This is a Machine Learning-based prediction project in which the task is to predict whether a student may get placed or not on the basis of different academic factors.
Steps involved in implementation of this project are -:
- Exploratory Data Analysis(EDA)
- Data Preprocessing and Feature Extraction
- Data Visualization
- Model Training
- Evaluation
- API development
- Deployment
Tools and Technologies used -:
- Cassandra Database - For dataset
The dataset contains a total of 215 non-null rows and 15 columns.
- Pandas - EDA
- Scikit-Learn, Scipy and StatsModels - Data Preprocessing and Feature Extraction
- Matplotlib and Seaborn - Data Visualization
- Logistic Regression - Final model training(best model chosen)
- Scikit-Learn Metrics - Evaluation
- Streamlit - For User Interface development
- Streamlit Cloud - Deployment
Database Link -: https://astra.datastax.com/org/0dd23226-b7a5-45db-9a1d-73ce17d26290/database/35d88150-d1f8-48c5-a5ef-3409fb0a3339
On clicking submit button at bottom,
We get the output as Placed/Not Placed -:
