Abrar Fahim's repositories
Covid_data_preparation
Gathered data from different sources and merged them together (e.g. daily covid data, country demographic data, and daily airplane passenger movement data) and created a master dataset for further analysis of the virus spread during the covid-19 pandemic.
CallofBurger-JavaGame
Undergrad Java project. A game where a running player has to ignore eating junk food found on the running path. The more avoiding junk food, the more score will be added.
Machine-Learning
Python implementation of different Machine Learning Algorithms. Principal Component Analysis, DBSCAN, Kmeans, KNN, Tree, SVM, Hierarchical Clustering
Predicting-Food-Ratings-Based_on_Recipe_Data
Used sentiment analysis on customers' reviews for understanding its effects on food ratings. Used PCA for dimension reductions. Applied three regression algorithm to predict the ratings of a food recipe.
Best-README-Template
An awesome README template to jumpstart your projects!
Bing-COVID-19-Data
A repo for coronavirus related case count data from around the world. The repo will be regularly updated.
Large-Language-Model
This repository contains Zero, Few shot Inference, Fine Tuning a Large Language Model For Document Summarization, and lot more is coming...
Natural-Language-Processing
This repo contains different types of NLP problems I explored. It ranges from text processing techniques, different types of embeddings, Multiclass classification of text, Sentiment analysis to different Transformer architectures.
School_Data_Visualization
Analyzed A-level student data from the UK govt. database. Used clustering to find similar Schools. Designed interactive Dashboards using Tableau and Microsoft PowerBI.
Understanding-Airplane-Demand-Drop-During-Covid
Processed 1.6 million instances of Crowdsourced Airplane movement data during Covid-19 with Distributed Computing. Used Hadoop MapReduce, PigLatin, Python Dask for parallel processing. Used Tableau for data visualization.
Vector-Database
this repository contains elements needed for a successful semantic search in vector database. It utilizes sqlite3, chromadb and other techniqes to create, store, query in a vector database
cv_sorting
Scoring CV based on required skills found on job seeker's CV
DeepFaceLab
DeepFaceLab is the leading software for creating deepfakes.
dlwpt-code
Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.
fahimabrar
This one is a special repo for showing my introduction at the GitHub homepage.
Generating-Heatmap-for-Corona-Virus-Propagation-in-Python-gmaps
Covid spread data plotted with a heatmap on google maps.
Hyperparameter_Tuning
Hyperparameter tuning using gridsearchCV and randomizedsearchCV
Image_data_prep_tools
You can crop an image into the different parts and get different cropped images using this tool. Made it for image data preparation.
llama
Inference code for LLaMA models
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Web-Scrapping
web scrapping for speech transcript of Barak Obama and Donald Trump and generating word cloud with frequent words