_fields(), {'__id', '__src_id', '__dst_id', 'color', 'vec', 'weight'})
with util.TempDirectory() as f:
g.save(f, format='csv')
vertices = SFrame.read_csv(f + "/vertices.csv")
edges = SFrame.read_csv(f + "/edges.csv")
g2 = SGraph().add_edges(edges, '__src_id', '__dst_id').add_vertices(vertices, '__id')
self.assertEqual(g2.summary(), {'num_vertices': 4, 'num_edges': 3})
self.assertItemsEqual(g2.get_fields(), {'__id', '__src_id', '__dst_id', 'color', 'vec', 'weight'})
with tempfile.NamedTemporaryFile(suffix='.json') as f:
g.save(f.name)
with open(f.name, 'r') as f2:
data = f2.read()
g2 = json.loads(data)
self.assertTrue("vertices" in g2)
self.assertTrue("edges" in g2)
def test_robust_parse(self):
df = pd.DataFrame({
'int': [1, 2, 3],
'float': [1., 2., 3.],
'str': ['one', 'two', 'three'],
'nan': [np.nan, np.nan, np.nan],
'sparse_int': [1, 2, np.nan],
'sparse_float': [np.nan, 2., 3.],
'sparse_str': [None, 'two', None]
})
g = SGraph().add_vertices(df)
self.assertItemsEqual(
g.get_fields(),
df.columns.tolist() + ['__id', '__src_id', '__dst_id'])
df2 = g.get_vertices(format='dataframe')
sf = g.get_vertices(format='sframe')
for col in df.columns:
# potential bug: df2 is missing the 'nan' column.
if (col != 'nan'):
self.assertItemsEqual(sorted(list(df2[col].dropna())),
sorted(list(df[col].dropna())))
self.assertItemsEqual(sorted(list(sf[col].dropna())),
sorted(list(df[col].dropna())))
def test_simple_graph(self):
for input_type in [pd.DataFrame, SFrame, list]:
g = SGraph()
if input_type is list:
vertices = [
Vertex(x[1]['vid'], {
'color': x[1]['color'],
'vec': x[1]['vec']
}) for x in self.vertices.iterrows()
]
edges = [
Edge(x[1]['src_id'], x[1]['dst_id'],
{'weight': x[1]['weight']})
for x in self.edges.iterrows()
]
g = g.add_vertices(vertices)
g = g.add_edges(edges)
else:
g = g.add_vertices(input_type(self.vertices), vid_field='vid')
g = g.add_edges(input_type(self.edges),
src_field='src_id',
dst_field='dst_id')
self.assertEqual(g.summary(), {'num_vertices': 4, 'num_edges': 3})
self.assertItemsEqual(
g.get_fields(),
['__id', '__src_id', '__dst_id', 'color', 'vec', 'weight'])
self.assertItemsEqual(
g.get_vertices(format='dataframe').columns.values,
['color', 'vec'])
self.assertItemsEqual(
g.get_edges(format='dataframe').columns.values,
['__src_id', '__dst_id', 'weight'])
self.assertTrue(g.get_edges(format='dataframe').shape, (3, 3))
self.assertTrue(g.get_vertices(format='dataframe').shape, (4, 3))
self.assertTrue(
g.get_vertices(format='dataframe', fields={
'color': 'g'
}).shape, (1, 2))
self.assertTrue(
g.get_edges(format='dataframe', fields={
'weight': 0.
}).shape, (1, 3))
self.assertItemsEqual(
g.get_vertices(format='sframe').column_names(),
['__id', 'color', 'vec'])
self.assertItemsEqual(
g.get_edges(format='sframe').column_names(),
['__src_id', '__dst_id', 'weight'])
self.assertTrue(g.get_edges(format='sframe').shape, (3, 3))
self.assertTrue(g.get_vertices(format='sframe').shape, (4, 3))
self.assertTrue(
g.get_vertices(format='sframe', fields={
'color': 'g'
}).shape, (1, 2))
self.assertTrue(
g.get_edges(format='sframe', fields={
'weight': 0.
}).shape, (1, 3))
vertices = g.get_vertices(format='list')
edges = g.get_edges(format='list')
self.assertEqual(len(vertices), 4)
self.assertEqual(len(edges), 3)
# get edges is lazy
edges = g.get_edges()
self.assertFalse(edges.__is_materialized__())
