Post Job Free

Resume

Sign in

Data Science, SQL,Python, PowerBI, Tableau

Location:
Boulder, CO
Posted:
March 31, 2024

Contact this candidate

Resume:

Vishadh Sawant

Contact: 1-425-***-**** Email: ad4o4i@r.postjobfree.com Location: Boulder, CO, USA

GitHub LinkedIn

Strong Computer Science background, hands on project experiences, & strong object-oriented skills Education

University of Colorado Boulder Aug. 2022 – Present Master of Sciences in Data Science, Specialization in Geographic Information System GPA: 3.7 / 4.0 Fr.C.Rodrigues Institue of Technology, Vashi, India (Mumbai University) Aug. 2018 – June 2022 Bachelor’s of Engineering in Computer Engineering GPA: 8.7 / 10.0 Skills

• Technologies: Python, C, Java, R, HTML, Verilog, CSS, SQL, PowerBI, Tableau, Visual Studio, MS Office, MYSQL, NumPy, Pandas, Matplotlib, Seaborn, Scikit-learn, Matlab.

Professional Experience

Tata Institute of Fundamental Research (TIFR) Mumbai, MH, India Software Intern July 2021 – July 2022

● Developed Multichannel time to digital converter (TDC) machine which improved time-based accuracy of cosmic particles nature detection by 18% (from 2.5 nanosec to 0.45 nanosec) coupled with bespoke coarse counter computer code. (Verilog, FPGA board)

● TDC machine did parallel processing & fast integration with UART module which improved institute’s GRAPES-3 experiment capability to process data faster.

Sparks Foundation (Non-profit Bootcamp NGO) Mumbai, MH, India Project Intern Feb 2022 – March

2022

● Developed banking system webapp for self-learning & shared the project learnings with NGO community via linked post. (PHP, SQL, HTML)

Achievements

Teaching Assistant in Algorithms: Awarded teaching assistant scholarship by university based on academic performance for year 2022- 2023.

Recognition Certificate: Received recognition certificate from TIFR for internship work on developing a Multichannel time to digital converter.

Research Paper: Published research paper on “Implementation of Multi-Channel Time-to-Digital Converter using FPGA” in IEEE conference. The paper was selected as one of the top 10 for presentation out of 304 paper submissions. Projects

Fake News Detection (Python Flask, HTML, CSS)

● Created fake news detector Machine Learning model which achieved accuracy of 98% on Kaggle news dataset by performing stemming, tokenization as preprocessing to improve accuracy and using Gradient Boosting algorithm for prediction.

● Developed a Webpage to improve User experience to use fake news detector by taking NEWS URL as input and showing the results of the prediction of fake news detector with confidence rating. Pneumonia Detection (Python, Seaborn, Scikit Image, Tensorflow, Keras, Numpy, Pandas)

● Developed algo to detect Pneumonia on Kaggle image dataset by preprocessing using median-blur filter, edge detectors to improve detector performance and used image segmentation for detection.

● Compared results with Neural Network to understand performance results of Neural Network with traditional computer vision methods.

Music Recommendation System (Scikit Learn, Pandas, Seaborn, YoutubeAPI, Google Sites)

● Built machine learning recommendation system by achieving 95% by implementing Naïve Bayesian algorithm.

● Developed website “music-recommendation” for data visualization by plotting graphs to understand data & system performance. Business Intelligence Project (Google BigQuery)

● Helped business team understand how customers(cyclist) use the product(bike) by generating a CSV file using ETL BigQuery workflow which gave insights about cyclist and their bike location.

● Created real-time Tableau visualization dashboards for making business decisions to setup new bike stations by using BigQuery ETL data pipeline to continuously load data into Tableau to achieve real time visualization of bicker location. SQL querying (Google BigQuery, Tableau)

● Wrote SQL queries which included nested queries, aggregations, Joins on School database to get insights school performance by using Python SQLITE to connect to IBM database and visualizing results and some in memory data transformation using Pandas. Pysaprk ETL (Spark, Python, ETL, SQL)

● Created ETL data pipeline using Spark SQL for continuous data processing by implementing Change Data capture sourcing data from multiple data sources and loading into target destination.



Contact this candidate