Hello, World.

I'm Pratik .

Data Science Engineer Cloud Architect Competitive Coder Big Data Developer

More About Me

Let me introduce myself.

Pratik Domadiya Picture

"Lad with a million dreams."

Profile

Artificial Intelligence & Data Science Developer In Toronto ON, CANADA, with a passion for data Engineering, visualization, Machine Learning and ETL data pipeline building With a team-oriented attitude, I am eager to contribute insightful, high-quality data analytics and visualizations, data modeling, and experimentation to enhance the experience of Organization's user, business efficiency, strategic goals, and profit. Also excited to apply my passion for data science to the collaborative efforts on insightful, high-quality data analytics and visualizations.

Skills

Languages Known:
English :
Read, Write, Speak : Native
Hindi :
Read, Write, Speak : Native
Gujarati :
Read, Write, Speak : Mother Tongue

  • Python | SQL | AWS
  • Machine Learning & AI | Big Data
  • Spark | Hive | Hadoop | kafka
  • Data Governance & Control
  • Data Modeling & Quality Testing
  • Git | AWS | DBT cloud | Airflow
  • Data WareHouse | ETL
  • Power BI | Tableau | MySQL
  • Scikit-learn | Tensorflow | Keras
  • Sqoop | oozie | impala | hdfs
  • Data Visualization & Analytics
  • Statistics & ML Modeling

More of my Credentials

Education

Post Graduation

LOYALIST COLLEGE IN TORONTO, ON, CANADA
Artificial Intelligence & Data Science

Completed Post-graduation with specialization in Artificial Intelligence & Data Science at Loyalist College In Toronto, ON, Canada.

Bachelor's Degree

DHARMSINH DESAI UNIVERSITY
Information Technology

Completed B.Tech. Degree specialization in Information Technology at Dharmsinh Desai University, Nadiad, Gujarat, India.

Work Experience

Data Engineer

Sept 2023 - Present

The Marketing Store
Toronto, Canada.

  • Technologies : Python, AWS, SQL, (CI/CD), Snowflake Cloud, DBT Cloud, Apache Airflow, Tableau, Spark, Scala, Hive, HDFS, Data Warehousing
  • Builds and Re-designed ETL data models and data architecture for McDonald’s Sales, Supply Chain and Marketing data that improve accessibility, efficiency, governance, and data quality.
  • Actively engaged in developing, testing, and maintaining data architectures for data platforms, Cloud databases (AWS, Snowflake), and analytical, or data science systems.
  • Built and Improved ETL Automation with an advanced distributed SQL query engine for big data using AWS Athena, AWS Lambda, AWS Glue, AWS step functions, S3, AWS RDBMS, Python, Pandas, Numpy, Pytest Framework, Project Documentation, Code Review, and Analysis to Refactor and Automate old Manual ETL/ELT Data workflow.
  • Developed Automation Unit testing Framework and Data validation framework.
  • Working on Data-driven and event-driven architecture to build robust ETL Data systems.

Data Engineer/scientist

Jan 2022 - Sept 2023

Blue Valorem IT Solutions
Toronto, Canada.

  • Technologies : Python, AWS, DBT Cloud, Apache Airflow, Tableau, Spark, Scala, Hive, HDFS, Data Warehousing
  • Created a data pipeline to gather sales information including product, price, date, and location from multiple sources, including transactional databases and customer feedback.
  • Conducted data cleansing tasks such as handling missing or inconsistent data, converting data types, and eliminating duplicates to ensure data quality for further analysis.
  • Utilized Python libraries like Matplotlib and Seaborn for exploratory data analysis, employing visualizations such as line charts, scatter plots, and histograms to uncover patterns and trends in the data.
  • Leveraged machine learning algorithms, regression analysis, and Decision Tree models to forecast product demand and predict future sales based on historical data.
  • Developed marketing strategies by utilizing Big Data processing tools like Spark and Hive QL to analyze marketing data and provide insights for the marketing team.
  • Presented actionable insights to the business through Tableau dashboards, showcasing real-time sales data, visualizations of sales trends, and future sales forecasts.
  • These insights facilitated optimized inventory management, pricing strategies, and targeted marketing campaigns to maximize profitability and foster business growth.

Team Lead, Data Engineer

May 2020 - Oct 2021

Wholetex
Gujarat, India

  • Technologies: Python, SQL, Spark, AWS, SQL, Kafka, Sqoop, Hive, Flutter - Mobile App development.
  • Introduced an automated Python script that extracts data from predetermined websites, performs transformation and cleansing, and stores it in a MySQL database for production use. This initiative significantly reduced manual work by 35% and resulted in an 18% reduction in overall annual costs.
  • Developed a cross-platform mobile application using the Flutter framework, resulting in increased vendor responses and surpassing the previous highest sales record by 20%.
  • Leveraged Spark Streaming with Kafka to ingest a stream of data into a Hive table, making it accessible through Impala. Imported data from various remote sources, including REST API calls, LFTP, SFTP, and SSHFS, into HDFS/Hive tables for further processing and analysis.
  • Utilized Sqoop to extract data from relational databases such as Oracle, DB2, and SQL Server, and loaded it into HDFS. Scheduled workflow management using Oozie and made the data available for BI reporting through MicroStrategy integration with Impala.
  • Developed test scripts to support test-driven development practices and enable continuous integration for the project.

Machine Learning Engineer - Research Project Intern (Deep Neural Network)

Jan 2020- April 2020

Physical Research Laboratory
A Unit of Dept. of Space, Govt. of India , Ahmadabad.

  • Developed Database of satellite images (Solar Observatory Image Dataset), cleaned it using python libraries, applied image processing on dataset, built Deep learning model for prediction of solar flares.
  • Applied concepts of Hybrid Convolution Neural Network, Auto Encoder, Keras/Tensorflow, Automation tool-Selenium Web Driver, Image Processing, Jupyter Notebook and Google Colab, Python 3, gained experience related to Real Industrial Work, Team work, & Presentation Skills.
Data Science Portfolio

Check Out Some of My Projects.

These Projects have helped me develop my Skills and understand the Industry better.

Look at My Accomplishments

"Proudly Displaying My Portfolio Achievements and Successes"

80

Crazy Ideas

150

Coffee Cups

720

Hours
Contact

I'd Love To Hear From You.

Feel free to Contact Me:

Sending...
Your message was sent, thank you!
Where to find me

Scarborough, Toronto, ON
M1P 3Y7, Canada.

Call Me At

Phone:+1 (437)988-5922