机器学习期中代码练习

期中复习

import pandas as pd
import numpy as np
import math
import random
import matplotlib.pyplot as plt

def load_data():
    data = pd.read_csv("C:/Users/lolo/Documents/WeChat Files/L15804627211/Files/iris.csv")
    return data

def choose_random(data,alpha):
    #划分数据集
    #alpha表示训练集的比例
    chooselist = random.sample(range(0,len(data)),int(alpha*len(data)))
    return data.loc[chooselist,:]
    
def sigmoid(x):
    return 1 / (1 + np.exp(-x))
    
def logistic_gradient_descent_method(train_x, train_y, alpha, maxnum):
    #train_x：训练集
    #train_y：训练集分类
    #alpha：步长
    #maxnum：最大迭代次数
    numSam, numFeature = train_x.shape
    add = np.ones((numSam,1))
    train_x = np.hstack((train_x,add))
    theta = np.ones((numFeature + 1, 1))
    for i in range(0,maxnum):
        cum = np.zeros((1,numFeature+1))
        for k in range(0,numSam):
            cum += (train_y[k]-sigmoid(np.dot(train_x[k],theta))) * train_x[k]
        theta = theta - alpha * cum.transpose()
    return theta

def logistic_newton_method(train_x, train_y, maxnum):
    #train_x：训练集
    #train_y：训练集分类
    #maxnum：最大迭代次数
    numSam, numFeature = train_x.shape
    add = np.ones((numSam,1))
    train_x = np.hstack((train_x,add))
    beta = np.ones((numFeature + 1, 1))
    for i in range(0,maxnum):
        patial1 = np.zeros((numFeature + 1, 1))
        patial2 = np.zeros((numFeature + 1, numFeature + 1))
        for k in range(0, numSam):
            p1 = sigmoid(np.dot(train_x[k], beta))
            patial1 -= np.matrix(train_x[k]).transpose() * (train_y[k] - p1)
            patial2 += np.dot(train_x[k].transpose(),train_x[k]) * p1 * (1-p1)
        beta <