Kanishk KUMAR

Data Scientist familiar with gathering, cleaning and organizing data for use by technical and non-technical personnel. Highly organized, motivated and diligent with significant background in Data Science, Machine Learning and Python Language field. A hardworking and passionate job seeker with strong organizational skills eager to secure an Associate Analyst position with 1+ total years of experience

Health and Medicine Assistant Chatbot Project [Skill Hackathon] - Moscow, Russia 11/2022 - 02/2023

• It based on Dialog Flow Framework(DFF) using Dialog Flow Engine (DFE) allows you to write conversational services such services chat-bots for social networks.
• It having Data folder and Data files and 6 Different Languages.
• It take the response for User by Medical Chatbot Services. Create mainstream languages in English & non-mainstream languages in Spanish, Dutch, Russia, Danish and Greek.

MLflow Docker Flask-Iris-Classification Application Project [Large Scale Machine Learning] - Moscow, Russia 03/2023 - 05/2023

• This is an Iris Flower Classification model deployment project as a Flask Application.
• Build an image (Dockerize) and run it on a Docker container.
• MLflow Architecture model - MLflow Project, Tracking, Models and Registry
• Asynchronous Celery library for building distributed message queue applications.
• Deploying a Machine Learning model to production and Exploratory Data Analysis With Iris Flower
• HTML Frontend Web browser and Flower Measurement Data predictions.

Advanced Python Spark DataFrame and HDFS RDD Project [Outbrain Click Prediction] - Moscow, Russia 01/2023 - 03/2023

• Use Hadoop Distributed File System for data load and processing.
• HDFS RDD for the transformation of data procedure and collection.
• To Analyse the Data with Spark DataFrame with Pyspark and SQL.
• Calculate the most visited document and topic identity in the page views data.
• Calculate users have different traffic sources in the page views data and its encoded data.

Modern Data Analysis Machine Learning Project [IMDb movies Dataset] - Moscow, Russia 09/2022 - 10/2022

• K Neighbors Classifier, Decision Tree Classifier and Logistic Regression Model.
• Ski-Learn library of features are metrics, accuracy score, classification report, confusion matrix and model selection.
• Data Visualization techniques & tools: matplot library, seaborn scatter plot library, cross validation metric.

SQL Sales Planning and Evaluation Project [Analysis Bike Production] - Moscow, Russia 05/2022 - 08/2022

• Relational Database for plan Data Management, Data Manipulations, Plan management, Materialized Views, Data Description Language(DDL)
• SQL Query with avg, max, count function, etc
• SQL Operators and Clauses, Join, Views, table
• Environment: PostgreSQL, Dbeaver

Python Advanced CountVectorizer Project [Tf-Idf] - Moscow, Russia 10/2021 - 12/2021

• Convert a collection of text documents to a matrix of token counts using Advanced Python Language and Library.
• Method: Term frequency and inverse document frequency