Subba Rao
- Data Scientist
- Fremont, CA
- Member Since Feb 22, 2023
Candidates About
|
|
Rao
SUMMARY
• 5+ years of global IT experience in Data Analytics and Data Engineering.
• Advanced Data Analytics capabilities (Exploratory Data Techniques, Machine Learning Algorithms, predictive modelling).
• Experience in integrating data, validating, data cleansing, transformation
And data visualization using R and Python.
• Hands on Experience in design, management of database using Oracle,
MySQL and SQL Server.
• In depth knowledge and hands on experience in Big Data/Hadoop ecosystem (MapReduce, HDFS, Hive, Pig and Sqoop).
• Experience in Apache Spark, Kafka for Big Data Processing & Scala
Functional programming.
• Experience in manipulating the large data sets with R packages like tidyr, tidyverse, dplyr reshape, lubridate, Caret and visualizing the data using lattice and ggplot2 packages.
• Experience in dimensionality reduction using techniques like PCA and LDA
• Experience in Descriptive Analysis problems like Frequent Pattern Mining, Clustering, Outlier Detection
• Worked on Machine Learning algorithms like Classification and Regression with KNN Model, Decision Tree Model, SVM Model.
• Good Understanding and knowledge in Tensorflow to implement ML/DL
Algorithms.
• Good knowledge in NLP and Time Series Analysis and Forecasting Using
ARIMA model in R and Python.
• Experience in developing software using Java, C (Data Structures and
Algorithms).
Education
May 2014 – Dec 2015 Master’s in Computer Science
NPU, Fremont, CA
June 2008 – May 2012 Bachelor in Information Technology
NIT, Narasaraopet, India
Work Experience
July 2017 – Present Viotalk llc
Software Engineer/ Data Scientist
· Extracted the data from Hive tables by writing
Efficient Hive queries.
· Performed preliminary data analysis using descriptive statistics and handled anomalies such as removing duplicates and imputing missing values.
· Performed Dimensionality reduction using near zero variance and correlation techniques.
· Implemented different models like Logistic Regression, Random Forest and Gradient-Boost Trees to predict whether a given die will pass or fail the test.
Aug 2015 – June 2017 Nitya Software Solutions
Big Data Engineer
• Work with business stakeholders to gather and document detailed project requirements.
• Extract, compile and analyze data to identify and interpret patterns and trends and generate meaningful insights.
· Migrate the existing data to Hadoop from RDBMS using Sqoop for processing of data.
· Used Hive data warehouse tool to analyze the data in HDFS and developed Hive quiries.
· Developed complex Map/Reduce jobs using Hive.
· Used to work with Python for mapreduce jobs in Cloudera.
· Experienced in using Machine Learning algorithms API(Spark,Scala,R) to drive useful insights.
· Using R prototype on sample large data sets exploration to identify the best algorithmic approach and then wrote scala scripts using Spark machine learning models.
· Responsible for creating Hive tables, loading the structured data resulted from MapReduce jobs into the tables and writing Hive queries to further analyze the data.
· Worked on Spark architecture and implementation in Java/Scala.
June 2012 – Feb 2014 c3 Solutins
Data Analyst
· Formulated dashboards and reports for the inventory management system. Perfectly developed and maintained SQL scripts and queries depending on the report requirements.
· Collected and analyzed the data and transforming it according to the business requirements
• Gather requirements to develop and execute detail oriented test plans and test cases.
KEY PROJECTS
Machine Learning –
· Digit Recognizer:
o The aim of this project is to correctly identify digits from a data set of tens of thousands of handwritten images.
o Applied modelling techniques such as SVM and Convolution Neural Network using Tensor Flow.
o Used Principal Component Analysis (PCA) for reducing the dimensionality of the existing data set and extracting important information.
· Leaf Classification:
o The objective of this project is to use binary leaf images and identify 99 species of leaves.
o Built algorithms to determine the species of leaf based on features such as texture, shape and margin.
o Used image feature extraction using openCV2, Feature scaling and applied modelling techniques such as Multinomial Logistic Regression, Random Forest using Python.
o Implemented Neural Network using Keras which landed me on top 11% in the Kaggle leaderboard.
· Capstone Project Compition:
o The aim of this project is to develop algorithms for lung cancer detection using thousands of Lung scans.
o Worked on 3-D visualization, numpy arrays and handling huge amount of data.
o Used Multinomial Logistic Regression and Xgboost model using python.
· Titanic:
o The aim of the project is the prediction of survival of passengers on the Titanic.
o Did exploratory data analysis, handled missing values and analysis of finding the variables with maximum importance.
o Applied various machine learning modelling techniques such as Logistic Regression, Random Forest in python.
· DengAI:
o The aim of this project is to predict the spread of Dengue based on weather and seasonal conditions.
o Used R and Time Series prediction to predict missing values and ggplot2 for visualization.
o Used Negative Binomial Regression model for prediction.
Sentiment Analysis –
· Twitter Data Sentiment:
o The aim of the project to classify a tweet as a positive, negative or neutral for 6 US Airlines.
o Created a classifier based on what features are relevant using feature extractor (NLTK function).
o Visualized the positive, negative and neutral sentiments on the WordCloud.
o Exploratory data analysis using matplotlib and seaborn packages in python.
Data Warehouse using MS SQL Server –
o Planning a conceptual model, designing a dimensional model and data mart implementation.
o ETL processes using SSIS and OLAP cube creation using SSAS.