KSwaviman
Data Science Professional | MS in Data Science | University of Trento, Italy info@swavimankumar.com
Rome, Italy
Pinned Repositories
Authourship-Attribution
Authourship attribution with naive bayes using word and ngram
Conjoint-Analysis
This project aims to conduct a random survey design for collecting responses regarding wine preferences of Italian consumers. Furthermore, it attempts to understand how preference share gets affected as we vary different attributes associated with wine with the use of a research method called Conjoint Analysis..
Cracking-The-Personality-Code-A-Behavioral-Research
Our study focused on using the Big Five personality inventory to predict traits from students' smartphone sensor data collected over 2 months under the Horizon Europe project. Through correlation analyses and machine learning with cross-validation, we showed that predictions are reliable and accurate enough for practical use.
EDA-Clustering-Classification-on-Stroke-Prediction-Dataset
Perform Extensive Exploratory Data Analysis, apply three clustering algorithms & apply 3 classification algorithms on the given stroke prediction dataset and mention the best findings.
ETL_Meltano_framework
This project demonstrates a complete ETL (Extract, Transform, Load) pipeline that integrates data extraction from an API, data transformation and normalization, and data exposure via an API endpoint. The solution leverages Meltano for ETL orchestration, FastAPI for API Endpoint, and Docker containerization.
ImageSimilarity
Apply machine learning to find top 10 similar images from a gallery folder given a query image.
PDF-Search-with-GPT
An experiemental project to utilize LangChain and extract information from PDFs, utilizing OpenAI Text Embeddings.
Power-BI-Report
End to end Business Intelligence Solution analyzing product, sales, finance and customer data. Showases use of advanced MS Power BI concepts, nuances of pivot, hierachy, snowflake schema, DAX and many more.
Sales_Report_Analysis
Developed an SQL Server data warehouse with a 'Production' schema, enabling PowerBI reporting and sales KPI analysis.
Social-Dynamics-Project
The purpose was to study the mood of respondents, what are the predictors of mood among students with different personality types and how do these predictors vary between different time diaries.
KSwaviman's Repositories
KSwaviman/Conjoint-Analysis
This project aims to conduct a random survey design for collecting responses regarding wine preferences of Italian consumers. Furthermore, it attempts to understand how preference share gets affected as we vary different attributes associated with wine with the use of a research method called Conjoint Analysis..
KSwaviman/ETL_Meltano_framework
This project demonstrates a complete ETL (Extract, Transform, Load) pipeline that integrates data extraction from an API, data transformation and normalization, and data exposure via an API endpoint. The solution leverages Meltano for ETL orchestration, FastAPI for API Endpoint, and Docker containerization.
KSwaviman/Cracking-The-Personality-Code-A-Behavioral-Research
Our study focused on using the Big Five personality inventory to predict traits from students' smartphone sensor data collected over 2 months under the Horizon Europe project. Through correlation analyses and machine learning with cross-validation, we showed that predictions are reliable and accurate enough for practical use.
KSwaviman/EDA-Clustering-Classification-on-Stroke-Prediction-Dataset
Perform Extensive Exploratory Data Analysis, apply three clustering algorithms & apply 3 classification algorithms on the given stroke prediction dataset and mention the best findings.
KSwaviman/PDF-Search-with-GPT
An experiemental project to utilize LangChain and extract information from PDFs, utilizing OpenAI Text Embeddings.
KSwaviman/Social-Dynamics-Project
The purpose was to study the mood of respondents, what are the predictors of mood among students with different personality types and how do these predictors vary between different time diaries.
KSwaviman/Authourship-Attribution
Authourship attribution with naive bayes using word and ngram
KSwaviman/breast-cancer-wisconsin-EDA
EDA on breast cancer dataset
KSwaviman/build-your-search-engine
A repository to learn basic data processing techniques (Wikipedia processing, feature selection), and use them for some basic Web query classification.
KSwaviman/Classification-of-Patients-with-Abnormal-Blood-Pressure
Employing statistical techniques, conduct a preliminary prognosis of Hypertension/hypotension, based on the level of hemoglobin and genetic history of the individual.
KSwaviman/ImageSimilarity
Apply machine learning to find top 10 similar images from a gallery folder given a query image.
KSwaviman/Power-BI-Report
End to end Business Intelligence Solution analyzing product, sales, finance and customer data. Showases use of advanced MS Power BI concepts, nuances of pivot, hierachy, snowflake schema, DAX and many more.
KSwaviman/Recommender-System
A therapy recommender system to suggest best suitable treatments for patients based on their past medical records and other patients treatment record.
KSwaviman/Sales_Report_Analysis
Developed an SQL Server data warehouse with a 'Production' schema, enabling PowerBI reporting and sales KPI analysis.
KSwaviman/Univariate-and-Multivariate-Analysis-of-Titanic-Dataset
Univariate and Multivariate Analysis performed on the Titanic Dataset
KSwaviman/Computational-Gastronomy
This simple project is focused on Computational Gastronomy & combines elements of data analysis, natural language processing, and information extraction. The assignment covers several tasks that involve working with recipe data and analyzing it using Python.
KSwaviman/Enterprise-ELT-Framework
Enterprise ELT Framework using Airbyte, dbt, Prefect, and Power BI for seamless data extraction, transformation, and visualization. This project showcases a scalable pipeline integrating SQL Server, GCP, and tabular models in Power BI for real-time analytics and business intelligence. Ideal for data engineers and analysts seeking efficient ETL/ELT.
KSwaviman/ETL_with_Airbyte
This project showcases an ELT pipeline that extracts JSON data, loads it into a PostgreSQL database, applies transformations using Python scripts, saves the transformed data in a CSV file, and shares it through a FastAPI endpoint.
KSwaviman/Hello-World
This is a little description about my new hello world prog. Thank you for reading this.
KSwaviman/Kswaviman
My Github Readme page
KSwaviman/NLP-Basics
This is a tutorial that covers the basics of NLP. We will cover few rudimentary operations such as tokenization, stemming etc. Happy learning.
KSwaviman/PySpark-Tutorial
This is a tutorial that covers the basics of PySpark. We will cover few rudimentary dataframe operations such as withColumn function, when, otherwise etc. Happy learning.
KSwaviman/Sparse-Representation-based-Classification
The idea behind SRC is that, instead of using a single feature vector to represent an input, multiple sparse representations are used, each one capturing a different aspect of the input.
KSwaviman/SVMs
Predicting Alzheimer from people's writing. Technique: SVMs.