Nishith Patel

I am currently a MS student in Computer Science from UC Riverside and I will be graduating in 10th December 2022. I have hands on experience with OOP languages like Python, Java, C++. DataBase like SQL, NoSQL, MongoDB, Azure, Cloud. Dashboards such as Tableau, Power BI, Google Analytics, Microsoft Excel. Tools I have used in my career are GoogleColab, Panda, Visual Studio Code, Sublime Text.

Tableau Personal Projects Jan 2021 – May 2021

Project Name: Covid 19 Analysis and Dashboard (World and India)

· Created a project on Covid 19 Analysis by taking a dataset from Kaggle for the whole world and India.

· Analyzing Data and creating different visualization in Tableau such as Confirmed Covid 19 cases in the world, Recovered Covid 19 cases in the world, Variation of Covid 19 Cases in the world.

· I faced some difficulties in Visualizing some data based such as Trend Line of Covid 19 in the whole world and in India. Also, I created a Covid 19 forecast to analyze how C19 has improved over the span of 1 year.

· I came up with that idea that there was some fault in the dataset as it was not cleaned properly so I cleaned that data using data frame and libraries such as pandas and then visualized my data after that and got my results.

From that dashboard we can predict the variation of C19 in next coming years.

Project 1: YouTube Trending Video Analysis | Data Mining | UC, Riverside | (Link) - Sept 2021 – Dec 2021

· Project Idea with datasets: The datasets were taken from Kaggle of different countries all over the world.

· Machine Learning models used: XGBoost, KNN, Random Forest.

· Predicted the accuracy of the data collected using Machine Learning models.

· Work done on Data: Data was cleaned, preprocessed, Visualize, correlating features with each other.

Project 2: Facial Expression Detection using CNN | Deep Learning | UC, Riverside - April 2022 – June 2022

· Project Idea: The datasets were taken from Kaggle of some random facial expressions.

· These data were raw images which were then converted to final images black and white.

· We applied CNN for facial expression detection of expressions such as happy, sad, confused etc.

We also predicted the accuracy of our model which came out to be 98%.