Increasing efficiency in Ensemble Selection

[franchuterivera]

• Added checking for ensemble selection -- this was created and tested with the old code, to make sure new enhancements do not break ensemble selection
• Removed unnecessary code in ensemble selection as well as unnecessary computations. In testing with just (10, 10000, 1) predictions this saves 7ms in average which is expected to scale with more (predictions, sample_points, target_columns)

[codecov]

Codecov Report

Merging #1040 (c80fe9d) into development (9f677e1) will decrease coverage by 0.04%.
The diff coverage is 100.00%.

@@               Coverage Diff               @@
##           development    #1040      +/-   ##
===============================================
- Coverage        85.52%   85.48%   -0.05%     
===============================================
  Files              127      127              
  Lines            10123    10139      +16     
===============================================
+ Hits              8658     8667       +9     
- Misses            1465     1472       +7     

Impacted Files	Coverage Δ
autosklearn/ensembles/ensemble_selection.py	67.12% <100.00%> (-1.30%)	⬇️
autosklearn/util/logging_.py	87.30% <0.00%> (-7.01%)	⬇️
...eline/components/feature_preprocessing/fast_ica.py	91.30% <0.00%> (-6.53%)	⬇️
...tosklearn/metalearning/metafeatures/metafeature.py	76.69% <0.00%> (-0.23%)	⬇️
autosklearn/evaluation/abstract_evaluator.py	88.44% <0.00%> (-0.18%)	⬇️
autosklearn/metalearning/metalearning/meta_base.py	87.83% <0.00%> (-0.17%)	⬇️
autosklearn/smbo.py	82.53% <0.00%> (-0.11%)	⬇️
.../metalearning/metalearning/kNearestDatasets/kND.py	94.04% <0.00%> (-0.08%)	⬇️
...ning/optimizers/metalearn_optimizer/metalearner.py	96.10% <0.00%> (-0.05%)	⬇️
...osklearn/metalearning/metafeatures/metafeatures.py	94.70% <0.00%> (-0.02%)	⬇️
... and 12 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 9f677e1...c80fe9d. Read the comment docs.