python实现随机森林_从头开始：用Python实现随机森林算法

从头开始：用Python实现随机森林算法

print('Mean Accuracy: %.3f%%' % (sum(scores)/float(len(scores))))

print('Scores: %s' % scores)

print('Trees: %d' % n_trees)

scores = evaluate_algorithm(dataset, random_forest, n_folds, max_depth, min_size, sample_size, n_trees, n_features)

for n_trees in [1, 5, 10]:

n_features = int(sqrt(len(dataset[0])-1))

sample_size = 1.0

min_size = 1

max_depth = 10

n_folds = 5

# evaluate algorithm

str_column_to_int(dataset, len(dataset[0])-1)

# convert class column to integers

str_column_to_float(dataset, i)

for i in range(0, len(dataset[0])-1):

# convert string attributes to integers

dataset = load_csv(filename)

filename = 'sonar.all-data.csv'

# load and prepare data

seed(1)

# Test the random forest algorithm

return(predictions)

predictions = [bagging_predict(trees, row) for row in test]

trees.append(tree)

tree = build_tree(sample, max_depth, min_size, n_features)

sample = subsample(train, sample_size)

for i in range(n_trees):

trees = list()

def random_forest(train, test, max_depth, min_size, sample_size, n_trees, n_features):

# Random Forest Algorithm

return max(set(predictions), key=predictions.count)

predictions = [predict(tree, row) for tree in trees]

def bagging_predict(trees, row):

# Make a prediction with a list of bagged trees

return sample

sample.append(dataset[index])

index = randrange(len(dataset))

while len(sample) < n_sample:

n_sample = round(len(dataset) * ratio)

sample = list()

def subsample(dataset, ratio):

# Create a random subsample from the dataset with replacement

return node['right']

else:

return predict(node['right'], row)

if isinstance(node['right'], dict):

else:

return node['left']

else:

return predict(node['left'], row)

if isinstance(node['left'], dict):

if row[node['index']] < node['value']:

def predict(node, row):

# Make a prediction with a decision tree

return root

split(root, max_depth, min_size, n_features, 1)

root = get_split(dataset, n_features)

def build_tree(train, max_depth, min_size, n_features):

# Build a decision tree

split(node['right'], max_depth, min_size, n_features, depth+1)

node['right'] = get_split(right, n_features)

else:

node['right'] = to_terminal(right)

if len(right) <= min_size:

# process right child

split(node['left'], max_depth, min_size, n_features, depth+1)

node['left'] = get_split(left, n_features)

else:

node['left'] = to_terminal(left)

if len(left) <= min_size:

# process left child

return

node['left'], node['right'] = to_terminal(left), to_terminal(right)

if depth >= max_depth:

# check for max depth

return

node['left'] = node['right'] = to_terminal(left + right)

if not left or not right:

# check for a no split

del(node['groups'])

left, right = node['groups']

def split(node, max_depth, min_size, n_features, depth):

# Create child splits for a node or make terminal

return max(set(outcomes), key=outcomes.count)

outcomes = [row[-1] for row in group]

def to_terminal(group):

# Create a terminal node value

return {'index':b_index, 'value':b_value, 'groups':b_groups}

b_index, b_value, b_score, b_groups = index, row[index], gini, groups

if gini < b_score:

gini = gini_index(groups, class_values)

groups = test_split(index, row[index], dataset)

for row in dataset:

for index in features:

features.append(index)

if index not in features:

index = randrange(len(dataset[0])-1)

while len(features) < n_features:

features = list()

b_index, b_value, b_score, b_groups = 999, 999, 999, None

class_values = list(set(row[-1] for row in dataset))

def get_split(dataset, n_features):

# Select the best split point for a dataset

return gini

gini += (proportion * (1.0 - proportion))

proportion = [row[-1] for row in group].count(class_value) / float(size)

continue

if size == 0:

size = len(group)

for group in groups:

for class_value in class_values:

gini = 0.0

def gini_index(groups, class_values):

# Calculate the Gini index for a split dataset

return left, right

right.append(row)

else:

left.append(row)

if row[index] < value:

for row in dataset:

left, right = list(), list()

def test_split(index, value, dataset):

# Split a dataset based on an attribute and an attribute value

return scores

scores.append(accuracy)

accuracy = accuracy_metric(actual, predicted)

actual = [row[-1] for row in fold]

predicted = algorithm(train_set, test_set, *args)

row_copy[-1] = None

test_set.append(row_copy)

row_copy = list(row)

for row in fold:

test_set = list()

train_set = sum(train_set, [])

train_set.remove(fold)

train_set = list(folds)

for fold in folds:

scores = list()

folds = cross_validation_split(dataset, n_folds)

def evaluate_algorithm(dataset, algorithm, n_folds, *args):

# Evaluate an algorithm using a cross validation split

return correct / float(len(actual)) * 100.0

correct += 1

if actual[i] == predicted[i]:

for i in range(len(actual)):

correct = 0

def accuracy_metric(actual, predicted):

# Calculate accuracy percentage

return dataset_split

dataset_split.append(fold)

fold.append(dataset_copy.pop(index))

index = randrange(len(dataset_copy))

while len(fold) < fold_size:

fold = list()

for i in range(n_folds):

fold_size = len(dataset) / n_folds

dataset_copy = list(dataset)

dataset_split = list()

def cross_validation_split(dataset, n_folds):

# Split a dataset into k folds

return lookup

row[column] = lookup[row[column]]

for row in dataset:

lookup[value] = i

for i, value in enumerate(unique):

lookup = dict()

unique = set(class_values)

class_values = [row[column] for row in dataset]

def str_column_to_int(dataset, column):

# Convert string column to integer

row[column] = float(row[column].strip())

for row in dataset:

def str_column_to_float(dataset, column):

# Convert string column to float

return dataset

dataset.append(row)

continue

if not row:

for row in csv_reader:

csv_reader = reader(file)

with open(filename, 'r') as file:

dataset = list()

def load_csv(filename):

# Load a CSV file

from math import sqrt

from csv import reader

from random import randrange

from random import seed

# Random Forest Algorithm on Sonar Dataset

来源: http://www.36dsj.com/archives/93623