Add contamination in search space

Former-commit-id: 3f139897fb [formerly 04d7e27734] [formerly e618da4e70 [formerly 2fd75c3049]] [formerly be4cdeb1ee [formerly bba38975a3] [formerly a5dcb7ab07 [formerly f945aa4364]]] [formerly 82ae2da087 [formerly bb11a4532c] [formerly 63451e4b70 [formerly 5035bf6322]] [formerly 7b791a30e1 [formerly 00e00dd70f] [formerly f66efd0a10 [formerly d7af1ef507]]]] [formerly d2a0264fc2 [formerly c55d4b16b4] [formerly 2d7715e3d3 [formerly 24307eed11]] [formerly ab2b1446d9 [formerly c057133710] [formerly e22102eb84 [formerly 2c55b6d1aa]]] [formerly d32a102292 [formerly b1caa653f5] [formerly a92a468a17 [formerly 4de123d446]] [formerly e48763f90b [formerly c90c8f7f0e] [formerly 80a9d94529 [formerly add1537efb]]]]] [formerly 37efaab596 [formerly 90f814268c] [formerly d7be7d5679 [formerly e3528a572a]] [formerly 8e1cff5939 [formerly 9f458320a3] [formerly 93f778acb1 [formerly b0e5c76275]]] [formerly 6e3d0e73b5 [formerly 126851f161] [formerly 79c90d2002 [formerly 988f625a20]] [formerly 648efa8778 [formerly aa10ee488e] [formerly 5be6e6d7b8 [formerly 4b102142c0]]]] [formerly 36ad409dcc [formerly 886dc8c7f4] [formerly 7e08e9f120 [formerly c0ba3a46fc]] [formerly d2ebd67acc [formerly cbff225436] [formerly 1328112d6b [formerly f2421d2131]]] [formerly 50b979e655 [formerly 6796c342fa] [formerly 7f272a3b6f [formerly 922fcbdc0c]] [formerly d916177935 [formerly 5ad31a4f53] [formerly eb1ce127ee [formerly 9c3372f82a]]]]]]
Former-commit-id: 9c1285f453 [formerly 21fdc9fdf0] [formerly 4f763c4d4c [formerly 5623ded1f9]] [formerly 07e1e9a446 [formerly febe242f80] [formerly 7e6c2ba8d3 [formerly 22172b003f]]] [formerly f00294c5aa [formerly 2f6b5bf341] [formerly b893578a6d [formerly 0f30b578c4]] [formerly dbda257930 [formerly 3195dd4d1b] [formerly 588f4a1274 [formerly 42517b31b7]]]] [formerly ea2c11d3c2 [formerly bb37d1e8b5] [formerly 8407f2ed5c [formerly b319e8fb74]] [formerly 4741fc5b10 [formerly 8701b6ebfb] [formerly 2c1e0cd268 [formerly 23d8ae15f2]]] [formerly 0c9ecc8d4e [formerly dc002a700f] [formerly 7147d97cbb [formerly c47ff75a02]] [formerly bf6a097ff3 [formerly 81b04b4f4b] [formerly eb1ce127ee]]]]
Former-commit-id: 4053f550f3 [formerly ce1c6ed88b] [formerly 8ccd6a1e2c [formerly 0a551d048d]] [formerly 57dba6d093 [formerly d7fb5c06b6] [formerly 410bf93bae [formerly feb3a1cf8e]]] [formerly f283cd9621 [formerly 796b8d0fcd] [formerly 9e57aad65d [formerly 6460b71277]] [formerly e3b6d69e00 [formerly a9086944fd] [formerly 3e49257f0b [formerly f420b0c0f4]]]]
Former-commit-id: 75f2277b9c [formerly 3347ba6632] [formerly 1b7191daf1 [formerly a31cda40e2]] [formerly edb6e56cbf [formerly 935752d705] [formerly 55033c663d [formerly 4d4d57a6a7]]]
Former-commit-id: 872be1c058 [formerly a6b17cdd10] [formerly f406d843b5 [formerly f0a48f8ceb]]
Former-commit-id: 3a4ff971b3 [formerly 1fee01220f]
Former-commit-id: 386e07f20a

examples/run_automl.py

@@ -13,6 +13,7 @@ table_path = 'datasets/yahoo_sub_5.csv'
 target_index = 6 # what column is the target
 #table_path = 'datasets/NAB/realTweets/labeled_Twitter_volume_IBM.csv' # The path of the dataset
 time_limit = 30 # How many seconds you wanna search
+
 #metric = 'F1' # F1 on label 1
 metric = 'F1_MACRO' # F1 on both label 0 and 1
 
@@ -21,7 +22,7 @@ df = pd.read_csv(table_path)
 dataset, problem_description = generate_dataset_problem(df, target_index=target_index, metric=metric)
 
 # Start backend
-backend = SimpleRunner(random_seed=0)
+backend = SimpleRunner(random_seed=42)
 
 # Start search algorithm
 search = BruteForceSearch(problem_description=problem_description, backend=backend)

tods/searcher/search/brute_force_search.py

@@ -148,7 +148,8 @@ primitive_python_paths = {
         #'d3m.primitives.tods.detection_algorithm.KDiscordODetector',
         #'d3m.primitives.tods.detection_algorithm.deeplog',
         #'d3m.primitives.tods.detection_algorithm.telemanom',
-    ]
+    ],
+    'contamination': [0.01, 0.02, 0.05, 0.07, 0.1, 0.15, 0.2],
 }
 
 
@@ -233,6 +234,7 @@ def _generate_pipline(combinations):
         tods_step_6= PrimitiveStep(primitive=index.get_primitive(combination[2]))
         tods_step_6.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.5.produce')
         tods_step_6.add_output('produce')
+        tods_step_6.add_hyperparameter(name='contamination', argument_type=ArgumentType.VALUE, data=combination[3])
         pipeline_description.add_step(tods_step_6)
 
         #tods_step_7 = PrimitiveStep(primitive=index.get_primitive(combination[3]))
@@ -267,7 +269,7 @@ def _generate_pipelines(primitive_python_paths, cpu_count=40):
     import multiprocessing as mp
 
     #components = ['data_processing', 'timeseries_processing', 'feature_analysis', 'detection_algorithm']
-    components = ['timeseries_processing', 'feature_analysis', 'detection_algorithm']
+    components = ['timeseries_processing', 'feature_analysis', 'detection_algorithm', 'contamination']
     combinations = itertools.product(*(primitive_python_paths[k] for k in components))