def output_predictions(dataset: Dataset, y_preds: np.ndarray,
csv_out: str) -> None:
"""Writes predictions to file.
Writes predictions made on `dataset` to a specified file on
disk. `dataset.ids` are used to format predictions. The produce CSV file will have format as follows
| ID | Task1Name | Task2Name |
| ----------- | ------------ | ------------ |
| identifer1 | prediction11 | prediction12 |
| identifer2 | prediction21 | prediction22 |
Parameters
----------
dataset: dc.data.Dataset
Dataset on which predictions have been made.
y_preds: np.ndarray
Predictions to output
csv_out: str
Name of file to write predictions to.
"""
data_ids = dataset.ids
n_tasks = len(dataset.get_task_names())
y_preds = np.reshape(y_preds, (len(y_preds), n_tasks))
assert len(y_preds) == len(data_ids)
with open(csv_out, "w") as csvfile:
csvwriter = csv.writer(csvfile)
csvwriter.writerow(["ID"] + dataset.get_task_names())
for mol_id, y_pred in zip(data_ids, y_preds):
csvwriter.writerow([mol_id] + list(y_pred))
def __init__(self, dataset: Dataset):
super(DuplicateBalancingTransformer, self).__init__(transform_X=True,
transform_y=True,
transform_w=True,
transform_ids=True,
dataset=dataset)
if len(dataset.get_task_names()) > 1:
raise ValueError(
"This transformation is only defined for singletask datsets.")
# Get the labels/weights
y = dataset.y
w = dataset.w
# Normalize shapes
if len(y.shape) == 1:
y = np.reshape(y, (len(y), 1))
if len(w.shape) == 1:
w = np.reshape(w, (len(w), 1))
if len(y.shape) != 2:
raise ValueError("y must be of shape (N,) or (N, n_tasks)")
if len(w.shape) != 2:
raise ValueError("w must be of shape (N,) or (N, n_tasks)")
self.classes = sorted(np.unique(y))
# Remove labels with zero weights
y = y[w != 0]
N = len(y)
class_weights = []
# Note that we may have 0 elements of a given class since we remove those
# labels with zero weight.
for c in self.classes:
# this works because y is 1D
c_weight = np.sum(w[y == c])
class_weights.append(c_weight)
weight_largest = max(class_weights)
# This is the right ratio since int(N/num_c) * num_c \approx N
# for all classes
duplication_ratio = [
int(weight_largest / float(c_weight)) if c_weight > 0 else 0
for c_weight in class_weights
]
self.duplication_ratio = duplication_ratio
