Parallelize Gini impurity calculation for oblique splitter

[eigenvivek]

Is your feature request related to a problem? Please describe.

The existing ObliqueSplitter implementation calculates Gini impurity for each potential split in series.

This is slow. As @parthgvora noted:

ProgLearn/proglearn/transformers.py

Lines 510 to 511 in 61fb08a

	Note that the code for this method needs to be parallelized. This is a major
	bottleneck in integration with scikit-learn.

Describe the solution you'd like

Replace this code block with a joblib parallelization:

ProgLearn/proglearn/transformers.py

Lines 536 to 546 in 61fb08a

	# Loop through projected features and examples to find best split
	# This can be parallelized for sure
	for j in range(self.proj_dims):
	# Sort labels by the jth feature
	idx = np.argsort(proj_X[:, j])
	y_sort = y_sample[idx]
	Q[1:-1, j] = np.array(
	[self.score(y_sort, i) for i in range(1, n_samples - 1)]
	)

Describe alternatives you've considered

Additional context (e.g. screenshots)