How_to_Make_Data_Amazing
This is the code for the "How to Make Data Amazing - Intro to Deep Learning #5" by Siraj Raval on Youtube
##Overview
This is the code for this video on Youtube by Siraj Raval as part of the Intro to Deep Learning Udacity nanodegree. I demo'd 3 different datasets in the video, and both notebooks are here. The 3rd demo isn't here because the original author deleted it in the middle of me making this weekly video. We talk about the 3 key steps to data preprocessing (cleaning, transformation, and reduction). We also talk about a popular dimensionality reduction technique called Principal Component Analysis.
##Dependencies
- plotly
- seaborn
Use pip to install missing dependencies. And install jupyter to run these notebooks if you haven't.
##Usage
You can run this code by typing jupyter notebook into terminal when you are in the main directory. You'll be able to see both notebooks in the browser that pops up.
#Challenge - Due Date, Thursday February 16th, 2017 at 12 PM PST
The coding challenge for this video is to use this speed dating dataset to predict if someone gets a match or not. This dataset is labeled so 1 means they got a match and 0 means they didn't. Build a neural network capable of predicting a match given a new person. You can use any library you like, bonus points if you do this from scratch using only numpy. Record any data preprocessing steps you took in your README. Good luck!
##Credits
The credits for this code go to arundasan91 and gfleetwood. I've merely created a wrapper to get people started.