Pratiksha Pradhan
Data Analytics at Northeastern University
United States
Get Remote-Ready with the Anywherepro Assessment
Increase your chances of landing your dream hybrid or remote job today!
Earn your badgeExperience
Indian Institute of Technology, Roorkee
Intern
May 2021 - December 2021
● Extracted 20K+ Covid-related tweets through SNScrape to assess the impact of Covid cases on social media posting using Python
● Performed reverse geocoding through GeoPy and Nominatim to determine where in India people were tweeting more often
● Conducted analysis of the tweets through sentiment analysis in TextBlob, time-series analysis, and word clouds in NLTK
● Strengthened the visualization through an innovative spatio-temporal analysis by implementing ffmpeg and cv2 to make a video highlighting the gradual increase in the number of tweets, with mostly neutral tweets indicating Covid-related news stories
Education
Data Analytics
Northeastern University
Graduating in 2024
Certificates & Badges
No certificates or badges added
Projects
Northeastern University
● Designed conceptual data models and mapped it to a relational model to build the database for a recommerce platform
● Executed relational model via MySQL and non-relational model via NoSQL in MongoDB to query data
● Accessed the database via Python and created Matplotlib visualizations to gain insights such as monthly change in new clients
Gender Recognition Using Speech Signal Processing
•https://github.com/ppratiksha95/Gender-Recognition-using-Speech-Signal-ProcessingDelhi Technological University
● Conducted data preprocessing, used librosa and ffmpeg to produce functions to extract features from each audio sample
● Developed a deep-feed forward neural network model with five hidden layers to predict the gender of the voice input
● Facilitated the testing of the model by inputting own voice using torchaudio, IPyWebRTC, IPython, with an accuracy of 85%
Northeastern University
• Performed data visualization, oversampling, data partitioning, standardization and scaling, and dimension reduction on dataset
• Implemented machine learning models like logistic regression, gradient boost, classification trees, Naïve Bayes using sklearn along with hyperparameter tuning, recursive feature elimination, k-fold cross validation to find the best classification model
• Evaluated and visualized model performance to conclude that gradient boost is the best algorithm with a sensitivity of 90%
Languages
English
Professional
Hindi
Professional
Skills
Communication Skills
Teamwork
NoSQL
SQL
Python
Document Applications like MS Word
Spreadsheet Applications like MS Excel
Presentation Applications like MS PowerPoint
Presentation Skills
R
Tableau
Leadership
MATLAB
Datawrapper
Power BI