Post Job Free
Sign in

Data Python

Location:
New York, NY
Posted:
February 22, 2021

Contact this candidate

Resume:

Subhash Madineni

********@*****.*** 716-***-**** github.com/SubhashMadineni linkedIn.com /subhash-madineni EDUATIONS AND HONOURS

University at Buffalo, School of Engineering and Applied Sciences Buffalo, NY Master’s in data science (Mps) August 2020 - Present

• Relative Coursework: Machine Learning, Data Science Statistics, Big Data Analytics, Probability & Discrete Mathematics Lovely Professional University India, PB

Bachelor of Technology (Electronics and communication) May 2020

• Cumulative GPA: 3.7/4.0, awarded Dean’s scholarship of $1000 (for top 5% of applicants).

• Relevant Coursework: Data Structures & Algorithms, Object-Oriented Programming(oops), Database management systems. PROFESSIONAL EXPERIENCE

Graduate Research Assistant – Data Engineering, Aug 2020 - Present Collage of Arts and Sciences, University at Buffalo, New York

• Gathered over 1 terabyte of unstructured data from different data sources and data lakes regarding grants awarded to researchers and made a dashboard that improved tracking efficiency by over 20% for the Dean of the College of arts and sciences.

• Wrangled and performed ETL operations on the research grants budgeting data stored in Aws S3 and 16 other database storages using Tableau and apache spark to remodel and visualize previously inaccessible datasets to allow 500+ professors and researchers to view transactions that happened in the grant's accounts.

• Presented results to the college's Dean and wrote requested executive summary detailing visualizations and dashboards to present to researchers and senior leadership.

Data Engineer Intern, Jan 2020 – May 2020

Cognizant Technology solutions, India

• Developed an interactive Machine learning application for the clients based on the data provided.

• analyzed the data in Tableau and made visualizations to present meaningful insights to the clients. Built a real-time application based on a really Huge dataset related to the Healthcare domain on AWS using Spark and other Hadoop Frameworks like hive and pig.

SKILLS

• Programming Languages: Python, R, C, C++, Java

• Big Data & Machine Learning: Spark, Hadoop, MongoDB, Python (e.g., scikit-learn, NumPy, pandas, matplotlib)

• Data Science & Miscellaneous Technologies: A/B testing, ETL, Data science pipeline (cleansing, wrangling, visualization, modeling, interpretation), Statistics, Time series, Experimental design, Hypothesis testing, OOP, OOD, APIs, Excel, Git

PROJECTS AND LEADERSHIP

Vice President

Metal Club (Lovely Professional University) Jan 2018 – May 2018

• Led team of 5 students to collaborate with technology experts (e.g., R, Python, AutoCAD) to create a total of 8 workshops, expositions, and hackathons that gathered a combined 1000+ attendees.

• Established and maintained 4 sponsorships with university faculties, companies, and other clubs. Movie Genre Prediction using PySpark (Python, Spark) May 2020

• Scored 89% accuracy in correctly classifying the genre labels of the movie given a plot using Logistic Regression implemented using PySpark’s MLLib library for distributed computation.

• Feature Engineering methods like TF-IDF, Word2Vec were employed. Sentiment Analysis of News Articles using Probabilistic Topic Modelling (Java, Python) Feb 2017 - Jul 2017

• Performed Sentiment Analysis to obtain insights about opinions expressed in news articles

• Prepared and cleaned a dataset by scraping 3200 news articles from the Internet using Scrapy and Beautiful Soup in Python

• Created a topic model of news articles using Latent Dirichlet Allocation written in Java and calculated sentiment scores of the topics using SentiWordNet 3.0



Contact this candidate