Resolve "Adding new datasets"

Closes #17 (closed)

code/bolsonaro/data/dataset_loader.py

 from bolsonaro.data.dataset import Dataset
 from bolsonaro.data.dataset_parameters import DatasetParameters
 from bolsonaro.data.task import Task
-from bolsonaro.utils import change_binary_func_load
+from bolsonaro.utils import change_binary_func_load, change_binary_func_openml
 
 from sklearn.datasets import load_boston, load_iris, load_diabetes, \
     load_digits, load_linnerud, load_wine, load_breast_cancer
 from sklearn.datasets import fetch_olivetti_faces, fetch_20newsgroups, \
     fetch_20newsgroups_vectorized, fetch_lfw_people, fetch_lfw_pairs, \
-    fetch_covtype, fetch_rcv1, fetch_kddcup99, fetch_california_housing
+    fetch_covtype, fetch_rcv1, fetch_kddcup99, fetch_california_housing, \
+    fetch_openml
 from sklearn.model_selection import train_test_split
 from sklearn import preprocessing
 import random
@@ -30,13 +31,15 @@ class DatasetLoader(object):
 
     dataset_names = ['boston', 'iris', 'diabetes', 'digits', 'linnerud', 'wine',
         'breast_cancer', 'olivetti_faces', '20newsgroups_vectorized', 'lfw_people',
-        'lfw_pairs', 'covtype', 'rcv1', 'california_housing', 'diamonds']
+        'lfw_pairs', 'covtype', 'rcv1', 'california_housing', 'diamonds', 'steel-plates',
+        'kr-vs-kp', 'kin8nm', 'spambase', 'musk', 'gamma']
 
     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,
-        'diamonds': 15}
+        'diamonds': 15, 'steel-plates': 15, 'kr-vs-kp': 15, 'kin8nm': 15,
+        'spambase': 15, 'musk': 15, 'gamma': 15}
 
     @staticmethod
     def load(dataset_parameters):
@@ -103,6 +106,24 @@ class DatasetLoader(object):
             df['clarity'] = label_clarity.fit_transform(df['clarity'])
             X, y = df.drop(['price'], axis=1), df['price']
             task = Task.REGRESSION
+        elif name == 'steel-plates':
+            dataset_loading_func = change_binary_func_openml('steel-plates-fault')
+            task = Task.BINARYCLASSIFICATION
+        elif name == 'kr-vs-kp':
+            dataset_loading_func = change_binary_func_openml('kr-vs-kp')
+            task = Task.BINARYCLASSIFICATION
+        elif name == 'kin8nm':
+            X, y = fetch_openml('kin8nm', return_X_y=True)
+            task = Task.REGRESSION
+        elif name == 'spambase':
+            dataset_loading_func = change_binary_func_openml('spambase')
+            task = Task.BINARYCLASSIFICATION
+        elif name == 'musk':
+            dataset_loading_func = change_binary_func_openml('musk')
+            task = Task.BINARYCLASSIFICATION
+        elif name == 'gamma':
+            dataset_loading_func = change_binary_func_openml('MagicTelescope')
+            task = Task.BINARYCLASSIFICATION
         else:
             raise ValueError("Unsupported dataset '{}'".format(name))