牛客编程题Python机器学习（入门例题5题）

Posted 2022-08-05 小哈里

【牛客编程题】Python机器学习（入门例题5题）
做题链接：https://www.nowcoder.com/exam/oj?page=1&tab=Python篇&topicId=329

文章目录

• • • AI1 鸢尾花分类_1
    • AI2 鸢尾花分类_2
    • AI3 决策树的生成与训练-信息熵的计算
    • AI4 决策树的生成与训练-信息增益
    • AI5 使用梯度下降对逻辑回归进行训练

AI1 鸢尾花分类_1

import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn import metrics
from sklearn.naive_bayes import GaussianNB


def train_and_predict(train_input_features, train_outputs, prediction_features):
    #code start here
    clf = GaussianNB();
    clf.fit(train_input_features, train_outputs);
    y_pred = clf.predict(prediction_features);
    return y_pred;
    #code end here

iris = datasets.load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target,
                                                    test_size=0.3, random_state=0)



y_pred = train_and_predict(X_train, y_train, X_test)


if y_pred is not None:
    
    #code start here
    print(metrics.accuracy_score(y_test, y_pred))

    #code end here

AI2 鸢尾花分类_2

import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import f1_score, roc_auc_score, accuracy_score
from sklearn.tree import DecisionTreeClassifier


def transform_three2two_cate():
    data = datasets.load_iris()
    # 其中data特征数据的key为data，标签数据的key为target
    # 需要取出原来的特征数据和标签数据，移除标签为2的label和特征数据，返回值new_feat为numpy.ndarray格式特征数据，new_label为对应的numpy.ndarray格式label数据
    # 需要注意特征和标签的顺序一致性，否则数据集将混乱
    # code start here
    index2 = np.where(np.array(data.target)==2)
    new_feat = np.delete(data.data, index2, axis = 0)
    new_label = np.delete(data.target, index2)
    # code end here
    return new_feat, new_label


def train_and_evaluate():
    data_X, data_Y = transform_three2two_cate()
    train_x, test_x, train_y, test_y = train_test_split(data_X, data_Y, test_size=0.2)
    # 已经划分好训练集和测试集，接下来请实现对数据的训练
    # code start here
    dtc = DecisionTreeClassifier(max_depth=3) # 建立决策树模型
    dtc.fit(train_x, train_y) # 训练模型
    y_predict = dtc.predict(test_x) # 预测结果
    # code end here
    # 注意模型预测的label需要定义为 y_predict，格式为list或numpy.ndarray
    print(accuracy_score(y_predict, test_y))


if __name__ == "__main__":
    train_and_evaluate()
    # 要求执行train_and_evaluate()后输出为：
    # 1、0,1，代表数据label为0和1
    # 2、测试集上的准确率分数，要求>0.95

AI3 决策树的生成与训练-信息熵的计算

# -*- coding: UTF-8 -*-
from math import log
import pandas as pd

dataSet = pd.read_csv('dataSet.csv', header=None).values.tolist()


def calcInfoEnt(dataSet):
    numEntres = len(dataSet) # 数据集样本数量
    #code start here
    labelCounts =  # 字典：每一类的样本数量
    for featVec in dataSet:
        currentLabel = featVec[-1] # 获取分类标签
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel] = 0
        labelCounts[currentLabel] += 1 # 每个类中数据个数统计
    infoEnt = 0
    for key in labelCounts:
        prob = float(labelCounts[key])/numEntres
        infoEnt -= prob*log(prob, 2)
    return infoEnt
    #code end here
    #返回值 infoEnt 为数据集的信息熵，表示为 float 类型
    
if __name__ == '__main__':
    print(calcInfoEnt(dataSet))
    #输出为当前数据集的信息熵

AI4 决策树的生成与训练-信息增益

# -*- coding: UTF-8 -*-
from math import log
import pandas as pd

dataSet = pd.read_csv('dataSet.csv', header=None).values.tolist()

#给定一个数据集，calcInfoEnt可以用于计算一个数据集的信息熵，可直接调用
#也可不使用，通过自己的方式计算信息增益
def calcInfoEnt(data):
    numEntres = len(data)
    labelcnt =  #用于统计正负样本的个数
    for item in data:
        if item[-1] not in labelcnt:
            labelcnt[item[-1]] = 0
        labelcnt[item[-1]] += 1
    infoEnt = 0.0
    for item in labelcnt: #根据信息熵的公式计算信息熵
        curr_info_entr = float(labelcnt[item]) / numEntres
        infoEnt = infoEnt - curr_info_entr * log(curr_info_entr,2)
    return infoEnt
    #返回值 infoEnt 为数据集的信息熵

#给定一个数据集，用于切分一个子集，可直接用于计算某一特征的信息增益 
#也可不使用，通过自己的方式计算信息增益   
#dataSet是要划分的数据集，i 代表第i个特征的索引index
#value对应该特征的某一取值
def create_sub_dataset(dataSet, i, value): 
    res = []
    for item in dataSet:
        if item[i] == value:
            curr_data = item[:i] + item[i+1:]
            res.append(curr_data)
    return res

def calc_max_info_gain(dataSet):#计算所有特征的最大信息增益，dataSet为给定的数据集
    n = len(dataSet[0])-1  # n 是特征的数量，-1 的原因是最后一列是分类标签
    total_entropy = calcInfoEnt(dataSet)#整体数据集的信息熵
    max_info_gain = [0,0]#返回值初始化
    #code start here
    for i in range(n): # 遍历特征, 计算特征i的信息增益
        featList = [feat[i] for feat in dataSet] 
        featValues = set(featList)# 获得所有该特征的数据
        newEntropy = 0.0 #计算经验条件熵
        for value in featValues:
            subDataset = create_sub_dataset(dataSet,i,value)
            prob = len(subDataset)/len(dataSet)
            newEntropy += prob*calcInfoEnt(subDataset)
        infoGain = total_entropy-newEntropy # 信息增益=信息熵-经验条件熵
        if(infoGain > max_info_gain[1]): # 信息增益取最大
            max_info_gain[1] = infoGain
            max_info_gain[0] = i
    #code end here
    return max_info_gain
if __name__ == '__main__':
    info_res = calc_max_info_gain(dataSet)
    print("信息增益最大的特征索引为：0,对应的信息增益为1".format(info_res[0],info_res[1]))

AI5 使用梯度下降对逻辑回归进行训练

import numpy as np
import pandas as pd
def generate_data():
    datasets = pd.read_csv('dataSet.csv', header=None).values.tolist()
    labels = pd.read_csv('labels.csv', header=None).values.tolist()
    return datasets, labels
def sigmoid(X): 
    #补全 sigmoid 函数功能
    #code start here
    return 1/(1+np.exp(-X)) # h(x)函数，直接计算并返回即可
    #code end here
def gradientDescent(dataMatIn, classLabels): # 输入 datasets,labels
    alpha = 0.001  # 学习率，也就是题目描述中的 α
    iteration_nums = 100  # 迭代次数，也就是for循环的次数
    dataMatrix = np.mat(dataMatIn) 
    labelMat = np.mat(classLabels).transpose() 
    m, n = np.shape(dataMatrix)  # 返回dataMatrix的大小。m为行数,n为列数。
    weight_mat = np.ones((n, 1)) #初始化权重矩阵
    #iteration_nums 即为循环的迭代次数
    #请在代码完善部分注意矩阵乘法的维度，使用梯度下降矢量化公式
    #code start here
    for i in range(iteration_nums):
        hx = sigmoid(dataMatrix*weight_mat)
        weight_mat = weight_mat-alpha*dataMatrix.transpose()*(hx-labelMat)
    return weight_mat
    #code end here
if __name__ == '__main__':
    dataMat, labelMat = generate_data()
    print(gradientDescent(dataMat, labelMat))