#%%% : Visualizing Decision Trees
#You can use Scikit-learn's export_graphviz function for display the tree within a Jupyter notebook. For plotting tree, you also need to install graphviz and pydotplus.
#pip install graphviz
#pip install pydotplus
#export_graphviz function converts decision tree classifier into dot file and pydotplus convert this dot file to png or displayable form
from sklearn.tree import export_graphviz
from sklearn.externals.six import StringIO
from IPython.display import Image
import pydotplus
dot_data = StringIO()
export_graphviz(clf, out_file=dot_data, filled=True, rounded=True, special_characters=True,feature_names = feature_cols, class_names=['0', '1'])
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
graph.write_png('diabetes.png')
Image(graph.create_png())
graph = Source(tree.export_graphviz(estimator, out_file=None , feature_names=labels, class_names=['0', '1', '2'] , filled = True))
display(SVG(graph.pipe(format='svg')))
#%%%%
Optimizing Decision Tree Performance
criterion : optional (default=”gini”) or Choose attribute selection measure: This parameter allows us to use the different-different attribute selection measure. Supported criteria are “gini” for the Gini index and “entropy” for the information gain.
splitter : string, optional (default=”best”) or Split Strategy: This parameter allows us to choose the split strategy. Supported strategies are “best” to choose the best split and “random” to choose the best random split.
max_depth : int or None, optional (default=None) or Maximum Depth of a Tree: The maximum depth of the tree. If None, then nodes are expanded until all the leaves contain less than min_samples_split samples. The higher value of maximum depth causes overfitting, and a lower value causes underfitting (Source).
#%%%%
# Create Decision Tree classifer object
