Digests » 46
this week's favorite
With the advent of excellent DL libraries and plethora of open-source implementations and papers, Image Classification is very easy to implement. That is, if you have the dataset. There are plenty of open datasets available to test and refine classification models. But obtaining a task specific dataset is tough. Nudity/ NSFW detection is one such use-case where there are no practically useful open datasets available.
This post is the fourth post of the NLP Text classification series. To give you a recap, I started up with an NLP text classification competition on Kaggle called Quora Question insincerity challenge. So I thought to share the knowledge via a series of blog posts on text classification.
As newbie when we used to learn Deep Neural Networks(DNN) we directly used to get the data ready in training and testing for example (MNIST hand written data set )to pass in our Neural Networks but here we will prepare out coming data and fit in our Neural Network.
A study regarding data science jobs showed that 60% of the time spent by data scientists consists only on cleaning and organizing data. So in order to make the most out of our time, my data science fellas, in this four-part series we’ll se how to preprocess data like a boss, using the Pandas Python library and the preprocessing module from scikit-learn.