We’re pouring over Wine Reviews from 2020 using NLP

This image was created from wine reviews published in 2020 — Artwork generated by Tony Bosco

The pandemic locked most of us down in March 2020, and for the most part has altered our behavior ever since.

The way we work, the way we educate and learn, the way we communicate, the way we gather together, the way we are entertained, the way we shop… all upheaved.

In some instances, the pandemic drove innovation that was long, long overdue — such as in the wine industry.

Think about it…

  • The marketplace for alcoholic beverages was rapidly transformed by the pandemic, driving new models that reached quarantined consumers…


Using Selenium and NLP to harvest tokens from 2020’s wine reviews

This image was generated from wine reviews published in 2020 — Artwork by Tony Bosco

Welcome to Wrangling the Words of Wine 101!

As you will see, this post is about to combine a few of my favorite things…

  1. Using Selenium in Python to scrape a website, then manipulating our data in a Pandas DataFrame.
  2. Tapping into several Natural Language Processing tools to get to the tokenized essence of the data we scraped (which includes enhancing STOPWORDS, and using CountVectorizer and TF-IDF to identify the counts and weighted importance of each term in our documents).
  3. Leveraging Logistic Regression and Multinomial Naïve Bayes to test a prediction model, using terms against reviews to predict associated wine…


DS IN THE REAL WORLD

A tale of Terroir, Time, Toasts, and setting the Tableau

Photo by Jaime Casap on Unsplash

WARNING:

The following blog is best enjoyed with a glass or two of wine. Quite simply, the more wine you enjoy as you read this, the more brilliant I will sound, so do us both a favor and uncork a bottle now…

It’s okay, really…I’ll wait…

Ready?

Great! It’s time for…

Story Time

The wine country of Napa Valley, California is filled with incredible stories, and I am going to share one of my all-time favorites with you.

In 1827, the house of G.H. Mumm was founded in Reims, France. By 1876, the bottles of the champagne brand were adorned with a sash…


DS IN THE REAL WORLD

How to use two U.S. Databases (NOAA & USDA) to access climate records and soil surveys for your Data Science Project

Photo by Diego Romeo on Unsplash

I recently completed an analysis of climate and soil data for a blog about vineyards in Napa Valley, using two different U.S. Databases.

The websites for both databases are relatively straight forward. After speaking with a few peers, I was surprised that none of them had considered these sites for data before.

So if you are in need of data for an analysis on climate change, or if you are curious about the soil of a several geographic locations, or if you find Earth Day is just around the corner and you are feeling inspired for your next project and…


DS IN THE REAL WORLD

What a Data Science Immersive taught me about Collaboration, Culture, and Community

Photo by Perry Grone on Unsplash

I’ve had my share of experience leading teams in my career — from small tactical agency teams, to orchestrating complex international cross-functional teams to achieve annual goals for global brands.

I make it a point to learn from each experience, and to carry those lessons forward in a process of continuous improvement for the benefit of the organization, and for myself. I also believe it is important to challenge ourselves to learn new skills outside of the workplace, to add even more value to our working relationships.

I recently had the chance to do this by joining an intense Data…


DS IN THE REAL WORLD

For Our Current Coronavirus Culture

Photo by Fusion Medical Animation on Unsplash

Yes, it’s serious.

Yes, we should all take it seriously.

Yes, it’s hard to be distracted from it when you can’t go out and escape it, and every news program commandeers every station to talk about it.

Thank you, Coronavirus, for making us all extras in someone else’s big, scary, pandemic-themed horror movie and for making us all hunker down at home in whatever rooms are now serving as our own personal panic rooms.

It can be depressing…and yet, it doesn’t have to be.

If you think about it, it’s a huge opportunity as well.

You gain back some time.


DS IN THE REAL WORLD

With Selenium and Python

Photo by Akshay Chauhan on Unsplash

In my last post, I talked about web-scraping as a tool to help you keep an eye on competitive or pricing trends by extracting knowledge from related retail and e-commerce websites.

Today, we’ll take a closer look at that process. We’ll approach it in simple investigative terms (Who, What, Why, Where and How), as setting a strategy for your scrape will help you get through the process that much faster.

We’ll also share some tips for using Python, and the Selenium package, to gather your data and press it into a DataFrame you can manipulate.

Before you begin, you will…


DS in the Real World

How web scraping can increase your insight into the wine market

Photo by Scott Warman on Unsplash

Anyone who is actively engaged in the wine business knows how challenging it can be to keep up on all of the information needed to maintain a perspective on the marketplace.

Fortunately, thanks to data science, there are a few great tools that can make life easier by automating research and capturing web-based information that can be used in analysis of:

  • Varietal Trends: Looking over consumer demand, appellation, wine type, wine style, vintage
  • Wine ratings: Assessing Wine Spectator, Wine Enthusiast, or Vivino consumer ratings and other awards and acclaim
  • Competitive Analysis: Researching the brands and products in your category —…

Tony Bosco

As an experienced marketer and business consultant to global brands, Tony embraced Data Science to help them drive new insights and visualize opportunities.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store