项目作者: AshuMaths1729

项目描述 :
News Article classification from raw unlabeled scraped data
高级语言: Python
项目地址: git://github.com/AshuMaths1729/News_Article_Classifier.git
创建时间: 2019-04-17T15:48:07Z
项目社区:https://github.com/AshuMaths1729/News_Article_Classifier

开源协议:

下载


News Article Classifier

News Article classification from raw unlabeled scraped data

To make scraper, first install Scrapy on your system, then make a Crawler named TOI, and scraper named toi, then replace the scraper in spyder folder with toi.py.

The main problem with this project was that the data collected was not labeled, that is it did not had labels for classes. So, I clustered the data into 5 classes after preprocessing it, and then made different analysis on it.

The results are as follows

alt text

alt text

alt text

alt text