PhD Student at UMBC - Healthcare AI and Computer Vision
amazon
I'm teaching myself TensorFlow and Keras. The entire principle of using data flow graphs and deep learning is really fascinating, but it's a learning curve for sure. I've been poking around the MNIST tutorial, and tried my hand at hacking some TensorFlow scripts like
sklearn
In this final task, my goal is to predict the Amazon score (1 - 5) based on the reviews - a multiclass text classification problem. This post discusses the use of five pipeline models using scikit learn. The next post will introduce using Keras for building a sequential model for
textblob
In Part I we did some exploratory analysis after using the TextBlob package to apply sentiment scores using its polarity method. We found the mean sentiment was around .24 and then spilt up the dataframe into five calendar years of review from 2008 to 2012, getting a better sense of
NLP
Now that we know a little about the extremes of perfectly positive and negative sentiment reviews, let's analyze some key features of the text. Here we'll allow a user to retrieve the top 25 text features based on inputting an Amazon Score of 1 to 5
sentiment
Ok, so now that we explored the contents of the Amazon Fine Reviews data file, it's time to move on to the second task: How many reviews and products are perfectly positive and perfectly negative in sentiment? TextBlob assigns a polarity value from -1.0 to +1.0,
amazon
It takes time to take advantage of all the great data science/ML resources out there like Coursera, Udacity, HackerRank, and Kaggle competitions. I won't bore you with the details, but granted that life sometimes gets in the way, one of my goals is to get into Kaggle
census
Using data from the American Community Survey, I analyzed the disparity of male over female veteran and non-veteran median income. Which states have the greatest disparity in income between the sexes? This post begins merely the exploration journey. The dataset: B21004: MEDIAN INCOME IN THE PAST 12 MONTHS (IN 2015
fake data
I ran into a pretty neat fake name generator that also generates fake addresses in different languages, called Faker: https://pypi.python.org/pypi/Faker. Using Faker, I generated a set of fake data to mock up a scenario of predicting end-of-year employee bonuses for 200 employees based on their
classification
In a project two years ago, I wrote a basic Naive Bayes classification script, largely from this tutorial [http://scikit-learn.org/stable/tutorial/text_analytics/working_with_text_data.html] off of scikit-learn's site, which was pretty much all that I needed. I typically use a private company
tensorflow
I'm definitely no where close to a deep learning expert. But, I'm pretty curious and interested to learn more about it and how I could start using it for "everyday" business problems. Decided to get started this morning and delve into the first TensorFlow