RankWell: Markov Chain Generation of Yelp Restaurant Reviews
a project by ericp
Updated almost 7 years ago. 2 hacker ♥️.

Ever left a restaurant wanting to write a review, but thinking it wasn't worth the trouble to tap out all those words on your phone -- you just want to give the place your n stars and provide a few words of praise or condemnation? If only you could press a button to generate a plausible review. If this project happens, you will.

We'll use the Yelp API to grab as many reviews of certain types of restaurants as the terms of service allow (I assume "Use any robot, spider, site search/retrieval application, or other automated device, process or means to access, retrieve, scrape, or index any portion of the Site or any Site Content;" doesn't apply to API users -- otherwise it wouldn't be much of an API).

We'll investigate libraries like spaCy for doing natural language processing (in Python).

We'll dive into the research on Markov Chains for Natural Language Generation

Finally we'll put this functionality on the web, using Flask & SQLAlchemy in front of a postgres database. The idea is to generate a sample review, and allow the user to easily tweak it and copy it to the clipboard, not to automatically post the reviews to Yelp.

Join this project

Looking for hackers with the skills:

python nltk webapps flask sqlalchemy

This project is part of:

Hack Week 15

Activity

  • almost 9 years ago: cschum liked this project.
  • almost 9 years ago: ericp added keyword "flask" to this project.
  • almost 9 years ago: ericp added keyword "sqlalchemy" to this project.
  • almost 9 years ago: ericp added keyword "python" to this project.
  • almost 9 years ago: ericp added keyword "nltk" to this project.
  • almost 9 years ago: ericp added keyword "webapps" to this project.
  • almost 9 years ago: ericp started this project.
  • almost 9 years ago: dmacvicar liked this project.
  • almost 9 years ago: ericp originated this project.


    • Comments

    • ericp
      almost 9 years ago by ericp | Reply

      Mixed results on the hack.

      On one hand, I learned how to use Python's nltk library to do natural language processing on the reviews, to the point that I could lex each word. nltk has parsing abilities as well, but I decided to see how far I could get with just lexing and statistical analysis. Also, the flask and sqlalchemy libraries were straightforward Python analogs of Ruby's sinatra and ActiveRecord/Sequel ORMs, nothing new here. And the Yelp API was straightforward to work with.

      The downside was that the Yelp API only exposed the first 10 words of three reviews for each business. If we assume the average business has 100 reviews of about 200 words each, this wasn't going to give me the data I needed. However, each review in the resource returned byhttps://api.yelp.com/v3/businessesBUSINESSID/reviews also contained a URL, and following that URL gave me the full text of 19 reviews.

      And apparently following that URL violated Yelp's general terms of service, but not the developers's ToS, and I was cut off after pulling down reviews for 350 restaurants. At least I randomized my selection procedure, so I ended up with a smattering of Mexican, Chinese, Japanese and American-style restaurants.

      The best generated sentence might have been one of the first: "I travel the bone tender." I also liked "My wife had the chipotle pancakes." But most of the sentences were grammatically incorrect, or made no sense, or both. I did try tweaking the Markov generator to use a mix of single-word and double-word prefixes, but given the lack of data, I ended the hack and went back to work.

    Similar Projects

    Improvements to osc (especially with regards to the Git workflow) by mcepl

    Description

    There is plenty of hacking on osc, where we could spent some fun time. I would like to see a solution for https://github.com/openSUSE/osc/issues/2006 (which is sufficiently non-serious, that it could be part of HackWeek project).

    Improve chore and screen time doc generator script `wochenplaner` by gniebler

    Description

    I wrote a little Python script to generate PDF docs, which can be used to track daily chore completion and screen time usage for several people, with one page per person/week.

    I named this script wochenplaner and have been using it for a few months now.

    It needs some improvements and adjustments in how the screen time should be tracked and how chores are displayed.

    Goals

    • Fix chore field separation lines
    • Change screen time tracking logic from "global" (week-long) to daily subtraction and weekly addition of remainders (more intuitive than current "weekly time budget method)
    • Add logic to fill in chore fields/lines, ideally with pictures, falling back to text.

    Resources

    tbd (Gitlab repo)

    Bring to Cockpit + System Roles capabilities from YAST by miguelpc

    Bring to Cockpit + System Roles features from YAST

    Cockpit and System Roles have been added to SLES 16 There are several capabilities in YAST that are not yet present in Cockpit and System Roles We will follow the principle of "automate first, UI later" being System Roles the automation component and Cockpit the UI one.

    Goals

    The idea is to implement service configuration in System Roles and then add an UI to manage these in Cockpit. For some capabilities it will be required to have an specific Cockpit Module as they will interact with a reasource already configured.

    Resources

    A plan on capabilities missing and suggested implementation is available here: https://docs.google.com/spreadsheets/d/1ZhX-Ip9MKJNeKSYV3bSZG4Qc5giuY7XSV0U61Ecu9lo/edit

    Linux System Roles:

    First meeting Hackweek catchup

    Liz - Prompt autocomplete by ftorchia

    Description

    Liz is the Rancher AI assistant for cluster operations.

    Goals

    We want to help users when sending new messages to Liz, by adding an autocomplete feature to complete their requests based on the context.

    Example:

    • User prompt: "Can you show me the list of p"
    • Autocomplete suggestion: "Can you show me the list of p...od in local cluster?"

    Example:

    • User prompt: "Show me the logs of #rancher-"
    • Chat console: It shows a drop-down widget, next to the # character, with the list of available pod names starting with "rancher-".

    Technical Overview

    1. The AI agent should expose a new ws/autocomplete endpoint to proxy autocomplete messages to the LLM.
    2. The UI extension should be able to display prompt suggestions and allow users to apply the autocomplete to the Prompt via keyboard shortcuts.

    Resources

    GitHub repository

    Collection and organisation of information about Bulgarian schools by iivanov

    Description

    To achieve this it will be necessary:

    • Collect/download raw data from various government and non-governmental organizations
    • Clean up raw data and organise it in some kind database.
    • Create tool to make queries easy.
    • Or perhaps dump all data into AI and ask questions in natural language.

    Goals

    By selecting particular school information like this will be provided:

    • School scores on national exams.
    • School scores from the external evaluations exams.
    • School town, municipality and region.
    • Employment rate in a town or municipality.
    • Average health of the population in the region.

    Resources

    Some of these are available only in bulgarian.

    • https://danybon.com/klasazia
    • https://nvoresults.com/index.html
    • https://ri.mon.bg/active-institutions
    • https://www.nsi.bg/nrnm/ekatte/archive

    Results

    • Information about all Bulgarian schools with their scores during recent years cleaned and organised into SQL tables
    • Information about all Bulgarian villages, cities, municipalities and districts cleaned and organised into SQL tables
    • Information about all Bulgarian villages and cities census since beginning of this century cleaned and organised into SQL tables.
    • Information about all Bulgarian municipalities about religion, ethnicity cleaned and organised into SQL tables.
    • Data successfully loaded to locally running Ollama with help to Vanna.AI
    • Seems to be usable.

    TODO

    • Add more statistical information about municipalities and ....

    Code and data

    Collection and organisation of information about Bulgarian schools by iivanov

    Description

    To achieve this it will be necessary:

    • Collect/download raw data from various government and non-governmental organizations
    • Clean up raw data and organise it in some kind database.
    • Create tool to make queries easy.
    • Or perhaps dump all data into AI and ask questions in natural language.

    Goals

    By selecting particular school information like this will be provided:

    • School scores on national exams.
    • School scores from the external evaluations exams.
    • School town, municipality and region.
    • Employment rate in a town or municipality.
    • Average health of the population in the region.

    Resources

    Some of these are available only in bulgarian.

    • https://danybon.com/klasazia
    • https://nvoresults.com/index.html
    • https://ri.mon.bg/active-institutions
    • https://www.nsi.bg/nrnm/ekatte/archive

    Results

    • Information about all Bulgarian schools with their scores during recent years cleaned and organised into SQL tables
    • Information about all Bulgarian villages, cities, municipalities and districts cleaned and organised into SQL tables
    • Information about all Bulgarian villages and cities census since beginning of this century cleaned and organised into SQL tables.
    • Information about all Bulgarian municipalities about religion, ethnicity cleaned and organised into SQL tables.
    • Data successfully loaded to locally running Ollama with help to Vanna.AI
    • Seems to be usable.

    TODO

    • Add more statistical information about municipalities and ....

    Code and data