This post explains how to use Jupyter notebooks in Docker containers alone.
Usually, as a Data Scientist, Jupyter Notebook is the primary form of communication that we use (Still got a fair amount of reputation despite Colab’s brilliance).
If you needed to set that up, all you are going to need is this:
$ conda create -n py38env anaconda
$ conda activate py38env
(py38env)$ jupyter notebook
This sets up a new environment with all the Anaconda bells and whistles🔔 like Spyder, Anaconda Navigator…
This post explains what Vectorization is and how Vectorhub can help with that
Whenever you are in work related to Natural Language Processing(NLP), you definitely will have come across the word:
What does it mean and what does VectorHub do to help you in that?
Let me tell you:
Word Vectorization or just Vectorization is the process of mapping words in a text to a corresponding vector of real numbers.
Vectors have a good number of use cases such as word prediction, text similarity, and so on.
You can look into the following article to learn more about…
The word in the title probably might have you thinking I made a grammatical error there but hear me out, it isn’t.
This post explains about a package I had created which will help in converting images into a single format and rename them easily.
When I was tasked to do binary classifier for images, we did not have a ready-made data for the given requirements.
So we had to collect images on our own to get the data(It was a pretty small dataset so we didn’t have to stress on it that much). We set a target of just 100 images and a split of about 80/20 for the train and validation respectively.
The web being how it is, we managed…
Ever had a situation where you have been learning something and wanted to try to implement it practically but never have any kind of idea on what you want to do?
Well, then you are looking through the right article cause this place has you covered.
This is a place for ML enthusiasts. Here, you can work on small projects (called features) that are real-world requirements. Yes, you can work with real-world requirements direct from employers.
Think of it as a freelancer site but only for ML/DS enthusiasts.
Employers provide their requirements in the site and volunteers(can be you here)…
Internships. A phase of learning in every person’s life where we can prove our skills as a person and I got a chance to show exactly that and boy was it a good one.
My college St. Joseph’s College of Engineering announced an internship happening at this company called TactLabs led by the amazing Raja CSP Raman for 3 months from July to October.
First, there was this introductory session where they talked about what they do at the company and I completely missed it so I can’t talk about that all too much (Quarantine messed me up…
This post shows what knowledge graphs are and how they help along with an example of knowledge graphs using Python
You open up Google and start typing something you want to look up. You type the term you need to find (Me being a football/soccer fan I am going to say Manchester United). You hit Enter and you’re filled to the brim with at least a billion results of whatever you typed and in record speed too (<1 second to be precise).
The big question here is:
How is it possible?
Google uses something called a Knowledge graph to relate…
You might be thinking I messed up the heading with a well-known movie but I did not. Salagar means lightning and you will not find that translation anywhere even if you tried.
So what am I even talking about?
Salagar’s Test is a Feature that we developed during my internship at Tactlabs with my good friend Kamal as part of Featurepreneur which I will explain at the end.
This feature was to help the company assess people on how strong they are in their libraries in Data Science such as Pandas, Numpy, etc.
This had to be done in a…
This article explains how I used Allen NLP to predict what happened to a certain character in Friends
There’s no denying that Friends is the GOAT of TV shows (Don’t even try to change my mind). More recently, I’ve been looking into a lot of NLP use cases and Allen NLP came up recently. So, what I decided to find out was: Can one of the GOATs of NLP models predict answers to things that happened in Friends: The GOAT of TV shows. Let’s find out.
The model I am going to be using is a BiDAF model with ELMO…
Us humans know how to differentiate entities(i.e objects) easily. There has been a necessity for machines to know this. Why? If a machine can do this we don’t need to do things like this by ourselves.
Enter NER a.k.a Named Entity Recognition which is a default model available in the Spacy package in Python. Spacy can be best described as a more souped-up version of nltk which has a built-in NER model for us to use. How do we use it? Let’s find out below
First, we need Spacy(How can we do it without that?)