This is the code for "How to Make a Prediction - Intro to Deep Learning #1' by Siraj Raval on YouTube
Python
Switch branches/tags
Nothing to show
Clone or download
Latest commit 6e274ef Jan 13, 2017
Permalink
Failed to load latest commit information.
README.md Update README.md Jan 13, 2017
brain_body.txt Add files via upload Jan 13, 2017
challenge_dataset.txt Add files via upload Jan 13, 2017
demo.py Create demo.py Jan 13, 2017
requirements.txt Update requirements.txt Jan 13, 2017

README.md

linear_regression_demo

This is the code for "How to Make a Prediction - Intro to Deep Learning #1' by Siraj Raval on YouTube

##Overview This is the code for this video by Siraj Raval on Youtube. This is the 1st episode in my 'Intro to Deep Learning' series. The goal is to predict an animal's body weight given it's brain weight. The model we'll be using is called Linear Regression. The dataset we're using to train our model is a list of brain weight and body weight measurements from a bunch of animals. We'll fit our line to the data using the scikit learn machine learning library, then plot our graph using matplotlib.

##Dependencies

  • pandas
  • scikit-learn
  • matplotlib

You can just run pip install -r requirements.txt in terminal to install the necessary dependencies. Here is a link to pip if you don't already have it.

##Usage

Type python demo.py into terminal and you'll see the scatter plot and line of best fit appear.

##Challenge

The challenge for this video is to use scikit-learn to create a line of best fit for the included 'challenge_dataset'. Then, make a prediction for an existing data point and see how close it matches up to the actual value. Print out the error you get. You can use scikit-learn's documentation for more help. These weekly challenges are not related to the Udacity nanodegree projects, those are additional.

Bonus points if you perform linear regression on a dataset with 3 different variables

##Credits

The credits for the original code go to gcrowder. I've merely created a wrapper to get people started.