SzIProjekt/Traktorek/Natalia Wiśniewska- drzewo_decyzyjne.py

training_data = [
    #nawodnienie, kiedyNawadniano, coIleDniTrzebaNawadniac, czyMaPadac, kiedyPadalo
    ['n', 2, 3, 't', 1],
    ['s', 1, 3, 't', 1],
    ['s', 5, 2, 'n', 1],
    ['n', 3, 5, 'n', 1],
    ['s', 3, 1, 't', 2],
    ['n', 2, 4, 'n', 2],
    ['n', 4, 6, 't', 3],
    ['n', 6, 5, 't', 3],
    ['s', 1, 2, 't', 4],
    ['s', 7, 3, 'n', 5],
    ['n', 4, 4, 'n', 5],
    ['s', 5, 6, 't', 5],
    ['n', 2, 7, 't', 1],
    ['s', 5, 6, 't', 7],
    ['s', 5, 3, 'n', 7],
    ['n', 3, 2, 'n', 7],
    ['s', 3, 5, 't', 4],
    ['n', 3, 4, 'n', 4],
    ['n', 4, 3, 't', 6],
    ['n', 6, 3, 't', 6],
    ['s', 1, 4, 't', 6],
    ['s', 7, 5, 'n', 3],
    ['n', 2, 5, 'n', 3],
    ['s', 4, 6, 't', 3],
    ['s', 4, 8, 'n', 4]
]

header = ["nawodnienie", "kiedyNawadniano", "coIleDni", "czyMaPadac", "kiedyPadalo"]

def class_counts(rows):
    counts = {}
    for row in rows:
        label = row[-1]
        if label not in counts:
            counts[label] = 0
        counts[label] += 1
    return counts


def is_numeric(value):
    return isinstance(value, int) or isinstance(value, float)


class Question:
    def __init__(self, column, value):
        self.column = column
        self.value = value

    def match(self, example):
        val = example[self.column]
        if is_numeric(val):
            return val >= self.value
        else:
            return val == self.value

    def __repr__(self):
        condition = "=="
        if is_numeric(self.value):
            condition = ">="
        return "Czy %s %s %s?" % (
            header[self.column], condition, str(self.value))

def partition(rows, question):
    true_rows, false_rows = [], []
    for row in rows:
        if question.match(row):
            true_rows.append(row)
        else:
            false_rows.append(row)
    return true_rows, false_rows


def gini(rows):
    counts = class_counts(rows)
    impurity = 1
    for lbl in counts:
        prob_of_lbl = counts[lbl] / float(len(rows))
        impurity -= prob_of_lbl**2
    return impurity


def info_gain(left, right, current_uncertainty):
    p = float(len(left)) / (len(left) + len(right))
    return current_uncertainty - p * gini(left) - (1 - p) * gini(right)


def find_best_split(rows):
    best_gain = 0
    best_question = None
    current_uncertainty = gini(rows)
    n_features = len(rows[0]) - 1
    for col in range(n_features):
        values = set([row[col] for row in rows])
        for val in values:
            question = Question(col, val)
            true_rows, false_rows = partition(rows, question)
            if len(true_rows) == 0 or len(false_rows) == 0:
                continue
            gain = info_gain(true_rows, false_rows, current_uncertainty)
            if gain >= best_gain:
                best_gain, best_question = gain, question
    return best_gain, best_question


class Leaf:
    def __init__(self, rows):
        self.predictions = class_counts(rows)

class Decision_Node:
    def __init__(self,
                 question,
                 true_branch,
                 false_branch):
        self.question = question
        self.true_branch = true_branch
        self.false_branch = false_branch

def build_tree(rows):
    gain, question = find_best_split(rows)
    if gain == 0:
        return Leaf(rows)
    true_rows, false_rows = partition(rows, question)
    true_branch = build_tree(true_rows)
    false_branch = build_tree(false_rows)
    return Decision_Node(question, true_branch, false_branch)


def print_tree(node, spacing=""):
    if isinstance(node, Leaf):
        print (spacing + "Predict", node.predictions)
        return
    print (spacing + str(node.question))
    print (spacing + '--> True:')
    print_tree(node.true_branch, spacing + "  ")
    print (spacing + '--> False:')
    print_tree(node.false_branch, spacing + "  ")


my_tree = build_tree(training_data)

print_tree(my_tree)