Irio Musskopf

@rafapetter Vocês seguem procurando apoio ou já tomaram a decisão de arquivar o projeto?

The [B1 Wortliste DTZ Goethe (vocab,sentenses,audio,translation)](https://ankiweb.net/shared/info/1586166030) deck has multiple sentences in each note. They name fields like `s1` (sentence 1), `s1e` (sentence 1 explanation?), and `s1a` (sentence 1 audio). Since...

Me and @jtemporal are [working on it](https://github.com/datasciencebr/DummyRDD/tree/dataframe-support), using it in a real project as experimentation before deciding to open a pull request. Hope to do so in the following weeks,...

Hi @Gmousse, Yes, I have look at them, but they don't seem to cover all the cases I needed and Pandas supports. There's always the chance they are too specific,...

*I also sent an email to Breno Costa after listening to the podcast.* 🥇 Not sure if this can help us directly with the receipts, but with other analyses leveraging...

@cuducos In this example they have distinct `document_id`'s. Before going to OCR, I'd try [SIFT](https://en.wikipedia.org/wiki/Scale-invariant_feature_transform), which I believe is much faster since does not depend on a vocabulary of words,...

Check the paper "Region Duplication Forgery Detection Technique Based on SURF and HAC" for references (https://sci-hub.cc/ is your friend). [Here](https://github.com/Irio/photoshopped-or-not/blob/master/develop/2016-06-16-im-sift-surf-region-duplication.ipynb)'s an example of Python code to run SIFT.

Hey everyone. You can find dataset and code that generated it on the following links: https://gist.github.com/Irio/7bf35f10dad39cea519ebee4ee7fc5cc https://github.com/Irio/budget

It's a suspicious activity that may be used as one of the features when predicting the legality, in a larger Machine Learning model. I personally like it.

A good start is collecting who politicians declare on their own Facebook profiles. Let's take Renato Molling, the RS federal deputy who spent more from the Quota for Exercising Parliamentary...