Feature lineage visualization

[frances-h]

Add graph_feature function which takes in a feature and returns a graph demonstrating how the feature was generated:

Closes #937

[codecov]

Codecov Report

Merging #1032 into master will increase coverage by 0.04%.
The diff coverage is 99.44%.

@@            Coverage Diff             @@
##           master    #1032      +/-   ##
==========================================
+ Coverage   98.30%   98.35%   +0.04%     
==========================================
  Files         124      126       +2     
  Lines       12695    13052     +357     
==========================================
+ Hits        12480    12837     +357     
  Misses        215      215              

Impacted Files	Coverage Δ
featuretools/feature_base/feature_visualizer.py	98.52% <98.52%> (ø)
featuretools/__init__.py	82.35% <100.00%> (ø)
featuretools/feature_base/api.py	100.00% <100.00%> (ø)
...s/tests/primitive_tests/test_feature_visualizer.py	100.00% <100.00%> (ø)
featuretools/synthesis/deep_feature_synthesis.py	97.83% <0.00%> (+0.48%)	⬆️

---

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 f21606a...00dfffe. Read the comment docs.

[thehomebrewnerd]

This looks good to me. I tested with quite a few different feature types and the output matched my expectations.

The only suggestion I have is to maybe add a mention of this capability to the documentation as this is a nice way to understand more about your features. Not sure exactly, where would be the best place but maybe here: Deep Feature Synthesis.

[rwedge]

Looks good to merge once it's up to date!