Skip to content
Snippets Groups Projects

Resolve "Adding new datasets"

Merged Leo Bouscarrat requested to merge 17-adding-new-datasets into master
3 files
+ 26
2
Compare changes
  • Side-by-side
  • Inline
Files
3
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
@@ -103,6 +104,12 @@ 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
else:
raise ValueError("Unsupported dataset '{}'".format(name))
Loading