Skip to content

aliduku/COVID-19_Case_Prediction_App

Repository files navigation

COVID-19_Case_Prediction_App

Kaggle Notebook

https://www.kaggle.com/code/aliessamali/covid-19-data-analysis-and-prediction-on-data-api/

Streamlit Web Application

https://covid-19casepredictionapp-kje9ropaqfuekhjdhyqgng.streamlit.app/

Info

Description

In this project, I embarked on a comprehensive analysis of COVID-19 data, leveraging a chosen API containing both valuable information and noise. Starting with data collection using Python, I stored the data in a Pandas DataFrame and meticulously cleaned it by removing irrelevant columns, handling null values, and eliminating duplicates. The pre-processing phase involved normalizing and scaling the numerical data, ensuring accurate model training.

Key Steps and Achievements:

Data Collection and Cleaning: I gathered COVID-19 data from a chosen API and organized it into a Pandas DataFrame. The data underwent thorough cleaning, ensuring data quality and reliability for subsequent analysis.

Exploratory Data Analysis (EDA): Through EDA, I unveiled trends, correlations, and patterns within the data. Visualizations such as histograms, scatter plots, and heatmaps were employed to provide meaningful insights into COVID-19 trends.

Supervised Algorithm Selection: I identified and selected the most suitable supervised algorithm for predicting future COVID-19 cases. Techniques like train-test split, cross-validation, and grid search were employed to fine-tune the model's performance.

Streamlit Deployment: Leveraging the Streamlit library, I deployed a user-friendly interface enabling users to input data and view the model's predictions. This interface facilitated interactive exploration of COVID-19 predictions.

Bonus Achievement:

I enhanced the project's impact by deploying the Streamlit app using Streamlit Share, making the application accessible to a broader audience and contributing to data-driven decision-making during the ongoing pandemic.

Through this project, I showcased proficiency in data collection, cleaning, EDA, model selection, and user interface development. By providing a streamlined way to interact with and predict COVID-19 trends, I contributed to informed insights and empowered users to make informed decisions.

About

COVID-19 Case Prediction App

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published