Introduction¶

Since I upgraded my desktop and added a gtx 1070 graphics card, I have been having tons of fun training models in Tensorflow and XGBoost using my GPU and have been enjoying the multiple factors of speedup training time versus training on my CPU. On top of that, I have been enjoying gaming on my pc with the 1070 as well.

One of the first notebooks I uploaded was my analysis on the animal outcome dataset for the Austin Animal Shelter. Recently, I ran across their open data set on Austin's open data government website: https://data.austintexas.gov/. The dataset on this site included both intake and outcome data which the dataset hosted on Kaggle did not have. The data on Kaggle was only the outcome dataset. I was very interested in how much the intake data would help improve results so we will run a similar analysis but now integrate both the intake and outcome data and also add some data visualizations. Both the intake and outcome dataset contain data from 2013 to 2017.

In my last notebook, I used a multilayer perceptron network (MLP) for classification using the MNIST dataset. For this notebook, I will apply a Convolutional Neural Network to the same dataset and see how this network performs| compared to the MLP.

Multilayer Perceptron¶

So I recently upgraded my desktop and now that I have a gtx 1070 card, I really wanted to get my hands on deep learning using my gpu. The library that I have decided to go with is Tensorflow. Tensorflow is a graph computation/deep learning library developed by Google. Tensorflow also has support for running on the gpu so that we can train larger and faster networks. This notebook will run through will include building a multilayer perceptron model on the classic MNIST dataset.

Motivation¶

It has been a year or two since I have done any analysis involving recommendation systems so I wanted to shake off the rust and dive into building a recommendation system for movies. At the end of the day, it will let me practice and since I am on break and have some free time, it doesn't hurt to have a working recommendation system so I have a good list of movies to watch.

Analysis Topic:¶

One topic that has been discussed recently in baseball is the third time through the order penalty (TTOP). Third time through the order penalty is simply the theory that a pitcher is less effective when he goes through the lineup of batters twice and faces each batter for the third time.

Austin Animal Shelter¶

Animal welfare is something that is really close to my heart so I am really excited to go through this dataset for analysis. This data was posted on Kaggle but I did not discover the dataset until after the competition expired. The goal posted by Austin Animal Shelter for this data was to predict the outcome of each animal.

Background information¶

With the support of the Institutional Research Department at Long Beach City College, I was given 10 years of college wide student data to provide them with any insights. For the purpose of privacy, the data will not be displayed in this notebook. However, I can provide desciptions and the variables that are being used along with results from the analysis. The data was given to me in three tables, enrollment, miscellaneous, and awards.