This repository contains a jupyter notebook, pickled model, readme_explore file, a kaggle csv file,training set,test set and a pickled lsvc model. the programming langauage used is python 3 using comet_ml version control and streamlit for model deployment. all the files are from student team's work on classification using machine learning under the EXPLORE DATA SCIENCE ACADEMY
A model needed to be built to enable classification of texts from a given dataset concerning a certain problem statement
Many companies are built around lessening one’s environmental impact or carbon footprint. They offer products and services that are environmentally friendly and sustainable, in line with their values and ideals. They would like to determine how people perceive climate change and whether or not they believe it is a real threat. This would add to their market research efforts in gauging how their product/service may be received.
We used a dataset which has a collection of tweets on climate change and we used NLP(Natural Language Processing) to help extract information from the data that enabled us to build a model that would classify if a twitter user was pro,anti, neutral on climate change. this would give the client an insight on their consumer base's bbeliefs and sentimets concerning climate change and and help with their future marketing strategies and product launch
For version control and collaboration we used github in conjuction with comet_ml to help keep track and record our experiments
We used streamlit to deploy our model, there is a REAME.MB file titled README_EXPLORE that explains and demonstrates how the model deployment process works and its requirements
The work was from a contributive collaboration from these team members
Justice Oyemike
David Odimegwu
Rachael Njuguna
Molapo Kgarose
olamide oladipo