一口气刷完牛客网全部机器学习算法题

不知道为什么最近突然觉得牛客网很火，好奇心驱使下我也点开看了看...发现真的不错。 

机器学习是python新增加的板块，其实只有5道题 哈哈 。 

ps:题目很简单很基础，真的很适合刚刚入门机器学习的小白检验阶段性的学习成果。 

趁着题还很少，将来出一道做一道，岂不是成就感满满。

鸢尾花分类_1

原题：鸢尾花分类_1_牛客题霸_牛客网 (nowcoder.com)

 这道题采用贝叶斯算法能够保证该数据集下准确率在100%。

# 朴素贝叶斯
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score

def train_and_predict(train_input_features, train_outputs, prediction_features):
    G = GaussianNB()
    G.fit(train_input_features, train_outputs)
    y_pred = G.predict(prediction_features)
    return y_pred

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:
    print(accuracy_score(y_pred,y_test))

鸢尾花分类_2

原题：鸢尾花分类_2_牛客题霸_牛客网 (nowcoder.com)

我使用的是决策树模型，默认参数下该二分类问题准确率还是100%

import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier


def transform_three2two_cate():
    data = datasets.load_iris()
    new_data = np.hstack([data.data, data.target[:, np.newaxis]])
    new_feat = new_data[new_data[:, -1] != 2][:, :4]
    new_label = new_data[new_data[:, -1] != 2][:, -1]
    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)
    DT = DecisionTreeClassifier()
    DT.fit(train_x, train_y)
    y_predict = DT.predict(test_x)
    print(accuracy_score(y_predict, test_y))


if __name__ == "__main__":
    train_and_evaluate()

信息熵的计算

原题：决策树的生成与训练-信息熵的计算_牛客题霸_牛客网 (nowcoder.com)

这道题十分简单，我的做法是把下面的数据转换为numpy的ndarray矩阵取出最后一列，直接套公式：

import numpy as np
import pandas as pd
from collections import Counter

dataSet = pd.read_csv('dataSet.csv', header=None).values[:, -1]


def calcInfoEnt(dataSet):
    numEntres = len(dataSet)
    cnt = Counter(dataSet)  # 计数每个值出现的次数
    probability_lst = [1.0 * cnt[i] / numEntres for i in cnt]
    return -np.sum([p * np.log2(p) for p in probability_lst])


if __name__ == '__main__':
    print(calcInfoEnt(dataSet))

信息增益的计算

原题：决策树的生成与训练-信息增益_牛客题霸_牛客网 (nowcoder.com)

import numpy as np
import pandas as pd
from collections import Counter
import random

dataSet = pd.read_csv('dataSet.csv', header=None).values.T  # 转置 5*15数组


def entropy(data):  # data 一维数组
    numEntres = len(data)
    cnt = Counter(data)  # 计数每个值出现的次数  Counter({1: 8, 0: 5})
    probability_lst = [1.0 * cnt[i] / numEntres for i in cnt]
    return -np.sum([p * np.log2(p) for p in probability_lst])  # 返回信息熵


def calc_max_info_gain(dataSet):
    label = np.array(dataSet[-1])
    total_entropy = entropy(label)
    max_info_gain = [0, 0]

    for feature in range(4):  # 4种特征 我命名为特征：0 1 2 3
        f_index = {}
        for idx, v in enumerate(dataSet[feature]):
            if v not in f_index:
                f_index[v] = []
            f_index[v].append(idx)
        f_impurity = 0
        for k in f_index:
            # 根据该特征取值对应的数组下标 取出对应的标签列表 比如分支1有多少个正负例 分支2有...
            f_l = label[f_index[k]]
            f_impurity += entropy(f_l) * len(f_l) / len(label)  # 循环结束得到各分支混杂度的期望

        gain = total_entropy - f_impurity  # 信息增益IG
        if gain > max_info_gain[1]:
            max_info_gain = [feature, gain]

    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]))

使用梯度下降对逻辑回归进行训练

原题：使用梯度下降对逻辑回归进行训练_牛客题霸_牛客网 (nowcoder.com)

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):
    hx = 1/(1+np.exp(-X))
    return hx
    
    #code end here
def gradientDescent(dataMatIn, classLabels):
    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

    for i in range(iteration_nums):
        hx=sigmoid(dataMatrix*weight_mat)
        weight_mat-=alpha*dataMatrix.transpose()*(hx-labelMat)
    return weight_mat

if __name__ == '__main__':
    dataMat, labelMat = generate_data()
    print(gradientDescent(dataMat, labelMat))