Close

02/16/2019

Data Science – A small intro, what enticed me and a few resources to start

Notes from IBM Data Science Professional Certificate course by IBM on Coursera__Notes by Diego Carrasco G.

I’m starting a small series of articles regarding Data Science, what enticed me, why I started, where to start and so on. I’m as of now by no way an expert but an enthusiastic learner who’s writing to learn better, share what I’ve learned and as an introduction and basis for others who would want to start in this area.

Right now I’m on an IBM Course on Coursera which I find to be really great (and so far from all the courses I’ve tried to take on Coursera the IBM ones are the only ones I’ve finished, and quickly may I add.)

image-1

I finished 7 courses from the IBM Data Science Professional Certificate and Im on the 6th week of the 8th one. It was the best trial ever (7 days, 6 IBM/Coursera Certificates and 6 IBM Badges by youracclaim.com)

Honestly, I couldnt recommend this set of courses enough. Its really quite a good basis to start in Data Science and Python. And it all began because I wanted to invest in Real Estate and wanted to have a Data Science base of all the freely available property ads in Chile using “www.yapo.cl” (its only accesible if you are in Chile, but a VPN works like a charm). I wrote a Python Script fast to scrap the data (15k rows up today for the last 6 months) using requests and bs4. That got me started, but excel took quite a lot of time to render the data and I still had to clean it up a bit more. I had read about python, pandas and so on and searched how to use those tools, and I stumped right into Coursera and this Professional Certificate. I also looked in edx, class-central and many others, but this one gave me a certificate (always good), the Data Analysis with Python was enjoyable and fast-paced, and I finished it in a couple of days, leaving me quite excited for more. I realized I like this area and started the other courses right away, and I’m now on the 8th course on Machine Learning with Python (it’s harder that the others and it’s taking more time to finish it, but I’m excited about the possibilities and astonished as to how many tools and models are available. Pandas is also quite a useful discovery for me and I’m loving it).

 

handwriten notes

I’ve taken lots of notes (by hand, hence the picture above) and I’ll be re-writing them in this site. Maybe they are helpful for others.

While I’m working on the Capstone Project I was in need of a way to get a DataFrame of venues near a coordinate using Foursquare API, so I developed a small package in python and published it to GitHub. You are free to check it out and play with it. Any recommendations are welcome, it’s my first package after all. And it’s under the MIT License, so enjoy.

You can check that project on GitHub and check a small post on that project here

%d bloggers like this: