This project is undertaken by three sophomores from IITB, as a part of the DS 203 Course curriculum project, under the guidance of Prof. Amit Sethi, Prof. Manjesh Hanawal, Prof. S. Sudarshan and Prof. Sunita Sarawagi.
This project has 4 .ipynb files - EDA_countries(1).ipynb, EDA_countries(2).ipynb, Classification_ICU.ipynb, EDA+Regression_IND.ipynb . There is no folder/ hierarchy required for the files. All the datasets will be downloaded from Google Drive automatically, when the ipynb files are loaded and run on Colab.
This project aims at analysing Covid-19 data worldwide, and explaining various possible reasons for the observations. We have implemented Linear, Polynomial, Ridge, and Lasso regression models to predict the number of deaths due to COVID-19 in India, given the historical data. We have also implemented ML models to predict whether a person might need admission to ICU or not, given their various health parameters. We have undertaken extensive exploratory data analysis to explore multiple relations and trends between various data features and their interdependencies. Hypothesis Testing was done and χ2 Contingency test was used to assert dependency of features. Five classification techniques have been used - Logistic Regression, SVM Classifier, MLP Classifier, Random Forest Classifier and Gradient Boosting Classifier.
The sources and links to datasets, contribution of team members and acknowledgements are provided in the report along with the other sections.