def test_graph_creation(self):
# Test multiple graph creation possibilities
# Import ratings as DataFrame
ratings_import = RatingsImporter(source=CSVFile(ratings_filename),
from_id_column='user_id',
to_id_column='item_id',
score_column='points',
timestamp_column='timestamp',
score_processor=NumberNormalizer())
ratings_frame = ratings_import.import_ratings()
# Create graph using the property 'starring' from representation '0' ('dbpedia')
g = NXTripartiteGraph(ratings_frame,
movies_dir,
item_exo_representation=0,
item_exo_properties=['starring'])
# Simple assert just to make sure the graph is created
self.assertGreater(len(g.user_nodes), 0)
self.assertGreater(len(g.item_nodes), 0)
self.assertGreater(len(g.property_nodes), 0)
# Create graph specifying only the exo representation
g = NXTripartiteGraph(ratings_frame,
movies_dir,
item_exo_representation="dbpedia")
# Simple assert just to make sure the graph is created
self.assertGreater(len(g.user_nodes), 0)
self.assertGreater(len(g.item_nodes), 0)
self.assertGreater(len(g.property_nodes), 0)
# Create graph specifying only the exo representation
g = NXTripartiteGraph(ratings_frame,
movies_dir,
item_exo_properties=['starring'])
# Simple assert just to make sure the graph is created
self.assertGreater(len(g.user_nodes), 0)
self.assertGreater(len(g.item_nodes), 0)
self.assertGreater(len(g.property_nodes), 0)
# Create graph specifying without properties
g = NXTripartiteGraph(ratings_frame)
# Simple assert just to make sure the graph is created
self.assertGreater(len(g.user_nodes), 0)
self.assertGreater(len(g.item_nodes), 0)
self.assertEqual(len(g.property_nodes), 0)
def test_populate_from_dataframe_w_labels(self):
df_label = pd.DataFrame.from_dict({
'from_id': ["1", "1", "2", "2", "2", "3", "4", "4"],
'to_id': [
"tt0112281", "tt0112302", "tt0112281", "tt0112346",
"tt0112453", "tt0112453", "tt0112346", "tt0112453"
],
'score': [0.8, 0.7, -0.4, 1.0, 0.4, 0.1, -0.3, 0.7],
'label': [
'score_df', 'score_df', 'score_df', 'score_df', 'score_df',
'score_df', 'score_df', 'score_df'
]
})
g: NXTripartiteGraph = NXTripartiteGraph(
df_label,
movies_dir,
item_exo_representation="dbpedia",
item_exo_properties=['film director'])
for user, item, score in zip(df_label['from_id'], df_label['to_id'],
df_label['score']):
expected = {'label': 'score_df', 'weight': score}
result = g.get_link_data(user, item)
self.assertEqual(expected, result)
def setUp(self) -> None:
self.df = pd.DataFrame.from_dict({'from_id': ["1", "1", "2", "2", "2", "3", "4", "4"],
'to_id': ["tt0112281", "tt0112302", "tt0112281", "tt0112346",
"tt0112453", "tt0112453", "tt0112346", "tt0112453"],
'score': [0.8, 0.7, -0.4, 1.0, 0.4, 0.1, -0.3, 0.7]})
self.g: NXTripartiteGraph = NXTripartiteGraph(self.df, movies_dir,
item_exo_representation="dbpedia",
item_exo_properties=['film director'])