Srinivasreddy H

Designed and implemented end-to-end data processing pipelines using Python, leveraging libraries such as pandas, numpy, sklearn and matplotlib. Conducted exploratory data analysis (EDA) on datasets to identify patterns, trends and actionable insights. Built predictive models and data visualizations to support data-driven decisions. Ensured code quality, maintainability and reproducibility following best practices in version control (Git) and documentation.

Content classification using Machine Learning and NLP techniques that allows a model to classify by extracting the text from the websites. Implemented zero-shot text classification with Hugging Face Transformers facebook-bart-large-mnli. Performed CRUD operations and data management in MongoDB. Developed Python scripts for data extraction, processing and analysis. Utilized pandas, beautifulsoup, requests, pymongo and transformers to develop efficient data extraction, processing and analysis workflows.

Built a predictive model using various machine learning tools to predict the possible date of refrigerator malfunction. Recommendation system for the movie industry which recommends movies to the user. Used Beautifulsoup and requests libraries for scraping the data, pandas library for data preprocessing, random forest algorithm from sklearn library for modeling and deployed using the flask framework, html and css.

Part of Named Entity Recognition (NER) project, extracting person names, geolocation entities from raw text. Identify person name, street name, area, city, state and country using trained ML/DL models.

Part of the Acoustic Detection project where Machine learning and Deep learning models were used to analyze the audio data and detect the label present in the clip. Collaborated with the Data science team for training and validating Machine learning and Deep learning models. Developed python script from scratch for Web scraping a website to download audio data and store the audio data information in a csv file. Data preprocessing which involves removing irrelevant data like silence in audio data. Developed python scripts for data cleaning and analyzing the data samples with python scripting.