随机森林（python）

什么是随机森林

随机 森林 是 几乎 任何 预测 问题 (甚至 非直线 部分) 的固有 选择 。 它是 一个 相对较 新 的 机器学习 的 策略 （ 在 90 年代产生于 贝尔 实验室 ) 和 它 可以 几乎用于 任何方面 。 它 属于 机器 学习 算法 一大类----- 集成学习 方法 。

集成学习

集成学习通过建立几个模型组合的来解决单一预测问题。它的工作原理是生成多个分类器/模型，各自独立地学习和作出预测。这些预测最后结合成单 预测，因此优于任何一个单分类的做出预测。

过程

在建立每一棵决策树的过程中，有两点需要注意 - 采样与完全分裂。首先是两个随机采样的过程，random forest对输入的数据要进行行、列的采样。对于行采样，采用有放回的方式，也就是在采样得到的样本集合中，可能有重复的样本。假设输入样本为N个，那么采样的样本也为N个。这样使得在训练的时候，每一棵树的输入样本都不是全部的样本，使得相对不容易出现over-fitting。然后进行列采样，从M个feature中，选择m个(m << M)。之后就是对采样之后的数据使用完全分裂的方式建立出决策树，这样决策树的某一个叶子节点要么是无法继续分裂的，要么里面的所有样本的都是指向的同一个分类。一般很多的决策树算法都一个重要的步骤 - 剪枝，但是这里不这样干，由于之前的两个随机采样的过程保证了随机性，所以就算不剪枝，也不会出现over-fitting。

按这种算法得到的随机森林中的每一棵都是很弱的，但是大家组合起来就很厉害了。我觉得可以这样比喻随机森林算法：每一棵决策树就是一个精通于某一个窄领域的专家（因为我们从M个feature中选择m让每一棵决策树进行学习），这样在随机森林中就有了很多个精通不同领域的专家，对一个新的问题（新的输入数据），可以用不同的角度去看待它，最终由各个专家，投票得到结果。

优点

• 在数据集上表现良好

• 在当前的很多数据集上，相对其他算法有着很大的优势

• 它能够处理很高维度（feature很多）的数据，并且不用做特征选择

• 在训练完后，它能够给出哪些feature比较重要

• 在创建随机森林的时候，对generlization error使用的是无偏估计

• 训练速度快

• 在训练过程中，能够检测到feature间的互相影响

• 容易做成并行化方法

• 实现比较简单

用python的sklearn包实现对kaggle上面泰坦尼克号的生存预测

#coding:utf-8
import pandas as pd
import numpy as np
import csv as csv
from sklearn.ensemble import RandomForestClassifier
train_df = pd.read_csv(r'D:\PythonDDD\shuju files\tantanic\train.csv', header=0) #没有第一条
train_df['Gender'] = train_df['Sex'].map({'female': 0, 'male': 1}).astype(int) #转化布尔值，astype实现变量类型转换
if len(train_df.Embarked[train_df.Embarked.isnull()]) > 0:#ISNULL 使用指定的替换值替换 NULL
    train_df.Embarked[train_df.Embarked.isnull()] = train_df.Embarked.dropna().mode().values#用mode众数替换空值
Ports = list(enumerate(np.unique(train_df['Embarked'])))#找出里面的第一个唯一值和他的索引，枚举变量，放进一个列表
print Ports
Ports_dict = {name: i for i, name in Ports}#前面函数，后面范围，把每种分类对应起来数值
# print Ports_dict # set up a dictionary in the form  Ports : index
train_df.Embarked = train_df.Embarked.map(lambda x: Ports_dict[x]).astype(int)#索引，用数值代表字符串对应起来
median_age = train_df['Age'].dropna().median()#中值
if len(train_df.Age[ train_df.Age.isnull()]) > 0:
    train_df.loc[ (train_df.Age.isnull()), 'Age'] = median_age#年龄中位数
train_df = train_df.drop(['Name', 'Sex', 'Ticket', 'Cabin', 'PassengerId'], axis=1)#去除不必要的属性
test_df = pd.read_csv(r'D:\PythonDDD\shuju files\tantanic\test.csv', header=0)        # Load the test file into a dataframe
test_df['Gender'] = test_df['Sex'].map({'female': 0, 'male': 1}).astype(int)
if len(test_df.Embarked[test_df.Embarked.isnull()]) > 0:
    test_df.Embarked[test_df.Embarked.isnull()] = test_df.Embarked.dropna().mode().values
test_df.Embarked = test_df.Embarked.map(lambda x: Ports_dict[x]).astype(int)
median_age = test_df['Age'].dropna().median()
if len(test_df.Age[test_df.Age.isnull()]) > 0:
    test_df.loc[(test_df.Age.isnull()), 'Age'] = median_age
if len(test_df.Fare[test_df.Fare.isnull()]) > 0:
    median_fare = np.zeros(3)#0矩阵
    for f in range(0, 3):                                              # loop 0 to 2
        median_fare[f] = test_df[ test_df.Pclass == f+1 ]['Fare'].dropna().median()
    for f in range(0, 3):                                              # loop 0 to 2
        test_df.loc[(test_df.Fare.isnull()) & (test_df.Pclass == f+1 ), 'Fare'] = median_fare[f]
ids = test_df['PassengerId'].values
test_df = test_df.drop(['Name', 'Sex', 'Ticket', 'Cabin', 'PassengerId'], axis=1)
train_data = train_df.values
test_data = test_df.values
print 'Training...'
forest = RandomForestClassifier(n_estimators=100)
# print train_data[0::,1:]
forest = forest.fit(train_data[0::, 1::], train_data[0::, 0])#特征和标签
print 'Predicting...'
# print train_data[0::, 1::]
output = forest.predict(test_data).astype(int)
predictions_file = open("D:\PythonDDD\shuju files\tantanic\myfirstforest.csv", "wb")
open_file_object = csv.writer(predictions_file)
open_file_object.writerow(["PassengerId", "Survived"])
open_file_object.writerows(zip(ids, output))
predictions_file.close()

python实现随机森林原理

#coding:utf-8
import csv
from random import seed
from random import randrange
from math import sqrt

def loadCSV(filename):#加载数据，一行行的存入列表
    dataSet = []
    with open(filename, 'r') as file:
        csvReader = csv.reader(file)
        for line in csvReader:
            dataSet.append(line)
    return dataSet

# 除了标签列，其他列都转换为float类型
def column_to_float(dataSet):
    featLen = len(dataSet[0]) - 1
    for data in dataSet:
        for column in range(featLen):
            data[column] = float(data[column].strip())

# 将数据集随机分成N块，方便交叉验证，其中一块是测试集，其他四块是训练集
def spiltDataSet(dataSet, n_folds):
    fold_size = int(len(dataSet) / n_folds)
    dataSet_copy = list(dataSet)
    dataSet_spilt = []
    for i in range(n_folds):
        fold = []
        while len(fold) < fold_size:  # 这里不能用if，if只是在第一次判断时起作用，while执行循环，直到条件不成立
            index = randrange(len(dataSet_copy))
            fold.append(dataSet_copy.pop(index))  # pop() 函数用于移除列表中的一个元素（默认最后一个元素），并且返回该元素的值。
        dataSet_spilt.append(fold)
    return dataSet_spilt

# 构造数据子集
def get_subsample(dataSet, ratio):
    subdataSet = []
    lenSubdata = round(len(dataSet) * ratio)#返回浮点数
    while len(subdataSet) < lenSubdata:
        index = randrange(len(dataSet) - 1)
        subdataSet.append(dataSet[index])
    # print len(subdataSet)
    return subdataSet

# 分割数据集
def data_spilt(dataSet, index, value):
    left = []
    right = []
    for row in dataSet:
        if row[index] < value:
            left.append(row)
        else:
            right.append(row)
    return left, right

# 计算分割代价
def spilt_loss(left, right, class_values):
    loss = 0.0
    for class_value in class_values:
        left_size = len(left)
        if left_size != 0:  # 防止除数为零
            prop = [row[-1] for row in left].count(class_value) / float(left_size)
            loss += (prop * (1.0 - prop))
        right_size = len(right)
        if right_size != 0:
            prop = [row[-1] for row in right].count(class_value) / float(right_size)
            loss += (prop * (1.0 - prop))
    return loss

# 选取任意的n个特征，在这n个特征中，选取分割时的最优特征
def get_best_spilt(dataSet, n_features):
    features = []
    class_values = list(set(row[-1] for row in dataSet))
    b_index, b_value, b_loss, b_left, b_right = 999, 999, 999, None, None
    while len(features) < n_features:
        index = randrange(len(dataSet[0]) - 1)
        if index not in features:
            features.append(index)
    # print 'features:',features
    for index in features:#找到列的最适合做节点的索引，（损失最小）
        for row in dataSet:
            left, right = data_spilt(dataSet, index, row[index])#以它为节点的，左右分支
            loss = spilt_loss(left, right, class_values)
            if loss < b_loss:#寻找最小分割代价
                b_index, b_value, b_loss, b_left, b_right = index, row[index], loss, left, right
    # print b_loss
    # print type(b_index)
    return {'index': b_index, 'value': b_value, 'left': b_left, 'right': b_right}

# 决定输出标签
def decide_label(data):
    output = [row[-1] for row in data]
    return max(set(output), key=output.count)


# 子分割，不断地构建叶节点的过程对对对
def sub_spilt(root, n_features, max_depth, min_size, depth):
    left = root['left']
    # print left
    right = root['right']
    del (root['left'])
    del (root['right'])
    # print depth
    if not left or not right:
        root['left'] = root['right'] = decide_label(left + right)
        # print 'testing'
        return
    if depth > max_depth:
        root['left'] = decide_label(left)
        root['right'] = decide_label(right)
        return
    if len(left) < min_size:
        root['left'] = decide_label(left)
    else:
        root['left'] = get_best_spilt(left, n_features)
        # print 'testing_left'
        sub_spilt(root['left'], n_features, max_depth, min_size, depth + 1)
    if len(right) < min_size:
        root['right'] = decide_label(right)
    else:
        root['right'] = get_best_spilt(right, n_features)
        # print 'testing_right'
        sub_spilt(root['right'], n_features, max_depth, min_size, depth + 1)

        # 构造决策树
def build_tree(dataSet, n_features, max_depth, min_size):
    root = get_best_spilt(dataSet, n_features)
    sub_spilt(root, n_features, max_depth, min_size, 1)
    return root
# 预测测试集结果
def predict(tree, row):
    predictions = []
    if row[tree['index']] < tree['value']:
        if isinstance(tree['left'], dict):
            return predict(tree['left'], row)
        else:
            return tree['left']
    else:
        if isinstance(tree['right'], dict):
            return predict(tree['right'], row)
        else:
            return tree['right']
            # predictions=set(predictions)
def bagging_predict(trees, row):
    predictions = [predict(tree, row) for tree in trees]
    return max(set(predictions), key=predictions.count)
# 创建随机森林
def random_forest(train, test, ratio, n_feature, max_depth, min_size, n_trees):
    trees = []
    for i in range(n_trees):
        train = get_subsample(train, ratio)#从切割的数据集中选取子集
        tree = build_tree(train, n_features, max_depth, min_size)
        # print 'tree %d: '%i,tree
        trees.append(tree)
    # predict_values = [predict(trees,row) for row in test]
    predict_values = [bagging_predict(trees, row) for row in test]
    return predict_values
# 计算准确率
def accuracy(predict_values, actual):
    correct = 0
    for i in range(len(actual)):
        if actual[i] == predict_values[i]:
            correct += 1
    return correct / float(len(actual))


if __name__ == '__main__':
    seed(1)
    dataSet = loadCSV('sonar-all-data.csv')
    column_to_float(dataSet)
    n_folds = 5
    max_depth = 15
    min_size = 1
    ratio = 1.0
    # n_features=sqrt(len(dataSet)-1)
    n_features = 15
    n_trees = 10
    folds = spiltDataSet(dataSet, n_folds)#先是切割数据集
    scores = []
    for fold in folds:
        train_set = folds[
                    :]  # 此处不能简单地用train_set=folds，这样用属于引用,那么当train_set的值改变的时候，folds的值也会改变，所以要用复制的形式。（L[:]）能够复制序列，D.copy() 能够复制字典，list能够生成拷贝 list(L)
        train_set.remove(fold)#选好训练集
        # print len(folds)
        train_set = sum(train_set, [])  # 将多个fold列表组合成一个train_set列表
        # print len(train_set)
        test_set = []
        for row in fold:
            row_copy = list(row)
            row_copy[-1] = None
            test_set.append(row_copy)
            # for row in test_set:
            # print row[-1]
        actual = [row[-1] for row in fold]
        predict_values = random_forest(train_set, test_set, ratio, n_features, max_depth, min_size, n_trees)
        accur = accuracy(predict_values, actual)
        scores.append(accur)
    print ('Trees is %d' % n_trees)
    print ('scores:%s' % scores)
    print ('mean score:%s' % (sum(scores) / float(len(scores))))