Sklearn常用集成算法实践

前言

用Sklearn常用的Ensemble算法对当当热销书评论进行分类实践。

关于集成算法概念可以看这篇文章 总结Bootstraping、Bagging和Boosting

先看一下这篇文章朴素贝叶斯分类算法实践，本文主要还是用当当评论数据做的分析。关于代码部分一些细节在朴素贝叶斯分类算法实践已经详细的解释了。

• 完整代码查看：https://github.com/xhades/rates_classify/tree/master/rates_classify
• 训练数据下载地址：https://pan.baidu.com/s/1kVOS39l

正文

RandomForest

sklearn RandomForestClassifier文档地址

代码

import numpy as np
from numpy import array, argmax, reshape
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
import pickle
from sklearn.ensemble import RandomForestClassifier as RDF
np.set_printoptions(threshold=np.inf)


# 训练集测试集 3/7分割
def train(xFile, yFile):
    with open(xFile, "rb") as file_r:
        X = pickle.load(file_r)

    X = reshape(X, (212841, -1))  # reshape一下 （212841, 30*128）
    # 读取label数据，并且encodig
    with open(yFile, "r") as yFile_r:
        labelLines = [_.strip("\n") for _ in yFile_r.readlines()]
    values = array(labelLines)
    labelEncoder = LabelEncoder()
    integerEncoded = labelEncoder.fit_transform(values)
    integerEncoded = integerEncoded.reshape(len(integerEncoded), 1)
    # print(integerEncoded)

    # 获得label  编码
    Y = integerEncoded.reshape(212841, )
    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.3, random_state=42)

    # 随机森林分类器
    clf = RDF(criterion="gini")
    # criterion 可以使用"gini"或者"entropy"，前者代表基尼系数，后者代表信息增益。一般说使用默认的基尼系数"gini"就可以了，即CART算法。除非你更喜欢类似ID3, C4.5的最优特征选择方法。

    clf.fit(X_train, Y_train)

    # 测试数据
    predict = clf.predict(X_test)
    count = 0
    for p, t in zip(predict, Y_test):
        if p == t:
            count += 1
    print("RandomForest Accuracy is:", count/len(Y_test))


if __name__ == "__main__":
    xFile = "Res/char_embedded.pkl"
    yFile = "data/label.txt"
    print("Start Training.....")
    train(xFile, yFile)
    print("End.....")

主要的参数说明

• criterion 可以使用"gini"或者"entropy"，前者代表基尼系数，后者代表信息增益。一般说使用默认的基尼系数"gini"就可以了，即CART算法。除非你更喜欢类似ID3, C4.5的最优特征选择方法。
• 其他参数都用默认，以后再更新 =。=

结果

Start Training.....
RandomForest Accuracy is: 0.9258453009255634
End.....

最终结果大概92.6%左右的准确率

梯度提升算法GradientBoostingClassifier

sklearn GradientBoostingClassifier 文档地址

Boosting不断串行地迭代弱学习器最终形成一个强学习器，这点和Bagging并行的 方式不同，所以在用梯度提升算法时耗时非常长

代码

import numpy as np
from numpy import array, argmax, reshape
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
import pickle
from sklearn.ensemble import GradientBoostingClassifier as GBC

np.set_printoptions(threshold=np.inf)


# 训练集测试集 3/7分割
def train(xFile, yFile):
    with open(xFile, "rb") as file_r:
        X = pickle.load(file_r)

    X = reshape(X, (212841, -1))  # reshape一下 （212841, 30*128）
    # 读取label数据，并且Encoding
    with open(yFile, "r") as yFile_r:
        labelLines = [_.strip("\n") for _ in yFile_r.readlines()]
    values = array(labelLines)
    labelEncoder = LabelEncoder()
    integerEncoded = labelEncoder.fit_transform(values)
    integerEncoded = integerEncoded.reshape(len(integerEncoded), 1)
    # print(integerEncoded)

    # 获得label 编码
    Y = integerEncoded.reshape(212841, )
    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.3, random_state=42)

    # 梯度提升分类器
    clf = GBC(loss="deviance", subsample=0.8, criterion="friedman_mse")

    clf.fit(X_train, Y_train)

    # 测试数据
    predict = clf.predict(X_test)
    count = 0
    for p, t in zip(predict, Y_test):
        if p == t:
            count += 1
    print("GradientBoosting  Accuracy is:", count/len(Y_test))


if __name__ == "__main__":
    xFile = "Res/char_embedded.pkl"
    yFile = "data/label.txt"
    print("Start Training.....")
    train(xFile, yFile)
    print("End.....")

主要的参数说明

• subsample 数据随机抽样对决策树进行训练，这个参数设置比1小即可，具体数值需要在“调参”过程中发现最优
• 其他参数日后再(tai)整(lan)理(le)
• 源码中的默认参数设置

    _SUPPORTED_LOSS = ('deviance', 'exponential')

    def __init__(self, loss='deviance', learning_rate=0.1, n_estimators=100,
                 subsample=1.0, criterion='friedman_mse', min_samples_split=2,
                 min_samples_leaf=1, min_weight_fraction_leaf=0.,
                 max_depth=3, min_impurity_split=1e-7, init=None,
                 random_state=None, max_features=None, verbose=0,
                 max_leaf_nodes=None, warm_start=False,
                 presort='auto'):

        super(GradientBoostingClassifier, self).__init__(
            loss=loss, learning_rate=learning_rate, n_estimators=n_estimators,
            criterion=criterion, min_samples_split=min_samples_split,
            min_samples_leaf=min_samples_leaf,
            min_weight_fraction_leaf=min_weight_fraction_leaf,
            max_depth=max_depth, init=init, subsample=subsample,
            max_features=max_features,
            random_state=random_state, verbose=verbose,
            max_leaf_nodes=max_leaf_nodes,
            min_impurity_split=min_impurity_split,
            warm_start=warm_start,
            presort=presort)

结果

Start Training.....
GradientBoosting  Accuracy is: 0.8833727467777551
End.....

最终准确率88.3%左右