September 12th, 2018

Automatic Feature Engineering for Text Analytics – The Latest Addition to Our Kaggle Grandmasters’ Recipes

RSS icon RSS Category: Data Science, Driverless AI, GPU, NLP

According to Kaggle’s ‘The State of Machine Learning and Data Science’ survey, text data is the second most used data type at work for data scientists. There are a lot of interesting text analytics applications like sentiment prediction, product categorization, document classification and so on.

In the latest version (1.3) of our Driverless AI platform, we have included Natural Language Processing (NLP) recipes for text classification and regression problems. Our platform has the ability to support both standalone text and text with other numerical values as predictive features. In particular, we have implemented the following recipes and models:

– **Text-specific feature engineering recipes**:
– TFIDF, Frequency of n-grams
– Truncated SVD
– Word embeddings

– **Text-specific models to extract features from text**:
– Convolutional neural network models on word embeddings
– Linear models on TFIDF vectors

A Typical Example: Sentiment Analysis

Let us illustrate the usage with a classical example of sentiment analysis on tweets using the US Airline Sentiment dataset from Figure Eight’s Data for Everyone library. We can split the dataset into training and test with this simple script. We will just use the tweets in the ‘text’ column and the sentiment (positive, negative or neutural) in the ‘airline_sentiment’ column for this demo. Here are some samples from the dataset:

Once we have our dataset ready in the tabular format, we are all set to use the Driverless AI. Similar to other problems in the Driverless AI setup, we need to choose the dataset and then specify the target column (‘airline_sentiment’).

Since there are other columns in the dataset, we need to click on ‘Dropped Cols’ and then exclude everything but ‘text’ as shown below:

Next, we will need to make sure TensorFlow is enabled for the experiment. We can go to ‘Expert Settings’ and switch on ‘TensorFlow Models’.

At this point, we are ready to launch an experiment. Text features will be automatically generated and evaluated during the feature engineering process. Note that some features such as TextCNN rely on TensorFlow models. We recommend using GPU(s) to leverage the power of TensorFlow and accelerate the feature engineering process.

Once the experiment is done, users can make new predictions and download the scoring pipeline just like any other Driverless AI experiments.

Bonus fact #1: The masterminds behind our NLP recipes are Sudalai Rajkumar (aka SRK) and Dmitry Larko.

Bonus fact #2: Don’t want to use the Driverless AI GUI? You can run the same demo using our Python API. See this example notebook.

Seeing is believing. Try Driverless AI yourself today. Sign up here for a free 21-day trial license.

Until next time,
SRK and Joe

About the Authors

Jo Fai Chow
Jo-Fai Chow

Jo-fai (or Joe) has multiple roles at H2O.ai. He is best known as the #360Selfie guy nowadays. On LinkedIn, he is the data science evangelist and community manager but everyone knows that his photography skills totally overshadow his data science knowledge these days. On Twitter, he sounds like a die-hard MATLAB fanboy with the handle @matlabulous (because MATLAB was his favourite tool at Uni). Since joining H2O.ai in 2016, Joe has delivered H2O talks/workshops in 40+ cities around Europe and US. Before joining H2O, he was in the business intelligence team at Virgin Media where he developed data products to enable quick and smart business decisions. He also worked remotely for Domino Data Lab as a data science evangelist promoting products via blogging and giving talks at external events.

Sudalai Rajkumar

Leave a Reply

Brief Perspective on Key Terms and Ideas in Responsible AI

INTRODUCTION As fields like explainable AI and ethical AI have continued to develop in academia and

April 2, 2020 - by Benjamin Cox
Three Ways Data and AI is Helping Against COVID19

We are in the midst of a global crisis that epidemiologists have warned us about.

April 1, 2020 - by Niki Athanasiadou
Modelling Currently Infected Cases of COVID-19 Using H2O Driverless AI

In response to the wake of the pandemic called COVID-19, H2O.ai organized a panel discussion

March 30, 2020 - by Marios Michailidis
Deploying Models to Maximise the Impact of Machine Learning — Part 1

Introduction to the 4 key pillars of considerations for model deployment (1st part of a

March 29, 2020 - by Stefan Pacinda and John Spooner
Igniting the AI in Healthcare Community

Yesterday we held our first Community Discussion on AI in Healthcare. Our CEO and founder,

March 28, 2020 - by David Engler
COVID-19: Doing Good with Data + AI

During times of severe societal strain, individuals have historically shown an inclination to offer aid

March 26, 2020 - by David Engler and Marios Michailidis

Join the AI Revolution

Subscribe, read the documentation, download or contact us.

Subscribe to the Newsletter

Start Your 21-Day Free Trial Today

Get It Now
Desktop img