Skip to main content

Simple library to write decision trees

Project description

This is a simple library to implement Binary decision Trees.

In computer science, a binary decision diagram (BDD) or branching program is a data structure that is used to represent a Boolean function. On a more abstract level, BDDs can be considered as a compressed representation of sets or relations. Unlike other compressed representations, operations are performed directly on the compressed representation, i.e. without decompression.

A simple example of this would be the following tree: alt text

Each node has a pair of childs, one child is the one associated to its father when the function inside the father returns a true value, and the other is associated when the fathers function returns false.

Use

You can create the nodes manually as python objects like is shown in this example:

from bdt.tree import BDT
from bdt.node import Node


true_node = Node(
    'True Node'
)

false_node = Node(
    'False Node'
)

head_node = Node(
   'Head Node',
   lambda var: var < 10,
   true_child=true_node,
   false_child=false_node
)

tree = BDT(
    head_node
)

Other option is to create the tree by passing a python dictionary:

from bdt.tools import tree_from_dict


tree_dict = {
    'head': 'Head Node',

    'variables': [
        'withd',
        'height'
    ],

    'nodes': [
        {
            'name': 'Head Node',
            'function': 'withd * height < 50',
            'true_child': 'True Node',
            'false_child': 'False Node'
        },
        {
            'name': 'True Node',
            'function': 'withd * height < 25',
            'true_child': 'True True Node',
            'false_child': 'True False Node'
        },
        {
            'name': 'False Node',
            'function': 'withd * height < 100',
            'true_child': 'False True Node',
            'false_child': 'False False Node'
        },
        {
            'name': 'True True Node',
            'function': 'None',
            'true_child': 'None',
            'false_child': 'None'
        },
        {
            'name': 'True False Node',
            'function': 'None',
            'true_child': 'None',
            'false_child': 'None',
        },
        {
            'name': 'False True Node',
            'function': 'None',
            'true_child': 'None',
            'false_child': 'None'
        },
        {
            'name': 'False False Node',
            'function': 'None',
            'true_child': 'None',
            'false_child': 'None'
        },
    ]
}

tree = tree_from_dict(tree_dict)

And the final form would be to load it from a JSON file the matches the previous dictionary and load it by using:

import json

from bdt.tools import tree_from_json

json_data = open('{PATH_TO_FILE/file.json}', 'r')
tree = tree_from_json(json_data)

And the final form would be to load it from a JSON file the matches the previous dictionary and load it by using:

import json

from bdt.tools import tree_from_json

json_data = open('{PATH_TO_FILE/file.json}', 'r')
tree = tree_from_json(json_data)

To traverse the created tree yo can makeit like this:

import json

from bdt.tools import tree_from_json

json_data = open('{PATH_TO_FILE/file.json}', 'r')
tree = tree_from_json(json_data)

tree.set_parameters({
    'withd': 25,
    'height': 25
})

for node in tree:
    print node.name

The set_parameters function let you initialize the values needed to run the boolean functions inside each node.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
BDT-0.0.3.tar.gz (4.3 kB) Copy SHA256 hash SHA256 Source None Jan 16, 2018

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page