Skip to content

FIX allow target to be a float #24

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mfeurer merged 1 commit into from
Jan 9, 2016
Merged

FIX allow target to be a float #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 3 additions & 4 deletions openml/entities/dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,8 +122,7 @@ def decode_arff(fh):
return decode_arff(fh)

############################################################################
# pandas related stuff...
def get_dataset(self, target=None, include_row_id=False,
def get_dataset(self, target=None, target_dtype=int, include_row_id=False,
include_ignore_attributes=False,
return_categorical_indicator=False,
return_attribute_names=False):
Expand Down Expand Up @@ -176,7 +175,7 @@ def get_dataset(self, target=None, include_row_id=False,

try:
x = data[:,~targets]
y = data[:,targets].astype(np.int32)
y = data[:,targets].astype(target_dtype)

if len(y.shape) == 2 and y.shape[1] == 1:
y = y[:,0]
Expand All @@ -191,7 +190,7 @@ def get_dataset(self, target=None, include_row_id=False,
raise e

if scipy.sparse.issparse(y):
y = np.asarray(y.todense()).astype(np.int32).flatten()
y = np.asarray(y.todense()).astype(target_dtype).flatten()

rval.append(x)
rval.append(y)
Expand Down
9 changes: 8 additions & 1 deletion openml/entities/task.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,14 @@ def get_dataset(self):
def get_X_and_Y(self):
dataset = self.get_dataset()
# Replace with retrieve from cache
X_and_Y = dataset.get_dataset(target=self.target_feature)
if 'Supervised Classification'.lower() in self.task_type.lower():
target_dtype = int
elif 'Supervised Regression'.lower() in self.task_type.lower():
target_dtype = float
else:
raise NotImplementedError(self.task_type)
X_and_Y = dataset.get_dataset(target=self.target_feature,
target_dtype=target_dtype)
return X_and_Y

def evaluate(self, algo):
Expand Down