Convert a decision tree to a table - machine-learning

Question

I'm looking for a way to convert a decision tree trained using scikit sklearn into a decision table.
I would like to know how to parse the decision tree structure to find the decisions made at each step.
Then I would like ideas on how to structure this table.
Do you know a way or have a idea to do it?

Answer 1

Building on the other answer here. The following traverses the tree in the same way but generates a pandas dataframe as an output.
import sklearn
import pandas as pd
def tree_to_df(reg_tree, feature_names):
tree_ = reg_tree.tree_
feature_name = [
feature_names[i] if i != sklearn.tree._tree.TREE_UNDEFINED else "undefined!"
for i in tree_.feature
]
def recurse(node, row, ret):
if tree_.feature[node] != sklearn.tree._tree.TREE_UNDEFINED:
name = feature_name[node]
threshold = tree_.threshold[node]
# Add rule to row and search left branch
row[-1].append(name + " <= " + str(threshold))
recurse(tree_.children_left[node], row, ret)
# Add rule to row and search right branch
row[-1].append(name + " > " + str(threshold))
recurse(tree_.children_right[node], row, ret)
else:
# Add output rules and start a new row
label = tree_.value[node]
ret.append("return " + str(label[0][0]))
row.append([])
# Initialize
rules = [[]]
vals = []
# Call recursive function with initial values
recurse(0, rules, vals)
# Convert to table and output
df = pd.DataFrame(rules).dropna(how='all')
df['Return'] = pd.Series(values)
return df

Answer 2

Here is a sample code to convert a decision tree into a "python" code. You can easily adapt it to make a table.
All you need to do is create a global variable that is a table that is the size of the number of leaves times the number of features (or feature categories) and fill it recursively
def tree_to_code(tree, feature_names, classes_names):
tree_ = tree.tree_
feature_name = [
feature_names[i] if i != _tree.TREE_UNDEFINED else "undefined!"
for i in tree_.feature
]
print( "def tree(" + ", ".join(feature_names) + "):" )
def recurse(node, depth):
indent = " " * depth
if tree_.feature[node] != _tree.TREE_UNDEFINED:
name = feature_name[node]
threshold = tree_.threshold[node]
print( indent + "if " + name + " <= " + str(threshold)+ ":" )
recurse(tree_.children_left[node], depth + 1)
print( indent + "else: # if " + name + "<=" + str(threshold) )
recurse(tree_.children_right[node], depth + 1)
else:
impurity = tree.tree_.impurity[node]
dico, label = cast_value_to_dico( tree_.value[node], classes_names )
print( indent + "# impurity=" + str(impurity) + " count_max=" + str(dico[label]) )
print( indent + "return " + str(label) )
recurse(0, 1)

Answer 3

code snippet
from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import export_text
iris = load_iris()
X = iris['data']
y = iris['target']
decision_tree = DecisionTreeClassifier(random_state=0, max_depth=2)
decision_tree = decision_tree.fit(X, y)
r = export_text(decision_tree, feature_names=iris['feature_names'])
print(r)
listt= [r]
print(listt)
#########OUTPUT###########################
|--- petal width (cm) <= 0.80
| |--- class: 0
|--- petal width (cm) > 0.80
| |--- petal width (cm) <= 1.75
| | |--- class: 1
| |--- petal width (cm) > 1.75
| | |--- class: 2