SI2020/drzewaDecyzyjne.py

165 lines
4.5 KiB
Python
Raw Normal View History

2020-06-06 10:00:53 +02:00
training_data = [
#zyznosc, nawodnienie, cien, kwasowosc
['z', 'n', 's', 'z', 1],
['z', 'n', 's', 'n', 1],
['j', 'n', 's', 'z', 1],
['z', 's', 's', 'n', 1],
['j', 'n', 'c', 'n', 1],
['z', 'n', 's', 'k', 1],
['z', 'n', 'c', 'k', 2],
['z', 's', 's', 'k', 2],
['z', 's', 'c', 'k', 2],
['j', 'n', 's', 'k', 2],
['z', 's', 'c', 'z', 3],
['j', 'n', 's', 'n', 3]
]
header = ["zyznosc", "nawodnienie", "cien", "kwasowosc", "wybor"]
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)
def classify(row, node):
if isinstance(node, Leaf):
return node.predictions
if node.question.match(row):
return classify(row, node.true_branch)
else:
return classify(row, node.false_branch)
def print_leaf(counts):
total = sum(counts.values()) * 1.0
probs = {}
for lbl in counts.keys():
probs[lbl] = str(int(counts[lbl] / total * 100)) + "%"
return probs
with open( 'dane.txt', "r" ) as f:
testing_data = [ line.split() for line in f ]
file = open("decyzje.txt", "w")
file.write("")
file.close()
for row in testing_data:
pom = print_leaf(classify(row, my_tree))
f = open("decyzje.txt", "a")
if pom == {1: '100%'}:
f.write("B\n")
if pom == {2: '100%'}:
f.write("Z\n")
if pom == {3: '100%'}:
f.write(".\n")
f.close()