Capstone_Yelp

Regarding keys in the dataset notebook

Contact @samomullane for active keys, unable to publicly declare these on github

Updated initial EDA databricks notebook:

https://databricks-prod-cloudfront.cloud.databricks.com/public/4027ec902e239c93eaaa8714f173bcfc/8566558053568016/3235680880483493/3484221038728175/latest.html

Uploaded a quick set for IL

/processed_data/numeric_ID_set_IL In this set, user_id and business_id are turned into numeric id's. This is mainly for social graph generation and simple searching. The python notebook will be uploaded, yet this kind of operation is MUCH faster using spark and databricks. The python notebook routine should be viewed as a backup approach.

Updated CF example notebook 6/11

Collabrative Filtering Example for the Capstone Project

https://databricks-prod-cloudfront.cloud.databricks.com/public/4027ec902e239c93eaaa8714f173bcfc/5289125420080101/3800886087298013/8301330479757772/latest.html

Some meta data is needed to play with this notebook, which have been added to /processed_data/

Snippets for Chao (business dataset cleaning)

https://databricks-prod-cloudfront.cloud.databricks.com/public/4027ec902e239c93eaaa8714f173bcfc/8566558053568016/4262012351773610/3484221038728175/latest.html

Updated NLP example notebook 6/14

Sentiment Analysis Notebook example

https://databricks-prod-cloudfront.cloud.databricks.com/public/4027ec902e239c93eaaa8714f173bcfc/2281281647728580/33322862051316/347222873603598/latest.html

Content based recommendation (NLP word2vec) example

https://databricks-prod-cloudfront.cloud.databricks.com/public/4027ec902e239c93eaaa8714f173bcfc/2281281647728580/33322862051354/347222873603598/latest.html

LDA

https://databricks-prod-cloudfront.cloud.databricks.com/public/4027ec902e239c93eaaa8714f173bcfc/2281281647728580/34326526546425/347222873603598/latest.html

Updated social network based example notebook 6/15

What did your friends say about nearby restaurants (example for LV)

This is a cleaner version of the social approach 6/16

https://databricks-prod-cloudfront.cloud.databricks.com/public/4027ec902e239c93eaaa8714f173bcfc/5289125420080101/3690050097713108/8301330479757772/latest.html