The PlacemenTrack is a cutting-edge application that revolutionizes the way educational institutions, students, and recruiters approach campus placements. This app harnesses the power of data analysis, machine learning, and web technologies to provide a comprehensive solution for optimizing the placement process.

• Reactjs
• Material-UI
• ApexCharts (React)
• Flask
• Redhat Openshift
• Docker
• Numpy, Pandas, Matplotlib, Seaborn and Scikit-learn

We presented the insights we extracted from the datasets about campus placements.

Here it predicts the campus placement results using ML models.

Students can use this feature to predict their probability of getting placed and their predicted salary by uploading their resume.

Backend: https://hub.docker.com/r/partheev8/campus-backend

Frontend: https://hub.docker.com/r/partheev8/campus-frontend

campus-placement-analysis/
├─ frontend - React application
├─ backend - Flask application
├─ EDA_Notebooks - Contains All EDA work of this project and their datasets
│  ├─ datasets/
│  │  ├─ Predicted_data.xlsx
│  │  ├─ gdp.xlsx
│  ├─ Campus_Placements_Insights
│  ├─ Salary_Prediction.ipynb
│  ├─ Placement_prediction.ipynb
│  ├─ GDP_VS_Placements_EDA.ipynb
├─ project reports - Project Documents
│  ├─ block-diagram.png
│  ├─ flow-chart.png
│  ├─ project-report.pdf
├─ screenshots - Contains sheetshots of insights, predictions, and analytics.
├─ .gitignore

Clone the repo

• cd frontend
• npm install
• npm run dev

Note: Node runtime must be installed to run the above commands. Create .env.local file and add VITE_BACKEND_URL variable name with endpoint as value.

keep VITE_BACKEND_URL=http://localhost:5000 while running the application locally in development mode.

• cd backend
• pip install -r requirements.txt
• flask run

Note: Python must be installed in the system (v3.9+ preferred). Configure env variables in backend/.env file.

Add these enviroment variables - ML_DEPLOYMENT_API_KEY, RESUME_PARSER_API, RECOMMEND_SKILLS_API

You will need two API keys from Affinda for the resume parser and recommend skills features

1. Login to the official Affinda website

2. Create a workspace by selecting resumes under the recruitment category
  
3. Select "Generate an API Key" to generate a unique key for the resume workspace. Then, add the key to the env variable RESUME_PARSER_API.

Using the same procedures, establish a Resume Redacts workspace and update the RECOMMEND_SKILLS_API env variable with the key.

You can visit the application at http://localhost:3000 in development mode.