Featured posts
We all see articles on how this is successful or that is successful and we get to brag about our successes. But what about when we fail? What about when it’s an #epicfail? I’ve gone through tons of code learning how to do machine learning for many types of things, but one thing intrigued me,…
Most of the time I’ve spent on Kaggle contests have been hyperparameter optimization. It’s a major part of deep learning and fine tuning if you hope to win or even getting into the top 10% for any contest or model building. Neural networks are quite difficult to configure and there are tons of parameters that need…
The NFL has created a competition in an attempt to reduce concussions on punt plays. Read more about the competition in my previous post. My proposal, see presentation here, is that the NFL stops allowing punt returns altogether. Where the punt lands is where the return team takes possession. This might sound extremely boring, but…
Recently, I entered the NFL Concussion on punt returns contest for data scientists. It wasn’t the normal machine learning problem. In fact, it is not machine learning at all. It is more true data analysis, which to be honest was much more fun. For the 2018 season, the NFL revised their kickoff rules in an effort to…
I don’t know why Google Colabs defaults to Python 2, regardless, it’s extremely easy to change your notebook to Python 3. It’s so easy I don’t even have more than one paragraph of words to write about how to do it. Here are the steps: Click on Runtime>Change Runtime Type From the Dropdown select Python…
If you are using Google Colabs it would make sense to want to pull in a CSV file for a machine learning project. It would further make sense that you would have some of this data in a Google Sheet. Since I started working on my Ohio Crime Data project, I started with inputting my…
Step one: Go to Google Cloud Platform and create a Project. Step two: Click Activate Cloud Shell Step three: In the console you will want to activate Google’s datalab package to setup your notebook. You do that by type in the following: gcloud components install datalab Step four: Next command is to type: datalab create (insert…
Often it seems like the biggest part of machine learning is actually acquiring and cleaning up data. The state of Ohio provides crime data in CSV format however the data cannot be used out of the box. I’m sure it is useful for someone but not for running predictions or even BI tools in its…
There are many ways to figure out which machine learning algorithm is the best for your dataset. One, you can just pick one and tweak the hyperparameters until you can’t tweak them anymore. And maybe you get lucky and choose wisely, or maybe you could have chosen something better. A better way is to let…
One of the most important aspects of running any machine learning program is the ability to pull in data from various sources and of various file types. In this tutorial I’ll walk you through how to pull various file types into notebooks using Python. The first file type that we will learn how to pull…