abstractive-text-summarization-enhancing-sequence-to-sequence-models-using-word-sense-disambiguatio

This repository contains code and resources for abstractive text summarization (TS) using a novel framework that leverages knowledge-based word sense disambiguation (WSD) and semantic content generalization to enhance the performance of sequence-to-sequence (seq2seq) neural-based TS.

alexa-reviews-sentiment-prediction-model

a classification model to predict the sentiment either (1 or 0) based on Amazon Alexa reviews

autogen

Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

bbc-dataset-news-classification

bbc-news-classification-using-hugging-face

classify news into five categories: business, entertainment, politics, sport, and tech.

bmail-project

canada-immegrant-dataset-analysis-

project to analyze data of immegrants from india and china to canada since 1980's until 2013

classification-mobile-price-analysis-

Create a classification model to predict whether price range of mobile based on certain specifications

clone_video_gen_application

generate clone videos for digital marketing

clumoss

AI Intern projects task repo

codeclause_covid_analysis_task1

an analysis of covid pandemic dataset of USA

coffee-machine-project

1. Prompt user by asking “ What would you like? (espresso/latte/cappuccino): ” a. Check the user’s input to decide what to do next. b. The prompt should show every time action has completed, e.g. once the drink is dispensed. The prompt should show again to serve the next customer. 2. Turn off the Coffee Machine by entering “ off ” to the prompt. a. For maintainers of the coffee machine, they can use “off” as the secret word to turn off the machine. Your code should end execution when this happens. 3. Print report. a. When the user enters “report” to the prompt, a report should be generated that shows the current resource values. e.g. Water: 100ml Milk: 50ml Coffee: 76g Money: $2.5 4. Check resources sufficient? a. When the user chooses a drink, the program should check if there are enough resources to make that drink. b. E.g. if Latte requires 200ml water but there is only 100ml left in the machine. It should not continue to make the drink but print: “ Sorry there is not enough water. ” c. The same should happen if another resource is depleted, e.g. milk or coffee. 5. Process coins. a. If there are sufficient resources to make the drink selected, then the program should prompt the user to insert coins. b. Remember that quarters = $0.25, dimes = $0.10, nickles = $0.05, pennies = $0.01 c. Calculate the monetary value of the coins inserted. E.g. 1 quarter, 2 dimes, 1 nickel, 2 pennies = 0.25 + 0.1 x 2 + 0.05 + 0.01 x 2 = $0.52 6. Check transaction successful? a. Check that the user has inserted enough money to purchase the drink they selected. E.g Latte cost $2.50, but they only inserted $0.52 then after counting the coins the program should say “ Sorry that's not enough money. Money refunded. ”. b. But if the user has inserted enough money, then the cost of the drink gets added to the machine as the profit and this will be reflected the next time “report” is triggered. E.g. Water: 100ml Milk: 50ml Coffee: 76g Money: $2.5 c. If the user has inserted too much money, the machine should offer change. E.g. “Here is $2.45 dollars in change.” The change should be rounded to 2 decimal places. 7. Make Coffee. a. If the transaction is successful and there are enough resources to make the drink the user selected, then the ingredients to make the drink should be deducted from the coffee machine resources. E.g. report before purchasing latte: Water: 300ml Milk: 200ml Coffee: 100g Money: $0 Report after purchasing latte: Water: 100ml Milk: 50ml Coffee: 76g Money: $2.5 b. Once all resources have been deducted, tell the user “Here is your latte. Enjoy!”. If latte was their choice of drink.

datastructures

contain all error-free programs for data structures and algorithms

dsa-workshop

A workshop organized by Tech-Cult to learn and practice DSA

easy-note-for-js-python-react

contains note for python,

ecommerce-website-customer-churn-data-analysis

given an ecommerce website I have to perform data analysis on customer churn and extract insights from it

face-extractor

Python script that detect faces on the image or video, extracts them and saves to the specified folder

google-cloud-genrative-ai

This repos contains notebooks for the Advanced Solutions Lab: ML Immersion

gpt-pilot

Dev tool that writes scalable apps from scratch while the developer oversees the implementation

hello-world

pahili repository

higer-lower-game

A game that gets two random Instagram account and asks user who has more followers.

ice-sejj

Introducing Ice-Sejj: Your Ultimate NLP and Machine Learning Solution

imageclassification

Jupyter notebook showing how to build an image classifier with Python and Tensorflow

largelanguagemodelsprojects

Large Language Model Projects

llmspracticalguide

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

machine-learning-projects

This Contain Some Machine Learning Projects that I have done while understanding ML Concepts.

mr_disrespect.ai

it is a chatbot project that generates disrespectful reply each time you have a conversation with it

privategpt

Interact with your documents using the power of GPT, 100% privately, no data leaks

priyansh4320

priyansh4320.github.io

portfolio