Manideep Sai

Experience

1. Data Scientist

   Carnival Cruise Line

   Sep 2021 — Present · FL, US

   Analyzed the data to be migrate and performed various analysis as per the client requirement.• Wrote Spark applications for data validation, cleansing, transformation, and customaggregation. • Participated in the development improvement and maintenance of snowflake database applications,• Developed a UNIX shell script to export all theDatabases DDL’s on the prem hive and imported and created them on the Azure Data Lake storage (ADLS) Gen1.• Developed aPySpark applications to copy the data from on-prem data lake to the Azure data box.• Hands on experience on analytics services such as Glue, Athena.• Performed independentanalysis on sensor data using Pandas, NumPy, Matplotlib, PyPlot• Designed and implemented data models and reports in PowerBI to help clients analyze the data to identify market trends, customer behavior, and competition.• Created various visualizations e.g. Clustered Barchart, Scatterchart, Piechart, StackedBarchart, Clusteredcolumn, Mapetc… in PowerBI as per the requirements.• Performed model validation using test, and validationsets via K-fold cross validation, statisticalsignificancetesting,• Involved in converting HiveQL/SQL queries into Spark transformations using SparkRDDs, Python.• Worked on developing ETL processes to load the data from multiple data sources to HDFS using FLUME and SQOOP, also performed various modification to existing HIVE scripts.• Configured EC2 instances and configured IAM users and roles and created S3 data pipe using Boto3 API to load data from internal data sources.• Experience developing Spark applications using SparkSQL in Databricks for dataextraction, transformation, and aggregation from multiple file formats for analysis and transform the data to find the customer usage patterns