Create DTree-Classifier.py

This commit is contained in:
op07n 2020-01-21 16:32:46 +01:00 committed by GitHub
parent 437f78836c
commit 1af747769d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 141 additions and 0 deletions

141
apps/DTree-Classifier.py Normal file
View File

@ -0,0 +1,141 @@
# import streamlit as st
import pandas as pd
def unique_values(rows, col):
return set([row[col] for row in rows])
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 f'Is {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 + ' ')
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
def predict(data, header):
header = header
tree = build_tree(data)
results = {}
for row in data:
# print(f'Actual: {row[-1]}. Predicted: {print_leaf(classify(row, tree))}')
results[row[-1]] = print_leaf(classify(row, tree))
return results, tree
# results, tree = predict(data, header)
# print(results)
# print_tree(tree)