Create basic tests for query strategy

[jeremykubica]

Create tests for the random and uncertainty based sampling methods. Does not create anything for QBD because I'm still trying to understand how those should work.

[github-actions]

Before [051369d]	After [6f9f52b]	Ratio	Benchmark (Parameter)
failed	failed	n/a	benchmarks.peakmem_learn_loop('KNN')
failed	failed	n/a	benchmarks.peakmem_learn_loop('RandomForest')
172±2ms	175±3ms	1.02	benchmarks.time_learn_loop('KNN', 'UncSampling')
2.62±0.01s	2.67±0.04s	1.02	benchmarks.time_learn_loop('RandomForest', 'RandomSampling')
170±0.9ms	170±0.8ms	1.00	benchmarks.time_learn_loop('KNN', 'RandomSampling')
2.67±0.01s	2.66±0.01s	1.00	benchmarks.time_learn_loop('RandomForest', 'UncSampling')
139±1ms	138±1ms	0.99	benchmarks.time_feature_creation

Click here to view all benchmarks.

[AmandaWasserman]

Not totally sure what this function is doing, but should this line be [0.5, 0.0, 0.5] instead of[0.5, 0.0, 5.0]?

[AmandaWasserman]

Okay, I think I understand now. Shouldn't change the results, but would be good to fix

[jeremykubica]

Good catch. I correct this.