def testExecuteCacheTable(self): df = self.odps_df[self.odps_df.name == 'name1'] result = df.execute().values self.assertEqual(len(result), 2) self.assertTrue(context.is_cached(df)) dag = self.engine.compile(df) calls = dag.topological_sort() self.assertEqual(len(calls), 1) self.assertTrue(is_source_collection(calls[0].expr)) df2 = df[:5] result = df2.execute() self.assertEqual(len(result), 2)
def testHandleCache(self): df = self.pd_df['name', self.pd_df.id + 1] df.execute() self.assertTrue(context.is_cached(df)) df2 = df[df.id < 10] dag = self.engine.compile(df2) self.assertEqual(len(dag.nodes()), 1) self.assertTrue(is_source_collection(dag.nodes()[0].expr.input)) df3 = self.pd_df[self.pd_df.id < 10].count() i = df3.execute() self.assertTrue(context.is_cached(df3)) df4 = df3 + 1 dag = self.engine.compile(df4) self.assertEqual(len(dag.nodes()), 1) self.assertIsNotNone(dag.nodes()[0].expr._fields[0].lhs.value) self.assertEqual(df4.execute(), i + 1)