def _find_best_split(self, X, target, n_features):
"""Find best feature and value for a split. Greedy algorithm."""
# Sample random subset of features
subset = random.sample(list(range(0, X.shape[1])), n_features)
max_gain, max_col, max_val = None, None, None
for column in subset:
split_values = self._find_splits(X[:, column])
for value in split_values:
if self.loss is None:
# Random forest
splits = split(X[:, column], target["y"], value)
gain = self.criterion(target["y"], splits)
else:
# Gradient boosting
left, right = split_dataset(X,
target,
column,
value,
return_X=False)
gain = xgb_criterion(target, left, right, self.loss)
if (max_gain is None) or (gain > max_gain):
max_col, max_val, max_gain = column, value, gain
return max_col, max_val, max_gain
def _find_best_split(self, X, target, n_features):
"""Find best feature and value for a split. Greedy algorithm."""
# Sample random subset of features
subset = random.sample(list(range(0, X.shape[1])), n_features)
max_gain, max_col, max_val = None, None, None
for column in subset:
split_values = self._find_splits(X[:, column])
for value in split_values:
if self.loss is None:
# Random forest
splits = split(X[:, column], target['y'], value)
gain = self.criterion(target['y'], splits)
else:
# Gradient boosting
left, right = split_dataset(X, target, column, value, return_X=False)
gain = xgb_criterion(target, left, right, self.loss)
if (max_gain is None) or (gain > max_gain):
max_col, max_val, max_gain = column, value, gain
return max_col, max_val, max_gain