Projects

Peak Energy Prediction

The project focused on predicting and displaying the next 48 hours of energy consumption(based on half hour intervals) using various factors that may affect the energy consumption in the South West Interconnected System (SWIS) electricity grid.

Using the analytics, it was determined if the upcoming day is going to be a peak day or not. The project involved a complete data science lifecycle. The project was built using python on a Jupyter IDE incorporationg various Machine Learning algorithms.

QA Model

The project develops a Question-Answering framework using sequence model with attention mechanism. The dataset consists of questions, corresponding candidate answers, and labels indicating whether each sentence is the correct answer. Document preprocessing involves consolidating sentences into documents for each question and capturing the correct answer sentences. Various functions are defined for data processing, including tokenization, word embedding using Word2Vec-SkipGram, padding, part-of-speech tagging, lemmatization, named entity tagging, and TF-IDF calculation. These functions transform the data and generate input features for the QA model.