Skip to content

A Data solution that scrapes news from energy sites and analyze them

Notifications You must be signed in to change notification settings

viniciusgribas/EnergyNewsScrapping

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 

Repository files navigation

Energy Engineer (UnB)Data Scientist and Analytics (USP)


Project Notebook [BR 🇧🇷]


Energy News Web Scrappers [EN 🇬🇧]


With the aim of applying knowledge in Text Mining, Sentiment Analysis, NLP, Machine Learning, Crowlers and Web Scrapping, data solutions were developed with themes relevant to the energy sector.

These solutions scrape data from the CNN Brasil website (with a focus on the international energy scenario); and from government websites of agencies such as ANP, ANEEL and MME (with a focus on the national energy scenario).

Once scraped, the data is manipulated and added to a dataframe, and finally presented via plotly and wordcloud, as shown in the figures below.

All notebooks were developed via jupyter notebook and are available in my GitHub repository (github.com/viniciusgribas).

The results obtained (listed in the comments) were very interesting! They allow us to extract insights into what is happening in Brazil and in the world in the energy theme.

Feel free to contact me if you have any feedback, interesting websites to scrape, or insights to share.

#energy #github #machinelearning #nlp #textmining #mme #cnn #aneel #anp

1️ - CNN-NEWS Results (energy):

2️ - ANEEL Results:

3️ - ANP Results:

4️- MME Results:

About

A Data solution that scrapes news from energy sites and analyze them

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published