Performed Data Ananlysis on 'Data Scientist Jobs' Data Set. I have done Data Cleaning, Statistical Analysis and Data Visualization using Python's Pandas, Numpy libraries for data cleaning and analysis; Matplotlib, Seaborn and Ploty for data visualization.

• Kaggle Notebook
• July 2020

#MakeOverMonday2021 provides opportunity to perform visualisations by providing interesting topic to work on every Monday! This is my attempt in visualization of "Perceived Obstacles to Gender Equality”. #IronViz

• Tableau Dashboard
• February 2021

Performed exploratory data analysis on a super store’s data to gain useful insights about the store’s sales. Visualization tools like Matplotlib, Seaborn and Plotly were used to display the information obtained by Performing EDA. Trained a time series analysis model, SARIMA using the pre-processed data to predict the future sales of the store.

• Github Repository
• August 2020 - September 2020

Trained a Machine Learning algorithm that uses expert- annotated knowledge base created by researchers that has manually annotated thousands of mutations as a baseline. Developed a system to automatically classify genetic variations and to correctly classify new mutation data after training the machine learning models on original dataset. This model is able to distinguish between driver (cancer-causing) and passenger (neutral) mutations. This system will speed up the time-consuming process of recognizing cancer cells and thus provide a personalized treatment.

• Github Repository
• Date: January 2020 – April 2020

Given a tweet, a machine learning model, Logistic Regression was trained that classifies whether the message generated from the tweet is positive, negative or neutral, and for the messages conveying both positive and negative sentiment, whichever is the strongest should be chosen.

• Github Repository
• January 2019 - April 2019