Training recommendation (Tutorials from PyCon 2014 – USA) and contest update
I am usually very selective about attending conferences!
Its not because I don’t like networking or talking to people. Its because I have a very high bar on time used in networking. I feel self-learning and discussing actual problems (when working on them) with people results in far more value for the time spent. However, there is one conference I want to attend at some point in future – PyCon (USA chapter).
For those who don’t know, PyCon is the largest annual gathering for the community using and developing the open-source Python programming language. While the conference is aimed to entire Python community (and not just data scientists), there is still a lot of learning and networking opportunities for data scientists. In India, the event is still not as big, but its recognition in industry is only a matter of time! This year, it is scheduled to be in September.
PyCon 2014 – USA happened recently (9th – 17th April) and I am sure it would have been a great platform for like minded people to interact and learn. As part of this conference, leading industry experts took a few tutorials. These tutorials are awesome source of knowledge, if you want to become awesome in using Python!
Here are my recommendations from these tutorials and the reasons why I like them:
- Exploring Machine learning with Scikit-learn and Diving deeper into Machine Learning with Scikit-learn – Just the right place to start learning about machine learning in Python. The 2 tutorials combined provide you with all the knowledge you need on the subject. The second tutorial covers some of the advanced topics like automated parameter tuning and how to scale up using iPython.parallel.
- Mining Social Web APIs with IPython Notebook – Coming from the author of popular book, mining the Social Web (O’Reilly, 2013), the tutorial and the accompanying iPython notebook provide you ways to extract data using social media APIs. Aimed towards beginners, the tutorial shows step by step extraction and mining of data. Once you know how to extract this data, you can get as creative as you want – How different are you from likes of your Facebook Friends? How much influence do you carry on Twitter? are just some of the questions to start your journey.
- Data Wrangling for Kaggle Data Science Competitions — An etude – A must read if you have participated in Kaggle competitions or want to at some point in near future. Krishna’s insights into how the competitions work and what data providers might do before providing data can save you months of scrolling through Kaggle Forums!
- Hands-on with Pydata: how to build a minimal recommendation engine – If you have not built a recommendation engine till now and are fascinated by the idea of building one, this is just what you needed. A tutorial which covers all the basics and quickly moves towards practical applications and the idea of iterational improvement.
We ran a 3 day contest asking 15 questions across our social media platforms. We saw awesome participation with really tough competition during these three days and are pleased to announce Datta Dharanikota as our winner. He gets a 3000 Rs. voucher from Amazon.
A few special mentions for their superb participation: Nitesh Singh, Dhanman Gupta, Nimit Gupta, Raghavendra Reddy, Avinash Asuri, Jenny Srinivasan, Sateesh Kumar, Aditi Vij – well done guys and thanks for your participation! I hope that the contest gave you a small glimpse of the work we have done in last year!