LXL Blog

Thinking will not overcome fear but action will.

Causal Inference

Paper Summary

Introduction This is a summary of Deaton, Cartwright - Understanding and misunderstanding randomized controlled trials(Challenge 1 of Causal Inference). Motivation Randomized controlled trails (...

车辆信息爬取

爬虫说明

简介 这是一个用于《道路机动车辆生产企业及产品公告》新产品公示信息爬取的爬虫程序。 import pandas as pd import requests from bs4 import BeautifulSoup import re import random import time import datetime import math 定义Header 这一步的目的在于将程...

Neural Networks

Do people like Avengers Endgame?

Introduction Movie reviews can be classified as positive or negative. Here we are going to use Neural Networks to predict whther each review is positive or negative. The training process is based...

Decision Tree and Random Forest

Assignment 5

Introduction In this article, we mainly use Decision Tree nad Random Forest to solve classification problem of heart disease and concern practical issue. Therefore, we use the same data as Classif...

Regularization--Prediction of House Price

Assignment 4

Introduction House sale prices are determined by a lot of factors, and some of them are important while others relatively not. Here in this study I will use regularization methods to prevent overf...

Classification--Empirical Study of Heart Disease

Assignment 3

Introduction Heart disease becomes more and more common in our daily life and there are a lot of reasons that are possible to cause it. Here in this simple study, we are going to use classificatio...

Resampling

Assignment 2

1. Definition In statistics, resampling is a relative broad concept of re-construct samples. Any method doing one of the following can be called resampling: Estimating the precision of sample ...

关于在博客中创建PDF链接

Tutorial about creating PDF link

第一步 按照教程创建个人网站 Creating and Hosting a Personal Site on GitHub 第二步 在你的个人网站repo里创建一个assets文件夹 然后上传你的作业PDF到assets文件夹里 创建readme文件是因为github不允许空文件夹 第三步 就像你创建第一篇博文一样,在_posts文件夹种创建YYYY-MM-DD-title.m...

Bias-Variance Trade-off

Assignment 1

Motivation When doing a learning problem, we always want our model to perfectly explain the data, which means that our model not only fits the sample we choose, but also predicts unseen population ...