Resolve "Experiment pipeline"

Closes #12 (closed)

code/bolsonaro/data/dataset_loader.py

@@ -19,13 +19,23 @@ class DatasetLoader(object):
     DEFAULT_NORMALIZE_D = False
     DEFAULT_DATASET_NORMALIZER = 'standard'
     DEFAULT_FOREST_SIZE = 100
-    DEFAULT_EXTRACTED_FOREST_SIZE = 10
+    DEFAULT_EXTRACTED_FOREST_SIZE_SAMPLES = 5
+    DEFAULT_EXTRACTED_FOREST_SIZE_STOP = 0.1
     DEFAULT_DEV_SIZE = 0.2
     DEFAULT_TEST_SIZE = 0.2
     DEFAULT_RANDOM_SEED_NUMBER = 1
     DEFAULT_SUBSETS_USED = 'train,dev'
     DEFAULT_NORMALIZE_WEIGHTS = False
 
+    dataset_names = ['boston', 'iris', 'diabetes', 'digits', 'linnerud', 'wine',
+        'breast_cancer', 'olivetti_faces', '20newsgroups_vectorized', 'lfw_people',
+        'lfw_pairs', 'covtype', 'rcv1', 'california_housing']
+
+    dataset_seed_numbers = {'boston':15, 'iris':15, 'diabetes':15, 'digits':5,
+        'linnerud':15, 'wine':15, 'breast_cancer':15, 'olivetti_faces':15,
+        '20newsgroups_vectorized':3, 'lfw_people':3,
+        'lfw_pairs':3, 'covtype':3, 'rcv1':3, 'california_housing':3}
+
     @staticmethod
     def load(dataset_parameters):
         name = dataset_parameters.name