"Passionate data science learner with excellent statistical knowledge and the ability to identify fine points of data in a sea of information.
Able to process new data quickly and communicate it effectively to lay individuals."
Data Science Consultant Machine Learning ScientistMachine learning Engineer
About Me.
I am Swati Thapa, a dedicated professional with a Master's degree in Big Data Science. Presently, I serve as a Machine Learning Scientist at Expedia Group, where I am deeply involved in the intricate realms of machine learning. My daily endeavors revolve around crafting robust ML model architectures tailored to specific project requisites, overseeing seamless model deployment processes, and orchestrating the development of ETL pipelines for data visualization.
Engaging in insightful dialogues with stakeholders to comprehend their needs and align our strategies accordingly is an integral part of my routine.
Driven by an unwavering passion for problem-solving, I find immense gratification in addressing real-world challenges through innovative applications of machine learning. Beyond the confines of my professional domain, I harbor a profound enthusiasm for outdoor adventures. Trekking amidst nature's marvels and embracing the serenity of swimming serve as cherished avenues for rejuvenation and introspection.
In this project, I have tried getting a complete analysis of agriculture monitoring data using Tableau. I have tried making some
dashboards interactive for better visualizing. Dataset details are mentioned in my GitHub.
A library for automatic supervised training of neural models.
In this project, I have tried to control the game movement using hand gestures. Here I have used pydirectinput where I have tried to control keyboard keys which in turn control the game movement.
I have used different types of gestures namely fist, HiFi,V, and thumbs up out of which I have used thumbs up for upward movement.
In this project, I have tried to replicate industry-standard modeling and deployment.
Here I have store my data in AWS RDS(PostgreSQL) and have extracted from it for EDA and modeling. Modeling has been to done to predict the type of crop damage 0(alive), 1(Damage due to other causes),
2(Damage due to Pesticides). Later I have used flask to create it's backend and have deployed in AWS EC2 using docker.
It was a hackathon conducted by HackerEarth. The aim was to build a sophisticated Machine Learning model that predicts selling prices.
I have secured the top 5% on the leaderboard.
I have used Tableau to analyze train data for better insight into our dataset.
Later I have used RandomForest Regressor for modeling. Finally using HTML & CSS as front end and Flask as backend I have deployed the model in Heroku.
Detecting blur and clear images of Simpson's character.
Developed and deployed image classfier which can detect both clear and blur image of Simpson's character. It can classify only ten Simpsons characters. Here some character class were highly skewed. Usage of data augmentation is done.Deployment is done in Heroku.
Developed and deployed machine learning model where we had to classify different seven types of forest cover based on various parameter like elevation,soil types,slope etc. Deployment is done using heroku.
Helping new restaurants in deciding their menus, cuisine etc. This model aims at finding similarity between neighborhoods of Bengaluru on the basis of food
This Zomato data aims at analysing demography of the location. Most importantly it will help new restaurants in deciding their theme, menus, cuisine, cost etc for a particular location.
It also aims at finding similarity between neighborhoods of Bengaluru on the basis of food.
I have tried to analysis hotel booking data using matplotlib and seaborn libraries.
The Hotel Booking demand dataset (attached) contains booking information for a city hotel and a resort hotel.
It includes information such as booking time, length of stay, number of adults, children/babies, number of available parking spaces, among other things.