鸢尾花分类

第1关:什么是决策树

1.AB

2.B

第2关:信息熵与信息增益

python 复制代码
import numpy as np


def calcInfoGain(feature, label, index):
    '''
    计算信息增益
    :param feature:测试用例中字典里的feature,类型为ndarray
    :param label:测试用例中字典里的label,类型为ndarray
    :param index:测试用例中字典里的index,即feature部分特征列的索引。该索引指的是feature中第几个特征,如index:0表示使用第一个特征来计算信息增益。
    :return:信息增益,类型float
    '''
    # 计算熵
    def calcInfoEntropy(feature, label):
        '''
        计算信息熵
        :param feature:数据集中的特征,类型为ndarray
        :param label:数据集中的标签,类型为ndarray
        :return:信息熵,类型float
        '''
        label_set = set(label)#创建一个无序不重复的元素集
        result = 0
        #统计不同标签各自的数量(一般为0和1)
        for l in label_set:
            count = 0
            for j in range(len(label)):
                if label[j] == l:
                    count += 1
            # 计算标签在数据集中出现的概率
            p = count / len(label)
            # 计算熵
            result -= p * np.log2(p)
        return result
    # 计算条件熵
    def calcHDA(feature, label, index, value):
        '''
        计算信息熵
        :param feature:数据集中的特征,类型为ndarray
        :param label:数据集中的标签,类型为ndarray
        :param index:需要使用的特征列索引,类型为int
        :param value:index所表示的特征列中需要考察的特征值,类型为int
        :return:信息熵,类型float
        '''
        count = 0
        # sub_feature和sub_label表示根据特征列和特征值
        #分割出的子数据集中的特征和标签
        sub_feature = []
        sub_label = []
        for i in range(len(feature)):
            if feature[i][index] == value:
                count += 1
                sub_feature.append(feature[i])
                sub_label.append(label[i])
        pHA = count / len(feature)
        e = calcInfoEntropy(sub_feature, sub_label)
        return pHA * e
    #######请计算信息增益############
    #*********** Begin ***********#
    values = []#定义一个列表存放index列,即特征列的所有特征
    for i in range(len(feature)):
        values.append(feature[i][index])
    values_list = set(values)#创建一个无序不重复的元素集
    g = calcInfoEntropy(feature, label)#计算总熵
    for i in values_list:
        g -= calcHDA(feature, label, index, i)#总熵-每个特征的条件熵
    return g#得到信息增益
    #*********** End *************#

第3关:使用ID3算法构建决策树

python 复制代码
import numpy as np
class DecisionTree(object):
    def __init__(self):
        #决策树模型
        self.tree = {}
    def calcInfoGain(self, feature, label, index):
        '''
        计算信息增益
        :param feature:测试用例中字典里的feature,类型为ndarray
        :param label:测试用例中字典里的label,类型为ndarray
        :param index:测试用例中字典里的index,即feature部分特征列的索引。该索引指的是feature中第几个特征,如index:0表示使用第一个特征来计算信息增益。
        :return:信息增益,类型float
        '''
        # 计算熵
        def calcInfoEntropy(label):
            '''
            计算信息熵
            :param label:数据集中的标签,类型为ndarray
            :return:信息熵,类型float
            '''
            label_set = set(label)
            result = 0
            for l in label_set:
                count = 0
                for j in range(len(label)):
                    if label[j] == l:
                        count += 1
                # 计算标签在数据集中出现的概率
                p = count / len(label)
                # 计算熵
                result -= p * np.log2(p)
            return result
        # 计算条件熵
        def calcHDA(feature, label, index, value):
            '''
            计算信息熵
            :param feature:数据集中的特征,类型为ndarray
            :param label:数据集中的标签,类型为ndarray
            :param index:需要使用的特征列索引,类型为int
            :param value:index所表示的特征列中需要考察的特征值,类型为int
            :return:信息熵,类型float
            '''
            count = 0
            # sub_feature和sub_label表示根据特征列和特征值分割出的子数据集中的特征和标签
            sub_feature = []
            sub_label = []
            for i in range(len(feature)):
                if feature[i][index] == value:
                    count += 1
                    sub_feature.append(feature[i])
                    sub_label.append(label[i])
            pHA = count / len(feature)
            e = calcInfoEntropy(sub_label)
            return pHA * e
        base_e = calcInfoEntropy(label)
        f = np.array(feature)
        # 得到指定特征列的值的集合
        f_set = set(f[:, index])
        sum_HDA = 0
        # 计算条件熵
        for value in f_set:
            sum_HDA += calcHDA(feature, label, index, value)
        # 计算信息增益
        return base_e - sum_HDA
    # 获得信息增益最高的特征
    def getBestFeature(self, feature, label):
        max_infogain = 0
        best_feature = 0
        for i in range(len(feature[0])):
            infogain = self.calcInfoGain(feature, label, i)
            if infogain > max_infogain:
                max_infogain = infogain
                best_feature = i
        return best_feature
    def createTree(self, feature, label):
        # 样本里都是同一个label没必要继续分叉了
        if len(set(label)) == 1:
            return label[0]
        # 样本中只有一个特征或者所有样本的特征都一样的话就看哪个label的票数高
        if len(feature[0]) == 1 or len(np.unique(feature, axis=0)) == 1:
            vote = {}
            for l in label:
                if l in vote.keys():
                    vote[l] += 1
                else:
                    vote[l] = 1
            max_count = 0
            vote_label = None
            for k, v in vote.items():
                if v > max_count:
                    max_count = v
                    vote_label = k
            return vote_label
        # 根据信息增益拿到特征的索引
        best_feature = self.getBestFeature(feature, label)
        tree = {best_feature: {}}
        f = np.array(feature)
        # 拿到bestfeature的所有特征值
        f_set = set(f[:, best_feature])
        # 构建对应特征值的子样本集sub_feature, sub_label
        for v in f_set:
            sub_feature = []
            sub_label = []
            for i in range(len(feature)):
                if feature[i][best_feature] == v:
                    sub_feature.append(feature[i])
                    sub_label.append(label[i])
            # 递归构建决策树
            tree[best_feature][v] = self.createTree(sub_feature, sub_label)
        return tree
    def fit(self, feature, label):
        '''
        :param feature: 训练集数据,类型为ndarray
        :param label:训练集标签,类型为ndarray
        :return: None
        '''
        #************* Begin ************#
        self.tree = self.createTree(feature, label)
        #************* End **************#
    def predict(self, feature):
        '''
        :param feature:测试集数据,类型为ndarray
        :return:预测结果,如np.array([0, 1, 2, 2, 1, 0])
        '''
        #************* Begin ************#
        result = []
        def classify(tree, feature):
            if not isinstance(tree, dict):
                return tree
            t_index, t_value = list(tree.items())[0]
            f_value = feature[t_index]
            if isinstance(t_value, dict):
                classLabel = classify(tree[t_index][f_value], feature)
                return classLabel
            else:
                return t_value
        for f in feature:
            result.append(classify(self.tree, f))
        return np.array(result)

第4关:信息增益率

python 复制代码
import numpy as np

def calcInfoGain(feature, label, index):
    '''
    计算信息增益
    :param feature:测试用例中字典里的feature,类型为ndarray
    :param label:测试用例中字典里的label,类型为ndarray
    :param index:测试用例中字典里的index,即feature部分特征列的索引。该索引指的是feature中第几个特征,如index:0表示使用第一个特征来计算信息增益。
    :return:信息增益,类型float
    '''
    # 计算熵
    def calcInfoEntropy(label):
        '''
        计算信息熵
        :param label:数据集中的标签,类型为ndarray
        :return:信息熵,类型float
        '''

        label_set = set(label)
        result = 0
        for l in label_set:
            count = 0
            for j in range(len(label)):
                if label[j] == l:
                    count += 1
            # 计算标签在数据集中出现的概率
            p = count / len(label)
            # 计算熵
            result -= p * np.log2(p)
        return result

    # 计算条件熵
    def calcHDA(feature, label, index, value):
        '''
        计算信息熵
        :param feature:数据集中的特征,类型为ndarray
        :param label:数据集中的标签,类型为ndarray
        :param index:需要使用的特征列索引,类型为int
        :param value:index所表示的特征列中需要考察的特征值,类型为int
        :return:信息熵,类型float
        '''
        count = 0
        # sub_label表示根据特征列和特征值分割出的子数据集中的标签
        sub_label = []
        for i in range(len(feature)):
            if feature[i][index] == value:
                count += 1
                sub_label.append(label[i])
        pHA = count / len(feature)
        e = calcInfoEntropy(sub_label)
        return pHA * e

    base_e = calcInfoEntropy(label)
    f = np.array(feature)
    # 得到指定特征列的值的集合,:表示获取所有行
    f_set = set(f[:, index])#将不重复的特征值获取出来(比如:男,女)
    sum_HDA = 0
    # 计算条件熵
    for value in f_set:
        sum_HDA += calcHDA(feature, label, index, value)
    # 计算信息增益
    return base_e - sum_HDA


def calcInfoGainRatio(feature, label, index):
    '''
    计算信息增益率
    :param feature:测试用例中字典里的feature,类型为ndarray
    :param label:测试用例中字典里的label,类型为ndarray
    :param index:测试用例中字典里的index,即feature部分特征列的索引。该索引指的是feature中第几个特征,如index:0表示使用第一个特征来计算信息增益。
    :return:信息增益率,类型float
    '''

    #********* Begin *********#
    up = calcInfoGain(feature, label, index)#信息增益率的分子
    #定义一个方法求分母中某个类型的个数(如求当v=1时表示性别为男的)
    def dcon(feature,value):
        s = 0
        for i in range(len(feature)):
            if feature[i][index] == value:
                s += 1
            else:
                pass
        return s      
    
    down = 0
    #取出特征值该列所有数据
    values = []
    for i in range(len(feature)):
        values.append(feature[i][index])
    values_set = set(values)#使用set()过滤重复值,得到特征值列中所有类型(如性别中男和女)
    #循环递归求出分母
    for value in values_set:
        down -= (dcon(feature,value)/len(feature)) * np.log2(dcon(feature,value)/len(feature))
    #求得信息增益率
    gain = up/down
    return gain
    #********* End *********#

第5关:基尼系数

python 复制代码
import numpy as np
def gini_index(label):
    unique_label = list(set(label))
    gini = 1
    for  i in unique_label:
        p = np.sum(label == i)/len(label)
        gini -=p**2
    return gini 
def calcGini(feature, label, index):
    '''
    计算基尼系数
    :param feature:测试用例中字典里的feature,类型为ndarray
    :param label:测试用例中字典里的label,类型为ndarray
    :param index:测试用例中字典里的index,即feature部分特征列的索引。该索引指的是feature中第几个特征,如index:0表示使用第一个特征来计算信息增益。
    :return:基尼系数,类型float
    '''
 
    #********* Begin *********#
    unique_value = list(set(feature[:, index]))
    gini2 = 0
    for value in unique_value:
        len_v = np.sum(feature[:, index] == value)
        gini2 += (len_v/len(feature))*gini_index(label[feature[:, index] == value])
    return gini2
    #********* End *********#

第6关:预剪枝与后剪枝

python 复制代码
import numpy as np
from copy import deepcopy
class DecisionTree(object):
    def __init__(self):
        #决策树模型
        self.tree = {}
    def calcInfoGain(self, feature, label, index):
        '''
        计算信息增益
        :param feature:测试用例中字典里的feature,类型为ndarray
        :param label:测试用例中字典里的label,类型为ndarray
        :param index:测试用例中字典里的index,即feature部分特征列的索引。该索引指的是feature中第几个特征,如index:0表示使用第一个特征来计算信息增益。
        :return:信息增益,类型float
        '''
        # 计算熵
        def calcInfoEntropy(feature, label):
            '''
            计算信息熵
            :param feature:数据集中的特征,类型为ndarray
            :param label:数据集中的标签,类型为ndarray
            :return:信息熵,类型float
            '''
            label_set = set(label)
            result = 0
            for l in label_set:
                count = 0
                for j in range(len(label)):
                    if label[j] == l:
                        count += 1
                # 计算标签在数据集中出现的概率
                p = count / len(label)
                # 计算熵
                result -= p * np.log2(p)
            return result
        # 计算条件熵
        def calcHDA(feature, label, index, value):
            '''
            计算信息熵
            :param feature:数据集中的特征,类型为ndarray
            :param label:数据集中的标签,类型为ndarray
            :param index:需要使用的特征列索引,类型为int
            :param value:index所表示的特征列中需要考察的特征值,类型为int
            :return:信息熵,类型float
            '''
            count = 0
            # sub_feature和sub_label表示根据特征列和特征值分割出的子数据集中的特征和标签
            sub_feature = []
            sub_label = []
            for i in range(len(feature)):
                if feature[i][index] == value:
                    count += 1
                    sub_feature.append(feature[i])
                    sub_label.append(label[i])
            pHA = count / len(feature)
            e = calcInfoEntropy(sub_feature, sub_label)
            return pHA * e
        base_e = calcInfoEntropy(feature, label)
        f = np.array(feature)
        # 得到指定特征列的值的集合
        f_set = set(f[:, index])
        sum_HDA = 0
        # 计算条件熵
        for value in f_set:
            sum_HDA += calcHDA(feature, label, index, value)
        # 计算信息增益
        return base_e - sum_HDA
    # 获得信息增益最高的特征
    def getBestFeature(self, feature, label):
        max_infogain = 0
        best_feature = 0
        for i in range(len(feature[0])):
            infogain = self.calcInfoGain(feature, label, i)
            if infogain > max_infogain:
                max_infogain = infogain
                best_feature = i
        return best_feature
    # 计算验证集准确率
    def calc_acc_val(self, the_tree, val_feature, val_label):
        result = []
        def classify(tree, feature):
            if not isinstance(tree, dict):
                return tree
            t_index, t_value = list(tree.items())[0]
            f_value = feature[t_index]
            if isinstance(t_value, dict):
                classLabel = classify(tree[t_index][f_value], feature)
                return classLabel
            else:
                return t_value
        for f in val_feature:
            result.append(classify(the_tree, f))
        result = np.array(result)
        return np.mean(result == val_label)
    def createTree(self, train_feature, train_label):
        # 样本里都是同一个label没必要继续分叉了
        if len(set(train_label)) == 1:
            return train_label[0]
        # 样本中只有一个特征或者所有样本的特征都一样的话就看哪个label的票数高
        if len(train_feature[0]) == 1 or len(np.unique(train_feature, axis=0)) == 1:
            vote = {}
            for l in train_label:
                if l in vote.keys():
                    vote[l] += 1
                else:
                    vote[l] = 1
            max_count = 0
            vote_label = None
            for k, v in vote.items():
                if v > max_count:
                    max_count = v
                    vote_label = k
            return vote_label
        # 根据信息增益拿到特征的索引
        best_feature = self.getBestFeature(train_feature, train_label)
        tree = {best_feature: {}}
        f = np.array(train_feature)
        # 拿到bestfeature的所有特征值
        f_set = set(f[:, best_feature])
        # 构建对应特征值的子样本集sub_feature, sub_label
        for v in f_set:
            sub_feature = []
            sub_label = []
            for i in range(len(train_feature)):
                if train_feature[i][best_feature] == v:
                    sub_feature.append(train_feature[i])
                    sub_label.append(train_label[i])
            # 递归构建决策树
            tree[best_feature][v] = self.createTree(sub_feature, sub_label)
        return tree
    # 后剪枝
    def post_cut(self, val_feature, val_label):
        # 拿到非叶子节点的数量
        def get_non_leaf_node_count(tree):
            non_leaf_node_path = []
            def dfs(tree, path, all_path):
                for k in tree.keys():
                    if isinstance(tree[k], dict):
                        path.append(k)
                        dfs(tree[k], path, all_path)
                        if len(path) > 0:
                            path.pop()
                    else:
                        all_path.append(path[:])
            dfs(tree, [], non_leaf_node_path)
            unique_non_leaf_node = []
            for path in non_leaf_node_path:
                isFind = False
                for p in unique_non_leaf_node:
                    if path == p:
                        isFind = True
                        break
                if not isFind:
                    unique_non_leaf_node.append(path)
            return len(unique_non_leaf_node)
        # 拿到树中深度最深的从根节点到非叶子节点的路径
        def get_the_most_deep_path(tree):
            non_leaf_node_path = []
            def dfs(tree, path, all_path):
                for k in tree.keys():
                    if isinstance(tree[k], dict):
                        path.append(k)
                        dfs(tree[k], path, all_path)
                        if len(path) > 0:
                            path.pop()
                    else:
                        all_path.append(path[:])
            dfs(tree, [], non_leaf_node_path)
            max_depth = 0
            result = None
            for path in non_leaf_node_path:
                if len(path) > max_depth:
                    max_depth = len(path)
                    result = path
            return result
        # 剪枝
        def set_vote_label(tree, path, label):
            for i in range(len(path)-1):
                tree = tree[path[i]]
            tree[path[len(path)-1]] = vote_label
        acc_before_cut = self.calc_acc_val(self.tree, val_feature, val_label)
        # 遍历所有非叶子节点
        for _ in range(get_non_leaf_node_count(self.tree)):
            path = get_the_most_deep_path(self.tree)
            # 备份树
            tree = deepcopy(self.tree)
            step = deepcopy(tree)
            # 跟着路径走
            for k in path:
                step = step[k]
            # 叶子节点中票数最多的标签
            vote_label = sorted(step.items(), key=lambda item: item[1], reverse=True)[0][0]
            # 在备份的树上剪枝
            set_vote_label(tree, path, vote_label)
            acc_after_cut = self.calc_acc_val(tree, val_feature, val_label)
            # 验证集准确率高于0.9才剪枝
            if acc_after_cut > acc_before_cut:
                set_vote_label(self.tree, path, vote_label)
                acc_before_cut = acc_after_cut
    def fit(self, train_feature, train_label, val_feature, val_label):
        '''
        :param train_feature:训练集数据,类型为ndarray
        :param train_label:训练集标签,类型为ndarray
        :param val_feature:验证集数据,类型为ndarray
        :param val_label:验证集标签,类型为ndarray
        :return: None
        '''
        #************* Begin ************#
        self.tree = self.createTree(train_feature, train_label)
        self.post_cut(val_feature, val_label)
        #************* End **************#
    def predict(self, feature):
        '''
        :param feature:测试集数据,类型为ndarray
        :return:预测结果,如np.array([0, 1, 2, 2, 1, 0])
        '''
        #************* Begin ************#
        # 单个样本分类
        result = []
        def classify(tree, feature):
            if not isinstance(tree, dict):
                return tree
            t_index, t_value = list(tree.items())[0]
            f_value = feature[t_index]
            if isinstance(t_value, dict):
                classLabel = classify(tree[t_index][f_value], feature)
                return classLabel
            else:
                return t_value
 
        for f in feature:
            result.append(classify(self.tree, f))
 
        return np.array(result)
        #************* End **************#

第7关:鸢尾花识别

python 复制代码
#********* Begin *********#
import pandas as pd 
from sklearn.tree import DecisionTreeClassifier
 
df = pd.read_csv('./step7/train_data.csv').as_matrix()
label = pd.read_csv('./step7/train_label.csv').as_matrix()
df_test = pd.read_csv('./step7/test_data.csv').as_matrix()
 
ft = DecisionTreeClassifier()
ft.fit(df,label)
result =ft.predict(df_test)
 
result = pd.DataFrame({'target':result})
result.to_csv('./step7/predict.csv', index=False)
#********* End *********#
相关推荐
网络真危险!!10 分钟前
【数据分析】认清、明确
数据挖掘·数据分析
菜鸟学Python11 分钟前
Python 数据分析核心库大全!
开发语言·python·数据挖掘·数据分析
WeeJot嵌入式16 分钟前
卷积神经网络:深度学习中的图像识别利器
人工智能
脆皮泡泡26 分钟前
Ultiverse 和web3新玩法?AI和GameFi的结合是怎样
人工智能·web3
机器人虎哥29 分钟前
【8210A-TX2】Ubuntu18.04 + ROS_ Melodic + TM-16多线激光 雷达评测
人工智能·机器学习
码银36 分钟前
冲破AI 浪潮冲击下的 迷茫与焦虑
人工智能
何大春40 分钟前
【弱监督语义分割】Self-supervised Image-specific Prototype Exploration for WSSS 论文阅读
论文阅读·人工智能·python·深度学习·论文笔记·原型模式
uncle_ll1 小时前
PyTorch图像预处理:计算均值和方差以实现标准化
图像处理·人工智能·pytorch·均值算法·标准化
宋138102797201 小时前
Manus Xsens Metagloves虚拟现实手套
人工智能·机器人·vr·动作捕捉
SEVEN-YEARS1 小时前
深入理解TensorFlow中的形状处理函数
人工智能·python·tensorflow