collection and short reviews of interesting streamlit applications

Streamlit application listing

Introduction:

Streamlit is an up and coming platform for hosting data apps with pythonic format to write them up. You don't need to know anything about tough and complicated web frameworks like django and flask and yet you can host your data apps using streamlit from now on. I created a streamlit application and released tutorials on starting up with streamlit and also how to design different components of apps in streamlit. Now I have connected with a few streamlit enthusiasts via that and have been seeing really cool apps being created with streamlit.

So in this post, I will post some of the cool streamlit apps I find in internet. Later on I may add descriptions for some of these.

NLP apps:

(1) nlp app for sentiment detection, tokenization and number of nlp actions

(2) my spacy streamlit app works on spacy, does dependency parsing, entity tagging and pos tagging.

Stock apps:

(1) stock analysis app:

This is written by one of my open-source friends and data developer, EE ajaegbu. This application creates and plots different charts, calculates number of metrics like alpha etc for stocks of different companies.

Code generator apps:

Let's look at this cool code generator app. This is written by johannes Rieke, a cool deep learning engineer. This application lets you create sklearn, pytorch codes for image classification, object detection.

Gravitational wave app:

This app is huge. Check out the latest post on streamlit's blog by Jonah Kanner and Jameson Rollins of the LIGO Laboratory, California Institute of Technology and Leo Singer of the NASA Goddard Space Flight Center on making exploring gravitational waves in deep space accessible to students 🛰️

I also wanna thank Mr. Ted TC Rick for helping in building this list as he points out kickass streamlit apps all the time.

Educational data exploration app:

check the following App on exploring US education data. This is created using US education data; and this app lets you predict the grade score given the main inputs using slider.

Streamlit based encryption app:

check this application built by immeonizer in streamlit, which helps us do text encryption using streamlit. it uses a python package named imcrypt; and let's you encrypt strings.

application with neural search:

This app is created by jina researcher alex to show off the power of jina, the neural search framework. Jina ai is a great neural search tool which employs the power of neural network based embeddings to power image, text and mixed search methods. In the application, alex shows the power of jina by implementing a search across around 10000 playstore and applestore applications. Check the app to know more about jina and streamlit. Specialties also lie in advanced style implementation in the front end code of the app. do check it out!

Application with showcasing streamlit theming! [new at 2021 19th march]

This app developed by streamlit showcases the theming feature. theming allows you to use all sorts of fancy css, html stylings without you ever touching the front end code. Check the app and its code for further understanding!

This post will not have any end. I encourage you to send me cool streamlit app links and I will write about them here. Let's create a great streamlit starter collection here.

Tinder bio generation with OpenAI GPT-3 API

Introduction: Recently I got access to OpenAI API beta. After a few simple experiments, I set on creating a simple test project. In this project, I will try to create good tinder bio for a specific person. The abc of openai API playground: In the OpenAI API playground, you get a prompt, and then you can write instructions or specific text to trigger a response from the gpt-3 models. There are also a number of preset templates which loads a specific kind of prompt and let's you generate pre-prepared results. What are the models available? There are 4 models which are stable. These are: (1) curie (2) babbage (3) ada (4) da-vinci da-vinci is the strongest of them all and can perform all downstream tasks which other models can do. There are 2 other new models which openai introduced this year (2021) named da-vinci-instruct-beta and curie-instruct-beta. These instruction models are specifically built for taking in instructions. As OpenAI blog explains and also you will see in our

Can we write codes automatically with GPT-3?

Introduction: OpenAI created and released the first versions of GPT-3 back in 2021 beginning. We wrote a few text generation articles that time and tested how to create tinder bio using GPT-3 . If you are interested to know more on what is GPT-3 or what is openai, how the server look, then read the tinder bio article. In this article, we will explore Code generation with OpenAI models. It has been noted already in multiple blogs and exploration work, that GPT-3 can even solve leetcode problems. We will try to explore how good the OpenAI model can "code" and whether prompt tuning will improve or change those performances. Basic coding: We will try to see a few data structure coding performance by GPT-3. (a) Merge sort with python: First with 200 words limit, it couldn't complete the Write sample code for merge sort in python. def merge(arr, l, m, r): n1 = m - l + 1 n2 = r- m # create temp arrays L = [0] * (n1) R = [0] * (n

What is Bort?

Introduction: Bort, is the new and more optimized version of BERT; which came out this october from amazon science. I came to know about it today while parsing amazon science's news on facebook about bort. So Bort is the newest addition to the long list of great LM models with extra-ordinary achievements. Why is Bort important? Bort, is a model of 5.5% effective and 16% total size of the original BERT model; and is 20x faster than BERT, while being able to surpass the BERT model in 20 out of 23 tasks; to quote the abstract of the paper, ' it obtains performance improvements of between 0 . 3% and 31%, absolute, with respect to BERT-large, on multiple public natural language understanding (NLU) benchmarks. ' So what made this achievement possible? The main idea behind creation of Bort is to go beyond the shallow depth of weight pruning, connection deletion or merely factoring the NN into different matrix factorizations and thus distilling it. While methods like knowle

Machine learning and statistics with python

Search This Blog