• Designed and managed API system deployment using fast HTTP server and Amazon AWS architecture• Setup database in AWS using RDS and configuring backups for S3 bucket.• Experience in setting up Elastic Load Balancers (ELB's) and Auto Scaling groups on Production EC2 Instances to build Fault-Tolerant and High Availability applications.• Developed entire frontend and backend modules using Python on Django Web Framework.• Used Python and Django creating graphics, XML processing, data exchange and business logic implementation• Utilized PyUnit, the Python unit test framework, for all Python applications.• Designed and maintained databases using Python and developed Python-based API (RESTful Web Service) using Flask, SQLAlchemy, and PostgreSQL.

• Identified the dimension, fact tables and designed the data warehouse using star schema.• Developed Multi-Dimensional Objects (Cubes, Dimensions) using SQL Server Analysis Services Stored and retrieved data from data-warehouses using Amazon Redshift.Wrote a Python library built on NumPy and sklearn to detect errors on daily reports. Debugging the spark code using local and in cluster mode.Applied various machine learning algorithms and statistical modeling like decision tree, logistic regression, Gradient Boosting Machine to build predictive model using scikit-learn package in Python.Worked on machine learning on large size data using Spark and MapReduce.Successfully migrated the Django database from SQLite to MySQL to PostgreSQL with complete data integrity.Parsing various format of files like XML, JSON format files and load into Oracle database with Python XML and JSON modules.

• Performed Data Integration, Extraction, Transformation, and Load (ETL) Processes• In preprocessing phase, used Pandas to remove or replace all the missing data and balanced the dataset with Over-sampling the minority label class and Under-sampling the majority label class to perform a well Data Cleaning Process.• Developed models relying on Linear Regression, Multiple Regression, Decision Trees, Random Forest, Logistic Regression, Naive Bayes.• Validated and selected models using k-fold cross validation, confusion matrices and worked on optimizing models for high recall rate and Implemented Ensemble models like Boosting and Bagging.• Provided data mining solutions on Association Rules, Classification and Clustering problems.• Used Python to identify trends and relationships between different pieces of data and drew appropriate conclusions.• Developed Rest API to serve the data generated by prediction model to serve other customers/teams.• Generated complex reports in various formats such as list reports, summary reports etc. using advanced data manipulation techniques from SAS Enterprise Guide.