Tiankai-Jiang / Yelp-Dataset

Relational database of yelp dataset, simple flask server client and data mining.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Yelp-Dataset

A project to

  • build relational database of yelp dataset using MySQL

  • build a simple server-client using Flask

  • perform data mining on the dataset(data visualization and classification on user comments)

Dependencies

  • Python3

  • mysql-connector-python

  • Flask

  • prettytable

  • numpy

  • seaborn

  • pandas

  • geopandas

  • sklearn

  • wordcloud

Usage

  • 01 and 02: Data preprocessing and extraction

  • 03: Dump data to mysql

  • 04: Flask server and client

  • 05: Data mining

The dataset is too large to be uploaded. The directory structure was exported in directory_structure.txt for reference.

Demo

Detailed implementation and analysis can be found in 06_report/report.pdf

ER Diagram

ER_Diagram

Commandline Client

client1 client2 client3

Some plots

Distribution_Restaurants

Distribution_Locations

Distribution_CheckinTime

Confusion_Matrix

Word_Cloud

About

Relational database of yelp dataset, simple flask server client and data mining.


Languages

Language:Jupyter Notebook 95.9%Language:Python 2.2%Language:TeX 1.6%Language:TSQL 0.3%