Gaurav Rajesh Sahani's repositories
Invoice-Data-Extraction-Gemini-Pro-LLM
The Invoice Data Extractor simplifies extracting key info from invoices using advanced OCR and AI, powered by Gemini Pro Vision and a Large Language Model. It transforms invoice images into structured data effortlessly, hosted locally via Streamlit.
Kaggle-Datasets
This Repository is created to showcase my work on the Datasets, downloaded from the Kaggle, since Kaggle is the platform, from which i have learned many new things, as well as implemented them, in my work.
Mask-Detector-Deep-Learning-and-Open-CV-Project
This project deals with Mask Detection, using Deep Learning model, trained using Convolutional Neural Nets, augmented with Open-CV, with Haarcascades for face and eyes detection, using Streamlit.
Hollywood-Movie-Recommendation-Deployment
Deployed Hollywood Movie recommendation Web-Application on Heroku. Please Have a look at the Description Below, for more information, and the Web-Application Link. Thank-you.
Covid-19-News-Classifier-and-Symtom-Predictor
The project and Web-application “Covid-19 News Classifier and Risk Predictor”, consist of two sections, namely as “Covid-19 News Classifier” and “Covid-19 Risk Predictor”, as seen in the abstract section. The only intention behind this Project and Web-application is to contribute a part of safety from the Covid-19 outbreak, also encouraging to stay home and stay safe
Forest-Fire-Prediction-Streamlit-application
This Application, gives the prediction whether the Forest is safe or Un-Safe from Fire Occurrence, depending on the features like Temperature, Humidity and Oxygen Content in Air, Used the basic Decision Tree Classifier to train the model, Later used the Streamlit library and Flask Framework for the deployment Purposes on Heroku, which is the Cloud Platform as a Service.
Indian-Currency-Notes-Predictor-App
Deployed Deep Learning, Indian Currency Note Predictor, used the Resnet50 at first, but did not achieved a good accuracy, later, tried making a Convolutional Neural Net, got a better Accuracy predicting 7 classes, considering all running Indian currency Notes, Later Deployed it Locally, and then on Heroku Platform.
Wine-Quality-Model-Deployment
In my Wine Quality Prediction Model, firstly took the dataset from Kaggle Datasets, trained it efficiently with appropriate EDA, and predicted the model, using CatBosstClassifier Algorithm, got accuracy around 85.98%, Deployed it locally using App.py and Html files, So basically, By inserting various parameters like, pH levels, Type of Wine, Acidity content, sulphate content, my model Predicts the Quality of the wine, within the range of 1 to 10.This Model can be efficiently used by the Wine Testers, in order to predict the quality of Wine, in production.
Flower-Classification
This is a Streamlit app use for prediction of the 102 types of flower.
Machine-Learning-Model-on-Breast-Cancer-Data
In this repository, I am added a 10 machine learning classification model for breast cancer dataset classification.
PySpark-Basic-Implementation
This repository is saved to share the work regarding basic implementation with PySpark. While, PySpark is an interface for Apache Spark in Python. It not only allows you to write Spark applications using Python APIs, but also provides the PySpark shell for interactively analyzing your data in a distributed environment. PySpark supports most of Spark’s features such as Spark SQL, DataFrame, Streaming, MLlib (Machine Learning) and Spark Core.
Machine-Hack-Workathon
This repository is saved to showcase my approaches towards dealing with MachineHack Workathon Price Prediction hackathon! Do star the repository if it was helpful!
Python-Practice-Codes
This repository is saved in order to save the python practice codes, which are useful for anyone to brush-up the python concepts.
Recommendation-System
This repository is specifically for the recommendation systems, for Movies using Weighted Average method, which was used in 2001's, and Content Based Recommendation System, which is used nowadays extensively, also for Books, I have used KNearestNeignbors principle for Recommending Books.
Kaggle-Playground-Series-March-2021
Repository Saved to display work for Kaggle competition Playground Series-March 2021".
Credit-Card-Fraud-Detection.
Credit Card Fraud Detection, dealing the imbalance data with, Isolation Forest Algorithm as well as, Outlier Detection algorithm, which worked really well handling largely imbalance dataset, giving accuracy of around 99.45% respectively.
Auto-Exploratory-Data-Analysis-EDA-Libraries-with-Python
This repository is saved to display some of the amazing libraries which serve the purpose of Automated Exploratory Data Analysis i.e. EDA. I have experimented with libraries like Python Profiling, Auto-Viz, and Sweet-Viz Automated libraries.
Ap-Script-Hackathon-Brute-Force
This repository is saved to display the work for the ApScript Hackathon
NLP-Using-TextBlob
Experimented with the amazing NLP Library TextBlob. It provides a simple API for diving into common natural language processing (NLP) tasks such as part-of-speech tagging, noun phrase extraction, sentiment analysis, classification, translation, and more. I have experimented with various features of TextBlob and presented in form of Colab Notebook.
Simple-Iris-Classifier-Web-App-using-Streamlit-Youtube
This repository is saved to share the Resources for my Youtube Playlist "Creating Simple ML Web-Application using Streamlit".
intel
Course: AI From the Data Center to the Edge - An Optimized Path Using Intel® Architecture
Language-translation-with-Python-Google-API
This repository is saved to share the code regarding language translation using translate which is API Supported by Microsoft and MyMemory API and Google translate API, I have tried to explain the code in simplest manner possible. This code can be served as a snippet for other APIs, projects and various applications.
Kaggle-Competitions-Approaches
This repository is created to share my approaches for Kaggle competitions.
Kaggle-Playground-Series-Top-10-
This repository is saved to share the work regarding the Kaggle competition "Kaggle Playground Series". I have used various approaches experimenting with EDA, Various models with hyperparameter tuning, used Optuna for tuning the hyperparameters.
Rock-Paper-Scissors-Kaggle-Simulation-Competetion
In this Kaggle simulation competition, I have created an AI Model to play against others in many rounds of this classic game.
Data-Science-Interview-Resources
This repository is created to open source and share some of the Data science Interview resources with the community. Some of the questions are added based on my own experience. Hope this content serves helpful