I worked for some time on different machine learning projects and writing blogs. But now, what I really wanted is to learn how to deploy a machine learning model. Well, what I really really wanted is to build an app for people to use. It’s all about making your work available to end-users, right? So yes, this post is all about deploying my first machine learning model. I am super excited about the results!
We will create a web page that will contain a search box like below and a “Go” button. …
Have you ever meet a Chatbot or chatterbot? Of course, you have! It is everywhere nowadays. I have met an annoying one, a smart one, and even a kind one. So, let’s start at the very beginning and go step by step from there to build a simple stupid one.
How I define this is:
A chatbot is a human-less solution for answering a question or resolving a complaint or communicating with brands or just a personal assistant without a body.
Now, how wiki defines it is:
A chatbot is a software application used to conduct an online chat conversation…
An expression that caught my attention recently is:
Data is the new oil.
I am not sure who used the term for the first time and who should get the credit for this. But, the quote is so appropriate! Mining or refining is a vital component of DATA. To transform the raw data into some useful insights is a key to some effective business strategies. In this whole process, SQL plays an important role. So, this post is all about data and SQL.
Sometimes, I like to challenge myself with SQL. Hackerank is a very good place for that. But…
Were you a fan of Donald Trump’s tweets? On a boring gloomy day, did you browse through his tweets to get your share of entertainment? Do you miss him on Twitter? Well, I do! So, I was wondering if all those complex deep learning algorithms can learn and get trained to generate some tweets in Donald Trump style. Does that sound fascinating to you? If the answer is “Yes”, then you are on the right page.
Well, I have a huge list of my favorites, and it is very difficult to choose just one. …
I created my first Deep Learning Model to generate Text using LSTM. The basic model ran for a few hours on my macOS Sierra (10.12.6). Let’s put it this way — the results were not so satisfactory. So, I became ambitious and thought of running a model with lots of layers — a deep and wider model. It turned out that was really me being over-ambitious. Initially, it displayed an ETA of 60 hours. I let it run for 2 days and 2 nights. Then, the next morning, I woke up and checked my kernel was dead!
After that heart-breaking…
Deep Learning is a topic that I had been avoiding for some time now. Somehow, its potential is intimidating. I always felt that Deep Learning Models are complex and not-so-easy to work with on my Mac OSx. I was worried that I will not be able to fit a Model and then finally see some output. But then, I built a Deep Learning Model to Generate Text or a Story using Keras LSTM with a very little glitch.
Do you work in Jupyter Notebooks and have an issue in installing and hence importing Keras? Well, you are at the right place.
I was in the same boat a few days back. I struggled for a few hours and could not get a breakthrough and gave up that day. The next day, I again started with a different approach and it clicked!
Just a disclaimer I work on Mac OSx Sierra(10.12.6) and this post is all about installing Keras and importing Keras in Jupyter Notebook.
So, first I did what I usually do to install any library.
I am in awe of Scikit-learn. I have always used scikit-learn for data modeling and metrics. But I had no idea how diverse and useful this library can be! So, this post is all about gazing and praising Scikit-learn.
Now, if you are the skeptical one and have not yet explored its possibilities, you must be thinking ‘ what is this fuss all about? ‘ So, let me tell you my reasons for this obsession.
Still not convinced? Now, it's time to demonstrate its versatility.
Data is the essence of any machine learning algorithm, right? Now, real-world data is messy…
Deploying an application on Heroku was a bit challenging. Although there are a lot of great posts and tutorials, I was facing issues at every step. But then, I was trying to do something different. I wanted to navigate through multiple HTML pages and gel the HTML, Python, and FLASK together on HEROKU. Well finally, it worked out all fine, and below are the details of my Twitter Sentiment Analysis application.
First, let me tell you how this Heroku application actually works.
While running a Flask application initially, an error that popped up, again and again, is :[Errno 98] Address already in use
The flask error is quite clear, but the resolution was not!
When you are running FLASK and building an application, you may forget, or sometimes you could not close that application. Thus re-running your application on localhost may end up in this error.
I usually work on Jupyter Notebook on my MAC and sometimes on the python terminal. I tried to find the running session and kill those but eventually ended up killing my up-and-running Jupyter Notebook session. …