Update visualize_decision_tree to include feature names

[angela97lin]

Closes #1718. Also removes feature_names as a parameter from decision_tree_data_from_estimator, since we can extract the feature names used to fit from the estimator now.

Not sure what the best way to add testing to our codebase to ensure the output png has the right name, but here's a code snippet and the resulting image 😁

from sklearn import datasets
from evalml.pipelines.components import DecisionTreeRegressor, DecisionTreeClassifier
from evalml.model_understanding.graphs import (
    visualize_decision_tree
)

def X_y():
    X, y = datasets.make_classification(n_samples=100, n_features=20,
                                        n_informative=2, n_redundant=2, random_state=0)

    return X, y


X_b, y_b = X_y()
X_b = pd.DataFrame(X_b, columns=[f'Testing_{col}' for col in range(len(X_b[0]))])
dt = DecisionTreeClassifier()
dt.fit(X_b, y_b)
visualize_decision_tree(dt, filepath='test.png')

[codecov]

Codecov Report

Merging #1813 (de85e0f) into main (a1f6e3a) will decrease coverage by 0.1%.
The diff coverage is 100.0%.

@@            Coverage Diff            @@
##             main    #1813     +/-   ##
=========================================
- Coverage   100.0%   100.0%   -0.0%     
=========================================
  Files         252      252             
  Lines       20061    20052      -9     
=========================================
- Hits        20053    20044      -9     
  Misses          8        8             

Impacted Files	Coverage Δ
evalml/model_understanding/graphs.py	100.0% <100.0%> (ø)
evalml/tests/conftest.py	100.0% <100.0%> (ø)
...lml/tests/model_understanding_tests/test_graphs.py	100.0% <100.0%> (ø)

---

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 a1f6e3a...de85e0f. Read the comment docs.

[angela97lin]

Removing feature names parameter. Since this test already checks that the output has the feature names but now we're just grabbing them from the estimator rather than setting explicitly, no other code changes needed.

[jeremyliweishih]

LGTM. Only comment I have is maybe we can make the feature names stand out a bit (bold or italicize it?).

[angela97lin]

@jeremyliweishih That's a great suggestion! With our current implementation though, I'm not sure there's an API available to easily do this though so we might need to punt on that: https://scikit-learn.org/stable/modules/generated/sklearn.tree.export_graphviz.html#sklearn.tree.export_graphviz

[bchen1116]

Looks good!