Predicting House Prices with the Ames Dataset
This problem is fairly simple to describe… given a bunch of variables that describe the various aspects of a house along with a sales price, is it possible to come up with a mathematical model that can be used to predict future prices based on different values of the same variables? It is based housing sales data …
Classifying the Fashion-MNIST dataset…
First the overall goal should be mentioned… the aim create a model that will classify small images of clothing items. That is, by learning patterns from a set of 60,000 labelled training images, it is possible to predict the category from 10,000 unseen images. The MNIST dataset is good as an introductory dataset, however there are some …
Non-Linear Regression… using Python, Javascript, NumPy, and TensorFlow
This is a continuation to the previous linear regression document. However this time the focus is on a few different ways to perform non-linear regression using Javascript and various Python frameworks (such as NumPy, SciKitLearn, and TensorFlow). Quadratic Regression Perhaps this is the first logical step beyond linear regression. A parabola of best fit is …
Python Linear Regression with SciPy, SciKitLearn, TensorFlow1, and TensorFlow2
This is more of a reference for myself on the multitude of ways that something as computing simple linear regression can be done with Python, SciKitLearn, TensorFlow1, and TensorFlow2. Also, this is a bit of a stepping stone type of project, where the next steps involve non-linear regression, multi-non linear regression in the form of …
Having fun with the Titanic Problem… Machine Learning from the Disaster
This is originally a Kaggle problem where the task is: to build a predictive model that answers the question: “what sorts of people were more likely to survive?” using passenger data (ie name, age, gender, socio-economic class, etc). The data is broken into train and test sets in a ratio of approximately 68 to 32 …