<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[Duke_LH的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/Duke_LH</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; Duke_LH]]></copyright><item><title><![CDATA[a_bogus逆向纯算]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/142920543</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/142920543</guid><author>Duke_LH</author><pubDate>Mon, 14 Oct 2024 17:24:33 +0800</pubDate><description><![CDATA[这里主要是根据时间戳和一些数组前面的值经过位运算后生成，里面的76位是取的环境值拼接成的字符串，77位是第76位加密得到的数组，可以写死。第一个是一个50位的数组，取自大数组里面固定位置的值，这个位置可以插桩得到，剩下两个是第82位和第87位。由第86位和第90位拼接后转字符串，和另外一个固定数组循环生成一串乱码。不断的调整断点跟栈发现整个vmp加密流程依靠着一个大数组，不断的往里进行取值，一番操作后又往里存，包括最后生成的。由第86位和数组前面的一些固定顺序的值通过位运算生成，参与第88位的生成。]]></description><category></category></item><item><title><![CDATA[爬虫：Sentry-Span参数逆向]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/140272408</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/140272408</guid><author>Duke_LH</author><pubDate>Mon, 08 Jul 2024 16:55:10 +0800</pubDate><description><![CDATA[在抓某眼查数据太过频繁时会出现极验的验证码。极验的教程有很多，主要是发现在这里获取验证码的时候需要携带参数。在这里记录一下逆向的主要过程，直接上补环境的代码。]]></description><category></category></item><item><title><![CDATA[数据挖掘：银行客户认购产品预测]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/127494179</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/127494179</guid><author>Duke_LH</author><pubDate>Mon, 24 Oct 2022 16:37:39 +0800</pubDate><description><![CDATA[数据挖掘：银行客户认购产品预测。]]></description><category></category></item><item><title><![CDATA[爬虫 — 大众点评商户信息的爬取和文字反爬]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/121864027</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/121864027</guid><author>Duke_LH</author><pubDate>Sat, 11 Dec 2021 20:40:06 +0800</pubDate><description><![CDATA[信息爬取
import requests
from lxml import etree
import time
import json
import pandas as pd
import re
import json

# 获取商户名称和ID
result = []
for i in range(1,51):
    print(i)
    url = r'http://www.dianping.com/haikou/ch10/p{page}'.format(page=i)
    headers = ]]></description><category></category></item><item><title><![CDATA[数据挖掘：贷款违约预测]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/117037249</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/117037249</guid><author>Duke_LH</author><pubDate>Wed, 19 May 2021 17:57:24 +0800</pubDate><description><![CDATA[数据
数据来源阿里天池学习赛：零基础入门金融风控-贷款违约预测
代码
import pandas as pd
import numpy as np
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_auc_score,accuracy_score
import joblib
from catboo]]></description><category></category></item><item><title><![CDATA[cat_features must be integer or string, real number values and NaN values should be converted to str]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/116798749</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/116798749</guid><author>Duke_LH</author><pubDate>Fri, 14 May 2021 17:40:44 +0800</pubDate><description><![CDATA[第一次用catboost训练模型时，出现报错，具体如下：

CatBoostError: Invalid type for cat_feature[non-default value idx=0,feature_idx=4]=3.0 : cat_features must be integer or string, real number values and NaN values should be converted to string.

报错信息很好理解，训练器要求我们指定的类别变量的值必须为整型或]]></description><category></category></item><item><title><![CDATA[分类预测：会员回购预测]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/112534254</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/112534254</guid><author>Duke_LH</author><pubDate>Tue, 12 Jan 2021 18:18:14 +0800</pubDate><description><![CDATA[项目说明
数据集来自阿里天池：会员回购预测
目的是为了判断顾客是否会响应活动从而回购，也就是一个是否响应活动的二分类模型
数据说明
train&amp;test

target:“0”代表不回购，“1”代表回购
transactions

代码
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import trai]]></description><category></category></item><item><title><![CDATA[Pyecharts 折线堆叠图数据序列和坐标轴不对应的问题]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/108267840</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/108267840</guid><author>Duke_LH</author><pubDate>Thu, 27 Aug 2020 20:47:51 +0800</pubDate><description><![CDATA[在用 pyecharts 练手的时候，尝试用下表中的数据构造一份折线堆叠图

year_line = Line().add_xaxis(summary.columns.to_list())
# year_line = Line().add_xaxis([1,2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12,13])

for i in range(4):
    year_line.add_yaxis(str(i+2012),
                       stack=']]></description><category></category></item><item><title><![CDATA[数据分析：母婴商品数据可视化]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/108214629</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/108214629</guid><author>Duke_LH</author><pubDate>Tue, 25 Aug 2020 11:32:06 +0800</pubDate><description><![CDATA[数据来源：Baby Goods Info Data
读取数据
import numpy as np
import pandas as pd
from pyecharts.charts import Pie,Bar,Page
from pyecharts import options as opts

filename = r'train.csv' #联结年龄和性别后的表
filename1 = r'trade_history.csv'
data = pd.read_csv(filename)
data1 =]]></description><category></category></item><item><title><![CDATA[回归分析:二手车价格预测]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/105514303</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/105514303</guid><author>Duke_LH</author><pubDate>Tue, 14 Apr 2020 16:25:18 +0800</pubDate><description><![CDATA[项目说明：数据来源阿里天池的一个挖掘比赛：预测二手车交易价格
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_absolute_err...]]></description><category></category></item><item><title><![CDATA[python：疫情数据可视化]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/105486441</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/105486441</guid><author>Duke_LH</author><pubDate>Mon, 13 Apr 2020 18:11:42 +0800</pubDate><description><![CDATA[数据来源：BlankerL
数据截止2020-04-10下午4点
json数据转 csv
import json
import time
import csv

file = open('DXYArea-TimeSeries.json','r',encoding='utf-8')

infos = json.load(file)
with open('data.csv','a',newline='...]]></description><category></category></item><item><title><![CDATA[《商务与经济统计》Python实现笔记（五）]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/105101132</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/105101132</guid><author>Duke_LH</author><pubDate>Wed, 25 Mar 2020 18:05:57 +0800</pubDate><description><![CDATA[时间序列分析
移动平均
import pandas as pd
import numpy as np


data = pd.DataFrame([17,21,19,23,18,16,20,18,22,20,15,22],columns=['sale'])
data["rolling_mean"] = data.rolling(3).mean().shift(1)#选前3个时间单位的平均值，预测值...]]></description><category></category></item><item><title><![CDATA[《商务与经济统计》Python实现笔记（四）]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/105100995</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/105100995</guid><author>Duke_LH</author><pubDate>Wed, 25 Mar 2020 18:04:00 +0800</pubDate><description><![CDATA[一元线性回归
import pandas as pd
import numpy as np
import statsmodels.api as sm
# import statsmodels.formula.api as smf方法二


x = np.array([2,6,8,8,12,16,20,20,22,26])
y = np.array([58,105,88,118,117,137,15...]]></description><category></category></item><item><title><![CDATA[《商务与经济统计》Python实现笔记（三）]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/105100793</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/105100793</guid><author>Duke_LH</author><pubDate>Wed, 25 Mar 2020 18:00:28 +0800</pubDate><description><![CDATA[方差分析
单因素方差分析（多个总体均值相等的假设检验）
import scipy.stats as stats

a = [58,64,55,66,67]
b = [58,69,71,64,68]
c = [48,57,59,47,49]

stats.f_oneway(a,b,c)

F_onewayResult(statistic=9.176470588235295, pvalue=0.003...]]></description><category></category></item><item><title><![CDATA[《商务与经济统计》Python实现笔记（二）]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/105100512</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/105100512</guid><author>Duke_LH</author><pubDate>Wed, 25 Mar 2020 17:51:13 +0800</pubDate><description><![CDATA[总体方差的置信区间
from scipy.stats import chi2
def CI(n,sigma2,alpha):
    """
    n:样本量
    sigma2:样本方差
    alpha:置信水平
    
    """
    a = (1-alpha)/2
    b = (n-1)*sigma2
    lower = b/chi2.ppf(a,df=n-1)
 ...]]></description><category></category></item><item><title><![CDATA[《商务与经济统计》Python实现笔记（一）]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/105100356</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/105100356</guid><author>Duke_LH</author><pubDate>Wed, 25 Mar 2020 17:40:16 +0800</pubDate><description><![CDATA[独立样本T检验（两样本均值估计两总体均值大小关系）
import pandas as pd
import numpy as np
from scipy import stats

# 传数据
data = pd.read_excel(r"C:\Users\liuhao\Desktop\python_work\Python数据分析与挖掘实战\chapter8\test\data\data.xls")...]]></description><category></category></item><item><title><![CDATA[norm.interval和t.interval不能直接求样本的置信区间]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/104711979</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/104711979</guid><author>Duke_LH</author><pubDate>Sat, 07 Mar 2020 12:16:18 +0800</pubDate><description><![CDATA[按网上搜到的结果调用scipy.stats包计算参数已知的置信区间
from scipy import stats as sst
conf_int = sst.norm.interval(0.95, loc=82, scale=20)
# conf_int = sst.norm.cdf(1.96)
conf_int

输出结果如下：
(42.80072030919892, 121.19927969...]]></description><category></category></item><item><title><![CDATA[购买行为预测婴儿年龄：Apriori 和 KNN 的简单实现]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/100810541</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/100810541</guid><author>Duke_LH</author><pubDate>Fri, 13 Sep 2019 21:54:20 +0800</pubDate><description><![CDATA[Apriori 代码

import pandas as pd

#自定义连接函数，用于实现L_{k-1}到C_k的连接
def connect_string(x, ms):
	"""
	x:频繁项集列表
	ms: 连接符，这里用 ‘---’
	return: 返回长度+1的频繁项集，即L_{k-1}到C_k的连接
	"""
    x = list(map(lambda i:sorted(i....]]></description><category></category></item><item><title><![CDATA[Python — 爬取饿了么外卖店信息]]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/85211582</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/85211582</guid><author>Duke_LH</author><pubDate>Sat, 22 Dec 2018 16:44:09 +0800</pubDate><description><![CDATA[在学数据可视化，缺少点数据进行实操，就想着从饿了么上面爬点外卖店信息。
主要是获取数据，所以代码比较简陋，直接上代码：
import requests
import json
import csv

def crawler_ele(page=0):
	
	def get_page(page):
		url = 'https://h5.ele.me/restapi/shopping/v3/resta...]]></description><category></category></item><item><title><![CDATA[Pandas 报错AttributeError: 'Index' object has no attribute 'remove_unused_levels']]></title><link>https://blog.youkuaiyun.com/Duke_LH/article/details/84776472</link><guid>https://blog.youkuaiyun.com/Duke_LH/article/details/84776472</guid><author>Duke_LH</author><pubDate>Mon, 03 Dec 2018 17:54:37 +0800</pubDate><description><![CDATA[执行代码，将 Series 转换成 DataFrame 时：
s1 = pd.Series(np.random.rand(5),index=['a','s','d','f','g'])
print(s1.unstack())

报错情况如下：
Traceback (most recent call last):
  File &amp;quot;C:\Users\liuhao\Desktop\资料\python_w...]]></description><category></category></item></channel></rss>