BudapestPy Workshops 107 (2019-11-07)

We started the November at One Identity’s place. Thank One Identity , and Balázs Antal for the venue, and the beer and pizza. All of our workshops in this month will be held at One Identity .

We had three things to talk about this week. The first is you, our attendees. Some of you have been with us for the past two months, and for some of you, this event was the first – but hopefully not the last. We wanted to get to know you better, so we asked everyone to introduce themselves, talk about the connection with Python and Data, and the future goals.
It was really helpful to us, to know which direction we should go next year.

After this session, Gray Tamás from Nofluffjobs told us about their website, and why could it be a big help for everyone in the IT field. Those who don’t know them, the special thing is that the job ads posted on their site must contain some required information such as the salary range, and the stack . They hope they can bring some transparency to the IT job market, as they’re doing it in Poland for years.

This evening, Balazs Balogh had the opportunity to talk about Scikit-learn, one of the most famous machine learning library in Python. He talked about the fundamentals of machine learning, and classification problems. The dataset was the bank notes authenticity data, where one should decide from four features that a bank note is authentic or fake.

Five ML models was shown and summarized: Logistic Regression, Decision Tree, Random Forest, Support Vector Machine and XGBoost. Each one has the same metrics, so at the end, it was easy to compare them, and see what was the best for this problem.
We also used Grid Search, and Cross Validation to improve the models.

Thanks for everyone for attending!
As always, the notebooks are on our GitHub:
https://github.com/budapestpy-workshops

You can join us on our meetup page:
https://www.meetup.com/budapest-py/

The Team: Balogh Balázs, Rónai Bertalan, Szabó Dóra, Doma Miklós, Hackl Krisztián and Zsarnowszky Lóránt (last name, first name order)