Data science and machine learning are fast-paced emerging technologies across all industries including oil and gas. The oil and gas industry has taken big steps to adopt these technologies to make its exploration and production operations more efficient.
In these tutorials, I will share with you a comprehensive set of notebooks from the absolute introduction to python programming, all the way to reliable implementations of machine learning on real-world data. Along the process, we will go through all the necessary steps for a successful data science project as we'll explore both theoretical and practical concepts related to data processing, statistical investigation, effective data visualization, and machine learning concepts, to the final implementation of a set of intelligent algorithms.
We'll be following the agenda listed below, hopefully in a concise weelly manner.
- 01 Where Data Science and Petroleum Engineering meet
- 02 Python primer
- 03 Dealing with data (Your 80% work)
- 04 Data through a statistician eyes
- 05 Data visualization story telling | In Process
- 06 Supervised machine learning (I've got them labeled buddy)
- 07 Unsupervised machine learning (ain't no label mate)
- 08 Time series modeling (This is not a financial advice)
- 09 Deep learning for tubular data (Welcome to over-fitting hh)
- 10 Deeper learning lol (Intresting concepts)
- 11 Case study 1 :
- 12 Case study 2 :
- 13 Case study 3 :
- 14 Case study 4 :
- 15 Case study 5 :
This is a self-study course, you can either download the full course repository and run the code locally on your computer using Anaconda, or run it directly using Google Collab by clicking on the top window of each notebook. If you choose the second option, be sure to import the data into your google drive first. I suggest a rate of a notebook per week, make sure to run the code yourself and just experience with it. If anything seem abstract I guarantee that we'll touch back on it in the case studies. So happy learning ;)